Method and apparatus for manipulating a container and other types of objects, such as parcels and/or slip sheets, using a robotic end effector of a mobile robot are provided. Image data representing one or more parcels and one or more containers is used to identify a first container located a first position in an environment of a mobile robot.
Method and apparatus for manipulating a container and other types of objects, such as parcels and/or slip sheets, using a robotic end effector of a mobile robot are provided. Image data representing one or more parcels and one or more containers is used to identify a first container located a first position in an environment of a mobile robot.
The mobile robot is controlled to pull the first container to a second position in the environment using a hook assembly coupled to a vacuum-based gripper of the mobile robot. When the first container is located at the second position, the vacuum-based gripper is activated to grasp a second container using at least one vacuum assembly of the vacuum-based gripper.
A robotic foot sensor for a mobile robot is described. The robotic foot sensor includes a member including a set of passive sensing elements, and a set of active sensors communicatively coupled to the set of passive sensing elements.
B62D 57/032 - Véhicules caractérisés par des moyens de propulsion ou de prise avec le sol autres que les roues ou les chenilles, seuls ou en complément aux roues ou aux chenilles avec moyens de propulsion en prise avec le sol, p. ex. par jambes mécaniques avec une base de support et des jambes soulevées alternativement ou dans un ordre déterminéVéhicules caractérisés par des moyens de propulsion ou de prise avec le sol autres que les roues ou les chenilles, seuls ou en complément aux roues ou aux chenilles avec moyens de propulsion en prise avec le sol, p. ex. par jambes mécaniques avec des pieds ou des patins soulevés alternativement ou dans un ordre déterminé
3.
Neural Network Architectures with Multiple Normalization Layers for Machine Vision
One example aspect of the present disclosure is directed to a neural network for machine vision. The neural network may include a stem block that includes a set of stem layers. The neural network may additionally include a visual transformer block. The set of stem layers may include a patch layer, a first normalization layer, an embedding layer, and a second normalization layer. The patch layer subdivides an input image into a set of image patches. The first normalization layer generates a set of normalized image patches by performing a first normalization process on each image patch of the set of image patches. The patch layer feeds forward to the first normalization layer. The embedding layer generates a set of vector embeddings. Each vector embedding of the set of embedding vectors is a projection of a corresponding normalized image patch from the set of normalized image patches onto a visual token. The first normalization layer feeds forward to the embedding layer. The second normalization layer generates a set of normalized vector embeddings by performing a second normalization process on each vector embedding of the set of vector embeddings. The embedding layer feeds forward to the second normalization layer. The transformer block enables one or more machine vision tasks for the input image based on the set of normalized vectors. The second normalization layer feeds forward to the transformer block.
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 10/26 - Segmentation de formes dans le champ d’imageDécoupage ou fusion d’éléments d’image visant à établir la région de motif, p. ex. techniques de regroupementDétection d’occlusion
4.
Systems and Methods of Person Recognition in Video Streams
A method for recognizing persons in video streams includes obtaining a live video stream, detecting a first person in the live video stream, determining from analysis of the live video stream first information that identifies an attribute of the first person, determining based on at least some of the first information that the first person is not identifiable to the computing system, storing at least some of the first information, receiving a user classification of the first person as being a stranger, and deleting the stored first information.
G06V 20/40 - ScènesÉléments spécifiques à la scène dans le contenu vidéo
G06V 40/10 - Corps d’êtres humains ou d’animaux, p. ex. occupants de véhicules automobiles ou piétonsParties du corps, p. ex. mains
G06V 40/16 - Visages humains, p. ex. parties du visage, croquis ou expressions
G08B 13/196 - Déclenchement influencé par la chaleur, la lumière, ou les radiations de longueur d'onde plus courteDéclenchement par introduction de sources de chaleur, de lumière, ou de radiations de longueur d'onde plus courte utilisant des systèmes détecteurs de radiations passifs utilisant des systèmes de balayage et de comparaison d'image utilisant des caméras de télévision
H04N 7/18 - Systèmes de télévision en circuit fermé [CCTV], c.-à-d. systèmes dans lesquels le signal vidéo n'est pas diffusé
H04N 23/611 - Commande des caméras ou des modules de caméras en fonction des objets reconnus les objets reconnus comprenant des parties du corps humain
5.
Machine Learning Based Performance Estimator for Large Scale Workloads
Aspects of the disclosure are directed to estimating the performance of workloads with reduced hardware utilization. This results in significant reduction in processing and memory costs to estimate the performance of workloads, as less hardware resources are involved to accurately estimate the performance of a workload. To estimate the performance with reduced hardware utilization, the workload is rewritten for local operations on the reduced hardware and the rewritten workload is run on the reduced hardware to generate a reduced hardware profile, including a reduced hardware performance. The workload is also input to a machine learning model trained to determine a communication cost for the workload. The machine learning model outputs the communication cost for the workload. The reduced hardware profile is combined with the communication cost to generate an estimated profile, including the estimated performance for the workload.
This document describes systems and techniques directed at consolidation and summarization of relevant information from home event data. Various examples are described herein, including a method, the method including receiving, by a machine-learned (ML) model, home data and generating, by the ML model, correlations based on the home data. The techniques further include generating, based on the correlations, a home summary including a text summary of a subset of the home data related to the correlations. The techniques may then generate a home output based on the home summary for output to a user. By so doing, users can get a better understanding of their homes through relevant and useful summaries of trends, patterns, and events happening within their homes.
H04L 12/28 - Réseaux de données à commutation caractérisés par la configuration des liaisons, p. ex. réseaux locaux [LAN Local Area Networks] ou réseaux étendus [WAN Wide Area Networks]
A port is provided in a housing of a computing device. The port uses a common installation volume in the housing to provide the functionality of a first component and a second component in a single, combined port. The port functions as an audio output port in a first mode, and as a charging and/or data communication port in a second mode. A front volume of an audio output device extends between an audio driver and a receptacle of the port for output of audio content via the receptacle in the first mode. An interface device may be provided in a void defined by a wall portion of the receptacle, to facilitate connection with a charging plug selectively insertable into the receptacle for charging of the computing device and/or wired data communication in the second mode.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using frames for performing tasks. One of the methods includes receiving a first request to perform a task, the first request comprising user speech identifying the task; generating a frame associated with the task, wherein the frame comprises one or more types of values necessary to perform the task, and wherein each type of value can be satisfied by a respective value; receiving a second request to provide information related to a question, the second request comprising user speech identifying the question; providing information identifying the question to a search engine, and receiving a response identifying one or more terms; determining that at least one term can satisfy a type of value necessary to perform the task; and storing the at least one term in the frame.
Methods and devices in a wireless network enable the use of an artificial intelligence or machine learning model for beam management based on an estimated distribution. A user equipment (UE) receives, from a network entity (NE), a control signaling for configuring a distribution to be estimated by the UE and a channel measurement resource. The UE estimates the distribution based on measuring a downlink reference signal received on the channel measurement resource, and transmits to the NE, an indication of the estimated distribution.
An example method includes receiving first and second audio signals from respective first and second audio input devices. The first and second audio signals correspond to speech input of a conversation between two participants. The method includes estimating, based on the first and second audio signals, a time delay in respective arrival times for the speech input at the first and second audio input devices. The method includes estimating respective directions for two audio sources based on the estimated time delay in the respective arrival times. The method includes associating, based on the estimated directions of the two audio sources, respective portions of a speech-to-text transcript of the conversation with the respective participants. The method includes displaying based on the associating of the respective portions, a modified speech-to-text transcript of the conversation that labels the respective portions of the speech-to-text transcript associated with the respective participants.
G10L 17/02 - Opérations de prétraitement, p. ex. sélection de segmentReprésentation ou modélisation de motifs, p. ex. fondée sur l’analyse linéaire discriminante [LDA] ou les composantes principalesSélection ou extraction des caractéristiques
G06F 40/103 - Mise en forme, c.-à-d. modification de l’apparence des documents
G06F 40/166 - Édition, p. ex. insertion ou suppression
G10L 25/06 - Techniques d'analyse de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits les paramètres extraits étant des coefficients de corrélation
11.
Image Saliency Based Smart Framing with Consideration of Tapping Position and Continuous Adjustment
A method includes receiving a first user-indicated area associated with a displayed image. The method also includes determining a first saliency region based on the first user-indicated area and the displayed image. The method further includes causing a first zoomed-in image to be displayed based on the first saliency region. The method additionally includes receiving a second user-indicated area associated with the first zoomed-in image. The method further includes determining a second saliency region based on the second user-indicated area and the first zoomed-in image. The method also includes causing a second zoomed-in image to be displayed based on the second saliency region, where the second zoomed-in image is further zoomed in than the first zoomed-in image.
H04N 23/63 - Commande des caméras ou des modules de caméras en utilisant des viseurs électroniques
H04N 23/611 - Commande des caméras ou des modules de caméras en fonction des objets reconnus les objets reconnus comprenant des parties du corps humain
H04N 23/69 - Commande de moyens permettant de modifier l'angle du champ de vision, p. ex. des objectifs de zoom optique ou un zoom électronique
H04N 23/90 - Agencement de caméras ou de modules de caméras, p. ex. de plusieurs caméras dans des studios de télévision ou des stades de sport
12.
Methods And Systems For Managing Application Programming Interfaces Using A Network Of Artificial Intelligence Agents
The disclosed technology is directed to apparatus, a system and a method for managing application programming interfaces (APIs) using a network of artificial intelligence (AI) agents. The disclosed technology enables efficient API management by utilizing multiple specialized AI agents working collaboratively, rather than a single agent approach. These agents obtain and analyze API metadata and runtime data to monitor performance, perform compliance checks, and determine root causes through dependency graph analysis. The system maps runtime data to API metadata, performs compliance checks, and enables specialized agents to collaborate through shared memory or storage. When users submit queries, user-facing agents determine their intent and route them to appropriate specialized agents, providing comprehensive insights into API health, potential issues, and their root causes.
H04L 41/5009 - Détermination des paramètres de rendement du niveau de service ou violations des contrats de niveau de service, p. ex. violations du temps de réponse convenu ou du temps moyen entre l’échec [MTBF]
H04L 41/0631 - Gestion des fautes, des événements, des alarmes ou des notifications en utilisant l’analyse des causes profondesGestion des fautes, des événements, des alarmes ou des notifications en utilisant l’analyse de la corrélation entre les notifications, les alarmes ou les événements en fonction de critères de décision, p. ex. la hiérarchie ou l’analyse temporelle ou arborescente
H04L 67/63 - Ordonnancement ou organisation du service des demandes d'application, p. ex. demandes de transmission de données d'application en utilisant l'analyse et l'optimisation des ressources réseau requises en acheminant une demande de service en fonction du contenu ou du contexte de la demande
13.
Generating Actionable Insights from Smart Home Event Data
This document describes systems and techniques directed at generating actionable insights from smart home event data. Various examples are described herein, including a method, the method including generating, by one or more home surveillance sensors, home data. The method further includes receiving, by a machine-learned (ML) model, the home data and generating, by the ML model, one or more correlations based on the home data. The method further includes generating, based on the one or more correlations, a home action and configuring, by one or more processors, the home action for output to a user.
H04L 12/28 - Réseaux de données à commutation caractérisés par la configuration des liaisons, p. ex. réseaux locaux [LAN Local Area Networks] ou réseaux étendus [WAN Wide Area Networks]
14.
EFFICIENT AND LATENCY REDUCING TASK DISTRIBUTION USING TRUSTED EXECUTION ENVIRONMENTS
Methods, systems, and apparatus, including medium-encoded computer program products for selecting and displaying content in privacy preserving manners are described. A first trusted content platform (CP) that executes within a first trusted environment can receive a digital component (DC) response that can include: (i) data indicating constrained DCs and, for each constrained DC, distribution parameters; and (ii) data indicating at least one contextual DC selected according to contextual data. The first trusted CP can send to a second trusted CP a second DC request that can include set of constraining values and the distribution parameters. The first trusted CP can receive from the second trusted CP, data indicating (i) one or more constrained DCs selected and (ii) selection values generated based on the set of constraining values. The first trusted CP can select a DC based on a selection value for each contextual DC and the selection value.
G06F 21/53 - Contrôle des utilisateurs, des programmes ou des dispositifs de préservation de l’intégrité des plates-formes, p. ex. des processeurs, des micrologiciels ou des systèmes d’exploitation au stade de l’exécution du programme, p. ex. intégrité de la pile, débordement de tampon ou prévention d'effacement involontaire de données par exécution dans un environnement restreint, p. ex. "boîte à sable" ou machine virtuelle sécurisée
G06F 7/544 - Méthodes ou dispositions pour effectuer des calculs en utilisant exclusivement une représentation numérique codée, p. ex. en utilisant une représentation binaire, ternaire, décimale utilisant des dispositifs n'établissant pas de contact, p. ex. tube, dispositif à l'état solideMéthodes ou dispositions pour effectuer des calculs en utilisant exclusivement une représentation numérique codée, p. ex. en utilisant une représentation binaire, ternaire, décimale utilisant des dispositifs non spécifiés pour l'évaluation de fonctions par calcul
G06F 21/62 - Protection de l’accès à des données via une plate-forme, p. ex. par clés ou règles de contrôle de l’accès
15.
Reconciling Speaker Permutation In Longform Speaker Diarization with Sequence Processing Neural Networks
A method includes obtaining a plurality of audio data segments characterizing a conversation between two or more speakers. For each respective audio data segment, the method includes generating a corresponding short-form diarized transcript of a respective portion of the conversation. The corresponding short-form diarized transcript includes a respective sequence of terms and a respective one or more speaker tokens attributing each of the sequence terms to a corresponding speaker identity. The method includes generating a reconciled long-form diarized transcript based on the corresponding short-form diarized transcript generated for each respective audio data segment. A sequence processing neural network generates the reconciled diarized transcript by, for one of the corresponding short-form diarized transcripts, permuting a first speaker token and a second speaker token of the at least one of the corresponding short-form diarized transcripts.
This disclosure describes apparatuses, methods, and techniques for enabling a user to safeguard a computing device with a fingerprint identification system by using biometric data. The fingerprint identification system includes a fingerprint sensor used during an enrollment process of the user's biometric data. The biometric data may include fingerprint data from the user's thumb, finger, a plurality of fingers, palm, and so forth. The computing device uses a collocation of a user's touch, for example, a thumb-tap, and a fingerprint sensor's location to guide the user to complete the enrollment process of a full fingerprint with ease and with fewer thumb-taps. Consequently, the techniques enable biometric security with an enrollment process having a good user experience.
G06V 40/60 - Moyens statiques ou dynamiques permettant d’aider l’utilisateur à positionner une partie du corps pour l’acquisition de données biométriques
A method for predicting a cardiac arrhythmia event is provided. The method includes determining a user wearing a wearable computing device has experienced an initial cardiac arrhythmia event based, at least in part, on biometric data obtained from one or more biometric sensors of the wearable computing device. The method includes obtaining biometric data indicative of a cardiac rhythm of the user for an observation period in response to determining the user has experienced the initial cardiac arrhythmia event. The method includes determining one or more temporal patterns of cardiac arrhythmia events of the user during the observation period. The method includes generating a prediction for at least one future cardiac arrhythmia event based, at least in part, on the one or more temporal patterns of cardiac arrhythmia events of the user during the observation period.
A computer-implemented method for assessing a fall risk of a user is provided. The computer-implemented method includes obtaining data indicative of the user engaging in a fall risk activity. The computer-implemented method includes adjusting a fall detection threshold of a wearable computing device worn by the user based, at least in part, on the data indicative of the user engaging in the fall risk activity. The method includes providing a notification indicative of the user being at risk of falling due, at least in part, to the user engaging in the fall risk activity.
A61B 5/11 - Mesure du mouvement du corps entier ou de parties de celui-ci, p. ex. tremblement de la tête ou des mains ou mobilité d'un membre
A61B 5/00 - Mesure servant à établir un diagnostic Identification des individus
G08B 21/04 - Alarmes pour assurer la sécurité des personnes réagissant à la non-activité, p. ex. de personnes âgées
G16H 10/60 - TIC spécialement adaptées au maniement ou au traitement des données médicales ou de soins de santé relatives aux patients pour des données spécifiques de patients, p. ex. pour des dossiers électroniques de patients
G16H 40/67 - TIC spécialement adaptées à la gestion ou à l’administration de ressources ou d’établissements de santéTIC spécialement adaptées à la gestion ou au fonctionnement d’équipement ou de dispositifs médicaux pour le fonctionnement d’équipement ou de dispositifs médicaux pour le fonctionnement à distance
G01C 5/06 - Mesure des hauteursMesure des distances transversales par rapport à la ligne de viséeNivellement entre des points séparésNiveaux à lunette en utilisant des moyens barométriques
G01P 13/00 - Indication ou enregistrement de l'existence ou de l'absence d'un mouvementIndication ou enregistrement de la direction d'un mouvement
To route application traffic, a user equipment (UE) initiates (1930), for the application traffic, an enforcement of a UE route selection policy (URSP) rule; receives (1932), from a core network (CN), a reporting trigger indication corresponding to the URSP rule; and reports (1941), to the CN and in accordance with the reporting trigger indication, the enforcement of the URSP rule.
H04W 40/04 - Sélection d'itinéraire ou de voie de communication, p. ex. routage basé sur l'énergie disponible ou le chemin le plus court sur la base des ressources nodales sans fil
H04W 60/00 - Rattachement à un réseau, p. ex. enregistrementSuppression du rattachement à un réseau, p. ex. annulation de l'enregistrement
20.
METHOD FOR REDUCING DEPTH CONFLICTS IN STEREOSCOPIC DISPLAYS
A depth conflict between objects displayed on a stereoscopic display occurs when a background object is rendered at a first depth that is smaller than a second depth of a foreground object overlaid on the background object. This conflict can be resolved by making the first depth of the background object larger while the foreground object is overlaid on the background object. After the overlapping condition concludes, the first depth of the background object may be returned to its original value.
H04N 13/128 - Ajustement de la profondeur ou de la disparité
H04N 13/361 - Reproduction d’images stéréoscopiques mixtesReproduction d’images stéréoscopiques et monoscopiques mixtes, p. ex. une fenêtre avec une image stéréoscopique en superposition sur un arrière-plan avec une image monoscopique
A waveguide system of an eyewear display device guides display light from a primary display to a primary field of view (FOV) and guides display light from a secondary display to a secondary FOV that is displaced from the primary FOV. Additional display light of a given color that is incoupled to the waveguide system at a different angle than the primary display light is outcoupled from the waveguide system at a corresponding angle displaced from the primary FOV to form a secondary FOV that is spatially displaced from the primary FOV in some embodiments.
Techniques and apparatuses are described for implementing proactive thermal control for a system-on-chip. In example aspects, a thermal-control system utilizes a prediction model to predict a future evolution of an SoC based on a current operation point and a current temperature of the SoC. The prediction is used to proactively update a thermal-control policy that manipulates an operation point of one or more subsystems of the SoC. In aspects, a user perception of a thermal limit to an enclosure (e.g., surface temperature of a surface of the enclosure that the user touches) of a device having the SoC is also used to determine tradeoffs and contradicting goals between the calculated power/thermal metrics for the device and the user's perception of the thermal limit for the enclosure (e.g., surface temperature that the user touches).
G05B 13/02 - Systèmes de commande adaptatifs, c.-à-d. systèmes se réglant eux-mêmes automatiquement pour obtenir un rendement optimal suivant un critère prédéterminé électriques
Methods and apparatus related to associating location data with one or more entities. Location data from, for example, mobile devices carried by users, may indicate a first entity as being associated with the given location data. However, one or more affirmative user inputs may indicate that a second entity is additionally, and/or alternatively associated with location data. Accordingly, location data may be associated with the second entity. In some implementations the first entity may be dissociated from the first location data. In some implementations second location data may be identified as being associated with the first entity and the second location data may be associated with the first entity.
A user computing device includes a housing defining a cavity and a circuitry connection system contained at least partially within the cavity. The circuitry connection system includes a circuit board comprising circuitry. The circuitry connection system also includes a static pin coupled to an electrical component and fixed relative to the circuit board. The static pin includes a flat top surface. In addition, the circuitry connection system includes an electrical connector including a base portion coupled to the circuit board, a curved portion spaced from the base portion, and an extension portion extending from the base portion to the curved portion. The extension portion is configured to bias the curved portion into contact with the flat top surface of the static pin to electrically connect the electrical component to the circuitry on the circuit board. The curved portion is configured to minimize direct current (DC) resistance between the static pin and the circuitry on the circuit board.
Aspects of the disclosed technology include techniques and mechanisms for customizing large language models (LLMs) for information retrieval (IR). For a plurality of (query, corpus) pairs, an IR adapter may generate embeddings and adapted embeddings associated with each of the query and the corpus. The IR adapter may analyze the adapted embeddings using a similarity function to determine the similarity between the adapted embeddings. The output of the similarity function may be used to determine a correlation between the query and the corpus, wherein the correlation may be fed back into the IR adapter to train an LLM.
A method is disclosed for providing a UI indicating characteristics of a baseline audience segment defining a first group of users designated to receive advertising content, receiving a user selection initiating an audience expansion feature, and in response to the user selection, identifying, based on the first group, an expanded audience segment comprising a second group of users not currently designated to receive the advertising content, estimating content related metrics for the second group, predicting, using a machine learning model and based on the estimated content related metrics for the second group, a performance metric lift representing an expected increase in user actions for the advertising content upon adding the expanded audience segment, responsive to the predicted performance metric lift satisfying a threshold condition, modifying campaign targeting parameters to include at least a subset of the expanded audience segment, and causing display of an indication of the expanded audience segment and a representation of the predicted performance metric lift.
H04N 21/4788 - Services additionnels, p. ex. affichage de l'identification d'un appelant téléphonique ou application d'achat communication avec d'autres utilisateurs, p. ex. discussion en ligne
H04H 60/66 - Dispositions pour des services utilisant les résultats du contrôle, de l'identification ou de la reconnaissance, couverts par les groupes ou pour utiliser les résultats côté distributeurs
27.
FUNCTIONALITY CONTROL FOR RADIO RESOURCE MANAGEMENT MEASUREMENT PREDICTION
This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for functionality control for radio resource management measurement prediction. A user equipment (UE) (102) receives (401), from a network entity (NE) (104), functionality activation configuration information. The UE obtains (403) a measurement result of a serving cell. The UE performs (406) a prediction on a non-serving cell according to the functionality activation configuration information based on at least one of: whether an s-Measure procedure is configured, or the measurement result of the serving cell.
Techniques for facilitating or optimizing the detection of neighboring cells by a UE (102) include the UE receiving (704), from a base station (104), system information, a measurement object, or a redirection instruction including an SMTC indicating first set of timing offsets and an indication of additional timing offset(s). The SMTC can correspond to a first synchronization transmission pattern utilized by neighboring cells, and the additional timing offset(s) can correspond to a different synchronization pattern. The additional offset(s) may be indicated by, e.g., a plurality of timing offsets, an indication of at least one satellite, a delta timing offset, an indication of PCIs corresponding to a target NR carrier frequency, etc. The UE derives one or more timing patterns based on the SMTC and the indication of the additional timing offset(s), and utilizes the derived timing pattem(s) to scan and measure for (708) and/or detect the presence of neighboring cells.
Methods, systems, and techniques are disclosed for channel state information (CSI) processing with machine learning (ML) model based encoders and decoders. In some aspects, the CSI processing may include CSI compression/decompression. In some other aspects, the CSI processing may include CSI prediction in frequency domain, spatial domain, time domain, or any combination thereof. An example method of wireless communication by a user equipment includes: receiving, from a network entity, a CSI report configuration including a plurality of channel measurement resources (CMRs) associated with an ML model for CSI processing; receiving, from the network entity, a CSI reference signal (CSI-RS) on the plurality of CMRs; and transmitting, to the network entity, a CSI report based on an output of the ML model using tokenized measurement information of the CSI-RS including a class token associated with the CSI report configuration as an input to the ML model.
H04L 1/00 - Dispositions pour détecter ou empêcher les erreurs dans l'information reçue
H04B 7/06 - Systèmes de diversitéSystèmes à plusieurs antennes, c.-à-d. émission ou réception utilisant plusieurs antennes utilisant plusieurs antennes indépendantes espacées à la station d'émission
H04L 5/00 - Dispositions destinées à permettre l'usage multiple de la voie de transmission
This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for network and UE power saving for beam prediction procedure. A UE (102) receives (504), from a network entity (104), a configuration for a beam prediction procedure. The UE (102) receives (510), from the network entity (104), DL-RS for a channel measurement associated with the beam prediction procedure. The UE (102) determines (514) whether a condition for a valid beam prediction report of the beam prediction procedure is satisfied. The UE (102) transmits (516), to the network entity (104), a beam prediction report according to the configuration based on the determining whether the condition for the valid beam prediction report is satisfied.
H04B 7/06 - Systèmes de diversitéSystèmes à plusieurs antennes, c.-à-d. émission ou réception utilisant plusieurs antennes utilisant plusieurs antennes indépendantes espacées à la station d'émission
31.
IN-BAND CONTROL OF USER-PLANE DATA COLLECTION IN A CELLULAR COMMUNICATION SYSTEM
To facilitate user-plane (UP) data collection in a cellular communication network, a user equipment (UE) establishes, with a core network, a user-plane (UP) connection for UP data collection, including establishing a User Datagram Protocol (UDP) tunnel (542) and communicates (552), with the CN and over the UDP tunnel, an in-band UP data collection control message (UPDC-CM) related to managing the UP data collection, the control message including a feature identifier (ID) identifying an artificial intelligence/machine learning (AIZML)-enabled feature to which the UP data collection pertains.
H04L 41/16 - Dispositions pour la maintenance, l’administration ou la gestion des réseaux de commutation de données, p. ex. des réseaux de commutation de paquets en utilisant l'apprentissage automatique ou l'intelligence artificielle
09 - Appareils et instruments scientifiques et électriques
14 - Métaux précieux et leurs alliages; bijouterie; horlogerie
18 - Cuir et imitations du cuir
Produits et services
Radio transmitters and receivers; wireless communication
devices for transmission of data; electronic tags for goods;
electronic tags for locating, monitoring, remotely operating
internet of things (IoT) devices, and tracking the position
of objects and people; mobile electronic devices for
locating, monitoring, remotely operating internet of things
(IoT) devices, and tracking the position of objects and
people; carrying cases for electronic tags and mobile
electronic devices; lanyards for electronic tags and mobile
electronic devices; peripheral devices for computers, mobile
telephones, and mobile electronic devices, namely,
electronic tags used for locating, monitoring, and tracking
the position of objects and people; computer software for
smart tags, namely, recorded and downloadable computer
software for locating, monitoring, and tracking the position
of objects and people. Key rings; key chains. Key cases; luggage tags; carrying cases.
33.
INTEREST DECAY AND MIGRATION ANALYSIS FOR CONTENT RECOMMENDATION
Disclosed implementations for content recommendation. In an example implementation, a current entity of interest is determined based on interaction data associated with a period of time. A next entity of interest and a transition timeframe is determined based on the current entity, the period of time, and a plurality of interest movement patterns. Each interest movement pattern of the plurality of interest movement patterns is associated with a respective entity pair and a respective transition time. The respective transition time and the respective entity pair being identified from user interaction histories. A recommended content item is identified based on the current entity of interest and the next entity of interest, The recommended content item is provided based on the transition timeframe.
Systems and methods for generating and using primary-ray based implicit neural representations of three-dimensional objects. In some examples, an implicit neural representation of an object may be generated by training a neural network using training examples that include a reference point, a ray, a perpendicular foot of the ray relative to the reference point, and a distance indicator indicating the shortest distance along the ray between the perpendicular foot and a surface of the object, and, optionally, an intersection indicator indicating whether the ray will intersect with the object. Once trained, the neural network may then be used to generate predictions of whether a ray will intersect with the object, and/or predictions of the shortest distance along a ray between its perpendicular foot and a surface of an object, based on a given reference point, ray, and perpendicular foot of the ray relative to the reference point.
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
35.
Generating Synthetic Data Associated with Graphical Text Stylization and Animation
Example embodiments of the present disclosure provide an example method for managing computer systems and networks that can generate template descriptions associated with graphical text. The computer systems and networks can generate the template descriptions associated with the graphical text via a template description generation pipeline. The machine-learned models can utilize the template descriptions associated with the graphical text to generate images and/or videos with graphical text. The machine-learned models can generate the images and/or videos with the graphical text, via an instance rendering pipeline. The images and/or videos with the graphical text can then be utilized to train another machine-learned model.
Generally disclosed herein is an automatic software agent update approach for dynamically deploying and configuring a software agent within a container in a cloud environment. The approach may include an agent platform and a configuration management system. The agent platform may be configured to manage the deployment and configuration of the software agent. The agent platform may register the software agent, track the status of the software agent, and distribute the software updates for the software agent. The configuration management system may be configured to dynamically configure the software agent based on predefined rules or policies.
The present application relates to systems and methods for efficiently managing a data storage. The database may be a distributed database in which objects include references to a plurality of distributed data chunks. These data chunks can be referenced by a plurality of objects, and the system is configured to efficiently identify when one or more data chunks are no longer referenced by any object within the system. The system can be configured to have a two-layer architecture in which back-references for the data chunks are collected and a total count of back-references are determined. These two-layers can be based on an incremental identification of back-references, and each layer can be horizontally partitioned.
Methods, systems, and apparatus for reducing power consumption in interrupt request processing. A computing system can include a system-on-chip (SoC), which in turn can include a central processing unit (CPU), an embedded processor, an interrupt handler and at least one hardware accelerator. The interrupt handler can receive interrupt requests from the SoC and route certain types of interrupt requests to the embedded processor for processing, instead of the CPU. This alleviates the need for the CPU to wake up from a lower power state to process particular interrupt requests.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using training data generated from user session data are described. In one aspect, a method includes obtaining session data that describes a user sessions. Each user session represents a corresponding interaction between a user and a search engine that occurs during a period of time. A training sequence is generated from the session data. For each user session, the training sequence includes subsequence blocks arranged one after another in a predetermined order. A neural network is trained, including learning parameter values of the neural network, by using the training sequences.
A computer-implemented method includes receiving, by a computing system, a query, computing, by the computing system, a similarity matrix based on a first content associated with the query generated by a first transformer and a second content associated with a plurality of documents generated by a second transformer, processing, by the computing system, the similarity matrix via a neural network to generate relevance values respectively corresponding to the plurality of documents, and ranking, by the computing system, the plurality of documents with respect to the query based on the relevance values.
Techniques and devices for joining a first Thread device to a Thread network are described. A second Thread device is discovered on the Thread network. Based on the discovering, an ephemeral code is requested from the second Thread device, the request directing the second Thread device to generate the ephemeral code. Using the ephemeral code, a secure session is established between the first Thread device and the second Thread device (or a commissioner device and the second Thread device), the establishing being effective to direct the second Thread device to transfer credentials for the Thread network to the first Thread device.
H04L 61/4511 - Répertoires de réseauCorrespondance nom-adresse en utilisant des répertoires normalisésRépertoires de réseauCorrespondance nom-adresse en utilisant des protocoles normalisés d'accès aux répertoires en utilisant le système de noms de domaine [DNS]
H04W 8/00 - Gestion de données relatives au réseau
A distributed unit (DU) of a distributed base station, where the distributed base station that includes the DU and a central unit (CU), can perform a method for managing early data transmission (EDT) with a user equipment (UE). The method includes: performing (1402), while a radio connection between the UE and the DU is not active, a random access procedure, including receiving, from the UE, an uplink message formatted in accordance with a protocol for controlling radio resources; sending (1404), to the CU, a DU-to-CU message including the uplink message; receiving (1406), from the CU, a CU-to-DU message when a validity of the uplink message has been verified; generating (1408) a contention resolution ID for the UE; and transmitting (1410), to the UE, the contention resolution ID for EDT without transitioning the UE to a connected state.
A radio access network (RAN) for configuring a user equipment (UE) generates (i) a conditional configuration, and (ii) a condition to be satisfied before the UE applies the conditional configuration (1402), receives, from a core network (CN), an interface message indicating to configure the UE (1404), determines that the interface message affects the conditional configuration (1406), generates a message related to the conditional configuration in view of the received interface message (1408), and transmits the message to the UE (1410).
Methods, systems, and computer media provide attestation tokens that protect the integrity of communications transmitted from client devices, while at the same time avoiding the use of stable device identifiers that could be used to track client devices or their users. In one approach, client devices can receive batches of N device integrity elements from a device integrity computing system, each corresponding to a different public key. The N device elements can be signed by a device integrity computing system. The signing by the device integrity computing system can be signing with a blind signature scheme. Client devices can include throttlers imposing limits on the quantity of attestation tokens created by the client device.
H04L 9/32 - Dispositions pour les communications secrètes ou protégéesProtocoles réseaux de sécurité comprenant des moyens pour vérifier l'identité ou l'autorisation d'un utilisateur du système
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for obtaining a plurality of training examples, each training example comprising a respective first image depicting a corresponding scene when a target light source is in a first state and a respective second image depicting the corresponding scene when the target light source is in a second state; generating, for each training example, a plurality of respective modified images that each depict the corresponding scene when the target light source is in a respective modified state; and generating an augmented set of training data for training an image generation model, wherein the augmented set of training data comprises a plurality of additional training examples, each additional training example corresponding to one of the training examples and comprising two images selected from the plurality of respective modified images generated for the corresponding training example.
G06V 10/774 - Génération d'ensembles de motifs de formationTraitement des caractéristiques d’images ou de vidéos dans les espaces de caractéristiquesDispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p. ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]Séparation aveugle de source méthodes de Bootstrap, p. ex. "bagging” ou “boosting”
G06T 11/60 - Édition de figures et de texteCombinaison de figures ou de texte
46.
COMBINING PARAMETERS OF MULTIPLE SEARCH QUERIES THAT SHARE A LINE OF INQUIRY
Methods, systems, and computer readable media related to generating a combined search query based on search parameters of a current search query of a user and search parameters of one or more previously submitted search quer(ies) of the user that are determined to be of the same line of inquiry as the current search query. Two or more search queries may be determined to share a line of inquiry when it is determined that they are within a threshold level of semantic similarity to one another. Once a shared line of inquiry has been identified and a combined search query generated, users may interact with the search parameters and/or the search results to update the search parameters of the combined search query.
Systems and methods of the present disclosure are directed to a computer-implemented method for multimodal search refinement. The method includes obtaining a visual search query from a user comprising one or more query images. The method includes providing a search interface for display to the user, the search interface comprising one or more result images responsive to the one or more query images and an interface element indicative of a request to the user to refine the visual search query. The method includes obtaining, from the user, textual data comprising a refinement to the visual search query. The method includes appending, by the computing system, the textual data to the visual search query to obtain a multimodal search query.
Various arrangements are presented that can help preserve bandwidth, such as for audio communications involving high fidelity audio being transmitted to wireless earbuds. A first earbud can receive an audio packet from an audio source device that includes stereo audio separately encoded as a first monophonic channel and a second monophonic channel. The first earbud can determine that it successfully received the audio packet. The second earbud may not successfully receive the audio packet. Thus, the second earbud can make a request to the first earbud. The first earbud can then directly transmit to the second earbud, audio data for only the second monophonic channel from the audio packet. Each earbud can then output its respective monophonic audio channel.
H04W 4/80 - Services utilisant la communication de courte portée, p. ex. la communication en champ proche, l'identification par radiofréquence ou la communication à faible consommation d’énergie
G10L 19/008 - Codage ou décodage du signal audio multi-canal utilisant la corrélation inter-canaux pour réduire la redondance, p. ex. stéréo combinée, codage d’intensité ou matriçage
H04M 1/60 - Équipement de sous-station, p. ex. pour utilisation par l'abonné comprenant des amplificateurs de parole
H04R 5/033 - Casques pour communication stéréophonique
This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for a UE to report power headroom associated with dynamic waveform selection for uplink multi-panel transmission. The UE may calculate and report UE-specific power headroom report (PHR) for one or more combinations of waveforms from the multiple antenna panels or panel-specific PHR for one or more waveforms for each panel. The UE (102) receives (410), from the network entity (104), a signaling for configuring at least one power headroom report (PHR) to support dynamic waveform indication in uplink multi-panel transmission. The UE (102) transmits (1012), to the network entity (104), the at least one PHR including a UE-specific PHR or a panel-specific PHR. The UE-specific PHR is associated with at least one waveform combination of the dynamic waveform indication and the panel-specific PHR is associated with at least one waveform of the dynamic waveform indication.
H04W 52/36 - Commande de puissance d'émission [TPC Transmission power control] utilisant les limitations de la quantité totale de puissance d'émission disponible avec une plage ou un ensemble discrets de valeurs, p. ex. incrément, variation graduelle ou décalages
H04W 52/14 - Analyse séparée de la liaison montante ou de la liaison descendante
Methods, systems, apparatus, including computer programs encoded on a computer storage medium, for spatialized audio feedback from automated assistants. In one aspect, the method includes actions of determining that a user input has been received at a client device, identifying, based on sensor data, one or more points of interest of an environment in which the client device is located and an orientation of a user of the client device relative to the one or more points of interest, identifying, based on processing the user input and the sensor data, a natural language response providing information relevant corresponds to a particular point of interest, determining, based on the orientation of the user of the client device relative to the particular point of interest, one or more spatial audio parameters to be used to provision the natural language response to the user, and causing the natural language response to be audibly rendered at the client device using one or more of the spatial audio parameters.
A web browsing application can implement a vector database to store session data. A web browsing application can automatically embed loaded web content into an embedded data store that maintains session data for a number of web sessions. A user can query the web browser using simple instructions. The web browser can interpret the instructions and use the embedded data store to quickly search across multiple modalities of embedded data to retrieve relevant results. The web browser can use machine-learned models to answer queries or perform other tasks by performing vector-based queries over the content of visited web data.
Methods and systems, including computer-readable media, are described for implementing a multi-cluster architecture for a hardware machine-learning (ML) accelerator. The architecture is implemented as a hardware integrated circuit and includes a controller that communicates with one or more cores and a first and second cluster of compute tiles. Each of the first and second cluster of compute tiles is configured to execute a respective ML workload. A first workload can be assigned to the first cluster of compute tiles and a second, different workload can be assigned to the second cluster of compute tiles. The first and second workloads are executed concurrently using the first and second clusters based on a program context of at least one core that is coupled to compute tiles of the first and second cluster.
Techniques for contextual search on multimedia content are provided. An example method includes extracting entities associated with multimedia content, wherein the entities include values characterizing one or more objects represented in the multimedia content, generating one or more query rewrite candidates based on the extracted entities and one or more terms in a query related to the multimedia content, providing the one or more query rewrite candidates to a search engine, scoring the one or more query rewrite candidates, ranking the scored one or more query rewrite candidates based on their respective scores, rewriting the query related to the multimedia content based on a particular ranked query rewrite candidate and providing for display, responsive to the query related to the multimedia content, a result set from the search engine based on the rewritten query.
A user equipment (UE) can perform a method for managing inter-frequency measurements. The method includes: determining (902) one or more carrier frequencies for inter-frequency measurements while a radio connection between the UE and the RAN is not active; determining (904) that data is available for early data communication between the UE and a core network (CN); and determining (906) whether to suspend (i) inter-frequency measurements on at least one of the carrier frequencies or (ii) the early data communication.
H04W 48/10 - Distribution d'informations relatives aux restrictions d'accès ou aux accès, p. ex. distribution de données d'exploration utilisant des informations radiodiffusées
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatically generating datasets for a particular target expression photo effect. In one aspect, a system comprises receiving a plurality of image pairs, each comprising an original face image and an expressive face image representative of a target expression photo editing effect, generating an initial overall editing vector, wherein generating the initial overall editing vector comprises processing each image pair using a style space encoder model to generate an embedding of the original face image and an embedding of the expressive face image in an embedding space, optimizing the initial overall editing vector in accordance with one or more optimization criteria to generate an optimized overall editing vector, and applying the optimized overall editing vector to an input face image to generate a target expression face image that has the target expression photo editing effect.
G06T 11/60 - Édition de figures et de texteCombinaison de figures ou de texte
G06V 10/774 - Génération d'ensembles de motifs de formationTraitement des caractéristiques d’images ou de vidéos dans les espaces de caractéristiquesDispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p. ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]Séparation aveugle de source méthodes de Bootstrap, p. ex. "bagging” ou “boosting”
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
56.
Joint Connected Isochronous Stream Communication with Cross Acknowledgement
Various arrangements for short-range wireless communication are presented herein. An earbud of a pair of true wireless earbuds can receive an audio packet addressed to the other earbud of the pair. A single connected isochronous stream (CIS) within a connected isochronous group (CIG) may be present between the pair of true wireless earbuds and an audio source which transmitted the audio packet. The earbud can transmit a cross-acknowledgement indicating receipt of the audio packet to the other earbud. The earbud can also transmit audio data from the audio packet to the other earbud after the cross acknowledgement.
Implementations described herein receive audio data that captures a spoken utterance, generate, based on processing the audio data, a recognition that corresponds to the spoken utterance, and determine, based on processing the recognition, that the spoken utterance is ambiguous (i.e., is interpretable as requesting performance of a first particular action exclusively and is also interpretable a second particular action exclusively). In response to determining that the spoken utterance is ambiguous, implementations determine to provide an enhanced clarification prompt that renders output that is in addition to natural language. The enhanced clarification prompt solicits further user interface input for disambiguating between the first particular action and the second particular action. Determining to provide the enhanced clarification prompt includes a current or prior determination to provide the enhanced clarification prompt instead of a natural language (NL) only clarification prompt that is restricted to rendering natural language.
G10L 15/22 - Procédures utilisées pendant le processus de reconnaissance de la parole, p. ex. dialogue homme-machine
G06F 3/0481 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] fondées sur des propriétés spécifiques de l’objet d’interaction affiché ou sur un environnement basé sur les métaphores, p. ex. interaction avec des éléments du bureau telles les fenêtres ou les icônes, ou avec l’aide d’un curseur changeant de comportement ou d’aspect
G06F 3/0488 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] utilisant des caractéristiques spécifiques fournies par le périphérique d’entrée, p. ex. des fonctions commandées par la rotation d’une souris à deux capteurs, ou par la nature du périphérique d’entrée, p. ex. des gestes en fonction de la pression exercée enregistrée par une tablette numérique utilisant un écran tactile ou une tablette numérique, p. ex. entrée de commandes par des tracés gestuels
G10L 15/18 - Classement ou recherche de la parole utilisant une modélisation du langage naturel
G10L 15/30 - Reconnaissance distribuée, p. ex. dans les systèmes client-serveur, pour les applications en téléphonie mobile ou réseaux
G10L 25/51 - Techniques d'analyse de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation
58.
CONTROLLING USER-PLANE DATA COLLECTION IN A CELLULAR COMMUNICATION SYSTEM
To facilitate user-plane (UP) data collection in a cellular communication network, a user equipment (UE) can transmitting, to a core network (CN), a registration request message including an indication of a capability of the UE with respect to the UP data collection; encapsulate, in a payload container, a UP data collection control message that includes a feature identifier (ID) identifying an artificial intelligence/machine learning (AI/ML)-enabled feature to which the UP data collection pertains; include the payload container in a non-access stratum (NAS) transport message; and transmit, to the CN, the NAS transport message.
H04W 24/02 - Dispositions pour optimiser l'état de fonctionnement
H04L 41/16 - Dispositions pour la maintenance, l’administration ou la gestion des réseaux de commutation de données, p. ex. des réseaux de commutation de paquets en utilisant l'apprentissage automatique ou l'intelligence artificielle
H04W 24/10 - Planification des comptes-rendus de mesures
A method includes, while driving a first mixer with a first local-oscillator (LO) signal, providing a first baseband signal to the first mixer. Providing the first baseband signal to the first mixer generates a first output signal of the first mixer. While driving a second mixer with a second LO signal that is shifted by a phase-shift that is relative to the first LO signal, a second baseband signal is provided to the second mixer. Providing the second baseband signal to the second mixer generates a second output signal of the second mixer. The first output signal and the second output signal are combined at a common load line. Combining the first output signal and the second output signal at the common load line generates a microwave signal with a controlled phase. The common load line is common to the first mixer and the second mixer.
G06N 10/40 - Réalisations ou architectures physiques de processeurs ou de composants quantiques pour la manipulation de qubits, p. ex. couplage ou commande de qubit
60.
MOBILE SENSING TARGET IN AN INTEGRATED SENSING AND COMMUNICATION ENVIRONMENT
This disclosure provides methods and apparatuses for integrated sensing and communication. The techniques enable sensing of a mobile sensing target (ST) (127) by sensing entities (125A, 125B, 125C) in a radio access network (RAN (120) ). A sensing entity can detect an occurrence or prediction of a sensing exception (150). Examples of sensing exceptions include the ST being out of range or cell coverage of a sensing entity involved with a sensing task. When a sensing exception occurs (or is predicted to occur), the sensing controller (135) (or a sensing entity) can activate another sensing entity to continue or resume the sensing task.
Decoding using partition aspect ratio constraints includes accessing block partition aspect ratio constraint data indicating a maximum block partition elongation and obtaining reconstructed block data. Obtaining the reconstructed block data includes obtaining a sequence of block partition symbols for the current block and partitioning the current block in accordance with the sequence of block partition symbols. Obtaining the sequence of block partition symbols includes in response to determining that partitioning the current block in accordance with a first available value of a current symbol from the sequence of block partition symbols corresponds with a block partition elongation that is greater than the maximum block partition elongation, obtaining, as a value of the current symbol, a second available value of the current symbol, wherein data indicating the value of the current symbol is absent from the encoded bitstream.
H04N 19/119 - Aspects de subdivision adaptative, p. ex. subdivision d’une image en blocs de codage rectangulaires ou non
H04N 19/70 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques caractérisés par des aspects de syntaxe liés au codage vidéo, p. ex. liés aux standards de compression
09 - Appareils et instruments scientifiques et électriques
Produits et services
Light-emitting diode (LED) lights sold as a feature of mobile phones; Light-emitting diode (LED) lights controlled by software recorded and pre-installed on mobile phones; Recorded and pre-installed software for providing notifications to mobile phone users, sold as a component of mobile phones; Recorded and pre-installed computer software for providing notifications to mobile phone users
Device-based anti-theft and recovery techniques for computing devices are disclosed herein. An example system includes one or more processors that execute instructions to receive, from a transferor that intends to convey the computing device to a transferee, one or more signal parameters that, if satisfied, permit the computing device to deactivate a protected mode of operation; activate, during a normal mode of operation, the protected mode, wherein the computing device disables one or more functions that are enabled during the normal mode of operation while the protected mode is activated; receive, during the protected mode, a user input from a potential transferee corresponding to a wake function of the computing device; and responsive to receiving the user input, determine, based on a comparison between one or more signals associated with the computing device and the one or more signal parameters, whether the computing device is in possession of the transferee.
A clutch assembly includes a first member for mechanically coupling to an output shaft. A first material is frictionally coupled to a first side surface of the first member. A second material is frictionally coupled to a second side surface of the first member. A compliant member is configured to apply an axial force on at least one of the first material and the second material. A radial spring least partially surrounds an exterior surface of the first member.
A radio access network (RAN) node acting as a base station or core network (CN) can implement a method for managing lower layer triggered mobility protocol procedure(s). An example method in a core network (CN) includes: transmitting, to a base station via which a user equipment (UE) communicates with the CN, a request for resources for a packet data unit (PDU) session, including; determining, based on a condition related to the UE and/or the base station, whether to include a PDU Set quality of service (QoS) parameter in the request; and receiving, from the base station, a response to the request for the resources.
A folding display device includes a housing and a continuous display coupled to the housing. The housing includes a first assembly, a second assembly; and a hinge assembly coupled to the first and second assemblies and defining a. folding axis. The continuous display is configured to fold around the folding axis and includes a display layer that includes an optical display, a cover layer overlying the display layer, and a backing layer underlying the display layer. The backing layer includes an elastic matrix or sheet and an array of ribs dispersed in or on the elastic matrix or sheet and aligned substantially parallel to the folding axis.
Methods, systems, and apparatus for targeted quantum processor recalibration. In one aspect, a method includes obtaining normalized values of quantum processor system metrics, wherein the system metrics comprise single qubit metrics and two qubit metrics; determining, for each single qubit metric, an effective single qubit metric, wherein the effective single qubit metric comprises the single qubit metric and a sum of two qubit metrics corresponding to pairs of qubits that include a same qubit as the single qubit metric; computing, using the normalized values of the system metrics, values of the effective single qubit metrics; combining, for each qubit referenced by single qubit metrics in the system metrics, effective single qubit metrics that correspond to the qubit to obtain a score for the qubit; and causing recalibration of operating parameters of qubits with scores that exceed a predetermined outlier threshold.
G06N 10/20 - Modèles d’informatique quantique, p. ex. circuits quantiques ou ordinateurs quantiques universels
G06N 10/40 - Réalisations ou architectures physiques de processeurs ou de composants quantiques pour la manipulation de qubits, p. ex. couplage ou commande de qubit
69.
TASK COMPLETION USING A LANGUAGE MODEL NEURAL NETWORK
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automating the interaction with user interfaces for task execution using a language model neural network. In one aspect, a method comprises receiving an input that describes a task; determining data describing the task; and executing the task by using a language model neural network by repeatedly performing following operations: obtaining a first input subsequence that is derived from the data describing the task; obtaining a second input subsequence that is derived from an image of a current user interface; generating, by the language model neural network, based on the first input subsequence and the second input subsequence, output data that describes one or more actions to be performed within the current user interface; and performing the one or more actions within the current user interface.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting a nucleating agent for synthesis of a target material. According to one aspect, a method comprises: receiving data identifying a target material; generating an embedding of the target material in a latent space using an embedding machine learning model; and selecting one or more nucleating agents for the target material, from a set of candidate nucleating agents, based at least in part on the embedding of the target material in the latent space.
G16C 20/70 - Apprentissage automatique, exploration de données ou chimiométrie
G16C 60/00 - Science informatique des matériaux, c.-à-d. TIC spécialement adaptées à la recherche des propriétés physiques ou chimiques de matériaux ou de phénomènes associés à leur conception, synthèse, traitement, caractérisation ou utilisation
71.
MACHINE-LEARNING FREQUENCY AND POWER PREDICTIONS FOR INTEGRATED HARDWARE CIRCUITS
Methods and systems, including computer-readable media, are described for implementing frequency and power predictions for an integrated circuit of a System-on-Chip (“SoC”). The system detects that an application is being executed at the SoC and determines a workload type of the application based on an indicator generated concurrent with the application being executed. Inferences are computed by a DVFS prediction engine of the SoC based on the workload type and the indicator. The inferences are used to achieve a threshold quality of service (“QoS”) when the application is executed at the SoC. The DVFS prediction engine generates a predicted frequency value and a predicted power value from the computed inferences. The predicted frequency value or power value is used to adjust an operating frequency or a power output at the hardware integrated circuit to achieve a threshold QoS when the application is executed at the SoC.
A centralized unit (CU) of a distributed base station that also includes a distributed unit (DU) transmits (413), to the DU, a request related to a context of a UE that communicates with a core network (CN) via the DU and the CU, the request including a packet data unit (PDU) Set quality of service (QoS) parameter for a QoS flow; receives (414), from the DU, a response to the request; and communicates (426), between the CN and the UE via the DU, a data packet in the QoS flow.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output audio signal. In some implementations, the output audio signal can be generated by using a generative neural network in a number of iterations that is independent of the length of the output audio signal.
Various arrangements for measuring blood pressure using sensor fusion are presented herein. Radio frequency (RF) signals are emitted and RF reflection signals are received by a radar sensor of a stationary device. The RF reflection signals are analyzed at a first distance range to identify a first pulse pressure waveform (PPW) at an aortic valve of a user. Vital sign data measured at an extremity of the user by a mobile device are received by the stationary device. The vital sign data is analyzed to identify a second PPW at the extremity of the user. Using the first PPW and the second PPW, a pulse transit time from the aortic valve to the extremity is determined. Using the PTT, a blood pressure (BP) of the user is determined and an indication of the BP is output.
A61B 5/021 - Mesure de la pression dans le cœur ou dans les vaisseaux sanguins
A61B 5/00 - Mesure servant à établir un diagnostic Identification des individus
A61B 5/024 - Mesure du pouls ou des pulsations cardiaques
A61B 5/05 - Détection, mesure ou enregistrement pour établir un diagnostic au moyen de courants électriques ou de champs magnétiquesMesure utilisant des micro-ondes ou des ondes radio
75.
DEEP LEARNING-BASED PHOTOPLETHYSMOGRAPHY MODEL FOR CARDIOVASCULAR RISK PREDICTION
Accurate prediction of the risk of cardiovascular disease (CVD) can lead to significantly improved health outcomes by prompting earlier, more effective, and lower-cost interventions (like lifestyle and diet changes). Available long-term predictive tests for CVD risk include costly, clinically intensive diagnostics that include the efforts of highly trained clinical or laboratory staff like blood or other fluid draws and related laboratory testing, ECG, sphygmomanometer-based blood pressure measurement, or other tests. Such testing is not available in resource-constrained healthcare settings. Embodiments are provided that use a trained machine learning model to generate, from photoplethysmographic (PPG) signals, features that can be used, in combination with readily available information like age and sex and PPG-derived heart rate, an estimate of CVD risk. PPG sensors are readily available, low-cost, and are able to be used without training, allowing the embodiments herein to be used to predict CVD risk even in low-resource healthcare systems.
Techniques are described herein for table cell splitting in an online document editor. A method includes: responsive to a request to split a cell in a table, determining a target number of rows and a target number of columns, automatically inserting rows adjacent to rows of the cell to reach the target number of rows, automatically inserting columns adjacent to columns of the cell to reach the target number of columns, and automatically merging groups of cells within an initial boundary of the cell, each group spanning a determined number of rows per group and a determined number of columns per group.
A first base station communicates with a UE via the first base station and a second base station. The first base station transmits, via a radio interface to the second base station, a configuration for concurrent communication between the UE and a group of base stations including the first base station and the second base station (802); and communicates, by processing hardware, data (i) over the radio interface directly with the UE, and (ii) via the radio interface and the second base station (804).
H04B 7/024 - Utilisation coopérative d’antennes sur plusieurs sites, p. ex. dans les systèmes à plusieurs points coordonnés ou dans les systèmes coopératifs à "plusieurs entrées plusieurs sorties" [MIMO]
H04W 28/08 - Équilibrage ou répartition des charges
78.
REDUCING POWER CONSUMPTION BY HARDWARE ACCELERATOR DURING GENERATION AND TRANSMISSION OF MACHINE LEARNING INFERENCES
A hardware accelerator can receive, from a host processor, a slice of input data at a time-step. The hardware accelerator can process the input data using a machine learning model deployed on the hardware accelerator to compute a respective probability among multiple probabilities for each of multiple classes. The respective probability for each class being a likelihood that content in the slice belongs to the class. The hardware accelerator can determine, from the multiple probabilities, a preset number of highest probabilities for the slice of input data. The hardware accelerator can transmit the preset number of highest probabilities for the slice to the host processor. Related apparatus, systems, techniques and articles are also described.
Implementations disclose selecting, in response to receiving a request and from among multiple candidate generative models (e.g., multiple candidate large language models (LLMs)) with differing computational efficiencies, a particular generative model to utilize in generating a response to the request. Those implementations reduce latency and/or conserve computational resource(s) through selection, for various requests, of a more computationally efficient generative model for utilization in lieu of a less computationally efficient generative model. Further, those implementations seek to achieve such benefits, through utilization of more computationally efficient generative models, while also still selectively utilizing less computationally efficient generative models for certain requests to mitigate occurrences of a generated response being inaccurate and/or under-specified. This, in turn, can mitigate occurrences of computational and/or network inefficiencies that result from a user issuing a follow-up request to cure the inaccuracies and/or under-specification of a generated response.
Implementations are directed to efficient federated learning of machine learning (ML) model(s) through on-the-fly decompression and compression of model parameters, of the ML model(s), when facilitating forward propagation and/or back propagation at client device(s). For example, implementations can transmit, from a remote system to a client device, a compressed on-device ML model that includes some compressed parameters. Further, the client device can, in performing forward propagation and/or back propagation using the on-device ML model, decompress those compressed parameters on-the-fly as the parameters are needed for the propagation. The propagation will utilize the decompressed parameters that were decompressed on the fly. Further, after the decompressed parameters are utilized, they can be deallocated from memory (while their compressed counterparts optionally remain in memory) to enable allocation of memory for further decompressed parameters that will be needed next and/or needed for other ongoing process(es).
G10L 15/06 - Création de gabarits de référenceEntraînement des systèmes de reconnaissance de la parole, p. ex. adaptation aux caractéristiques de la voix du locuteur
Arrangements for transitioning content are presented herein. A first signal, associated with a media playback device, can be received that includes first user identification information. A first user can be identified based on the first signal. Media content can be caused to be presented on the media playback device based on the identification of the first user. A second signal can be received that associated with the media playback device. A determination can be made that the first user has transitioned away from the media playback device based on the second signal. The media content may then no longer be presented by the media playback device in response to determining that the first user has transitioned away from the media playback device.
H04N 21/442 - Surveillance de procédés ou de ressources, p. ex. détection de la défaillance d'un dispositif d'enregistrement, surveillance de la bande passante sur la voie descendante, du nombre de visualisations d'un film, de l'espace de stockage disponible dans le disque dur interne
G06V 40/16 - Visages humains, p. ex. parties du visage, croquis ou expressions
H04H 60/33 - Dispositions de contrôle du comportement ou des opinions des utilisateurs
H04H 60/40 - Dispositions d'identification ou de reconnaissance de caractéristiques en liaison directe avec les informations radiodiffusées ou le créneau spatio-temporel de radiodiffusion, p. ex. pour identifier les stations de radiodiffusion ou pour identifier les utilisateurs pour identifier le temps ou l'espace de radiodiffusion pour identifier le temps de radiodiffusion
H04H 60/45 - Dispositions d'identification ou de reconnaissance de caractéristiques en liaison directe avec les informations radiodiffusées ou le créneau spatio-temporel de radiodiffusion, p. ex. pour identifier les stations de radiodiffusion ou pour identifier les utilisateurs pour identifier les utilisateurs
H04N 21/44 - Traitement de flux élémentaires vidéo, p. ex. raccordement d'un clip vidéo récupéré d'un stockage local avec un flux vidéo en entrée ou rendu de scènes selon des graphes de scène du flux vidéo codé
H04N 21/4415 - Acquisition de l'identification d'un utilisateur final utilisant les caractéristiques biométriques de l'utilisateur, p. ex. par reconnaissance de la voix ou balayage d'empreintes digitales
H04N 21/45 - Opérations de gestion réalisées par le client pour faciliter la réception de contenu ou l'interaction avec le contenu, ou pour l'administration des données liées à l'utilisateur final ou au dispositif client lui-même, p. ex. apprentissage des préférences d'utilisateurs pour recommander des films ou résolution de conflits d'ordonnancement
H04N 21/458 - Ordonnancement de contenu pour créer un flux personnalisé, p. ex. en combinant une publicité stockée localement avec un flux d'entréeOpérations de mise à jour, p. ex. pour modules de système d'exploitation
H04N 21/6587 - Paramètres de contrôle, p. ex. commande de lecture à vitesse variable ("trick play") ou sélection d’un point de vue
H04N 21/845 - Structuration du contenu, p. ex. décomposition du contenu en segments temporels
82.
RESTRICTED ENVIRONMENTS FOR MESSAGE GENERATION IN NETWORKED ENVIRONMENTS
Systems and methods described herein can provide a restricted environment for the local execution of server provided processor-executable instructions. The restricted environment can be maintained by a web browser to enable sandboxed generation of content requests by the web browser during the rendering of web pages. The restricted environment can enable the web browser to control the generation and transmission of content requests.
Implementations utilize a LLM to generate one or more summaries for long-form content such as an audiobook. Implementations determine whether the long-form content has a token length that exceeds a maximum token length for the LLM. In response to determining that the token length exceeds the maximum token length, the long-form content (or a transcript thereof) is segmented into at least a first content portion and a second content portion. A first summary is generated for the first content portion based on processing the first content portion as input using the LLM. A second summary is generated for the second content portion based on processing the first summary and the second content portion using the LLM. An overall summary can be generated to include the first and second summaries. The overall summary can be rendered visually and/or audibly in response to a user request for a summary of the long-form content.
Implementations relate to handling visual content across a multi-turn dialog. A user input that includes natural language content and visual content is received during the dialog. If the visual content is being received for the first time in the dialog, the visual content is processed to generate a corresponding tokenized representation of the visual content. The corresponding tokenized representation can be cached in a database in association with the dialog, or in association with a user account of a user of the user query. If the visual content is subsequently referenced in the dialog, the corresponding tokenized representation of the visual content is retrieved from the database. The corresponding tokenized representation of the visual content, corresponding tokenized representations of natural language content, and optionally other metadata can be processed, using a generative model, to generate a response responsive to the user input.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating suggested search queries. One method includes receiving, during a search session, a request for a suggested search query; in response to receiving the request for the suggested search query, identifying an entity that is associated with an item of media content; generating a suggested search query based on the identified entity; and providing data that causes the generated suggested search query to be presented in a user interface.
A method includes obtaining an input matrix and determining a domain index matrix that includes, for each respective input value of the input matrix, a corresponding domain index value that indicates a corresponding training data distribution of a plurality of training data distributions. The method also includes providing the input matrix and the domain index matrix to a machine learning model that has been trained using the plurality of training data distributions, where each respective training data distribution is associated with a different attribute. The method further includes generating, by the machine learning model and based on the input and the domain index matrices, an output matrix that includes, for each respective input value, a corresponding output value generated based on (i) the respective input value and (ii) the corresponding domain index value such that the corresponding output value exhibits the attribute of the corresponding training data distribution.
G06V 10/778 - Apprentissage de profils actif, p. ex. apprentissage en ligne des caractéristiques d’images ou de vidéos
G06V 10/771 - Sélection de caractéristiques, p. ex. sélection des caractéristiques représentatives à partir d’un espace multidimensionnel de caractéristiques
Determining a dialog state of an electronic dialog that includes an automated assistant and at least one user, and performing action(s) based on the determined dialog state. The dialog state can be represented as one or more slots and, for each of the slots, one or more candidate values for the slot and a corresponding score (e.g., a probability) for each of the candidate values. Candidate values for a slot can be determined based on language processing of user utterance(s) and/or system utterance(s) during the dialog. In generating scores for candidate value(s) of a given slot at a given turn of an electronic dialog, various features are determined based on processing of the user utterance and the system utterance using a memory network. The various generated features can be processed using a scoring model to generate scores for candidate value(s) of the given slot at the given turn.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for verifying current transformer polarity for one or more current transformers. In one aspect, a method comprises for each input power leg of a protected device, injecting a first test current into a first primary node H1 of a respective current transformer to induce a second test current in a first secondary node S1 of the respective current transformer, determining a positive test result based on the flow of the second current, and determining a polarity verification for each of the input power legs of the protected device when a positive test result is determined for each of the one or more input legs of the protected device.
G01R 35/02 - Test ou étalonnage des appareils couverts par les autres groupes de la présente sous-classe des dispositifs auxiliaires, p. ex. des transformateurs pour appareils en fonction du rapport de transformation, de l'angle de phase ou de la puissance à l'utilisation
H02M 3/335 - Transformation d'une puissance d'entrée en courant continu en une puissance de sortie en courant continu avec transformation intermédiaire en courant alternatif par convertisseurs statiques utilisant des tubes à décharge avec électrode de commande ou des dispositifs à semi-conducteurs avec électrodes de commande pour produire le courant alternatif intermédiaire utilisant des dispositifs du type triode ou transistor exigeant l'application continue d'un signal de commande utilisant uniquement des dispositifs à semi-conducteurs
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for blending content from different domains. A method includes obtaining, from a given content provider, a set of text and a set of images that are designated for combination to create a digital component. A saliency model is applied to an electronic document to identify salient areas in the electronic document. A set of modifications that do not result in the salient areas in the electronic document being overlapped are constructed. Visual characteristics of the electronic document are determined. A request for content to integrate into the electronic document that is provided by a different domain than the digital component is received. Visual modifications are made to the digital component based on (i) the constructed set of modifications and (ii) the determined visual characteristics of the electronic document. The modified digital component is served.
G06V 10/764 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant la classification, p. ex. des objets vidéo
G06V 30/413 - Classification de contenu, p. ex. de textes, de photographies ou de tableaux
G11B 27/10 - IndexationAdressageMinutage ou synchronisationMesure de l'avancement d'une bande
Methods, systems, and computer readable medium facilitating encrypted information retrieval. Methods can include receiving a batch of queries that includes queries to special buckets in each database shard. Query results responsive to the batch of queries are transmitted to the client device. The query results includes server-encrypted secret shares obtained from the special buckets. Client-encrypted versions of the secret shares are received. A full set of server-encrypted secret shares is transmitted to the client device, which is encrypted by the client device to create a full set of client-server-encrypted secret shares. The client device is classified based on how many of the secret shares are included in both of the client-encrypted secret shares received from the client device and the full set of client-server-encrypted secret shares received from the client device.
Implementations relate to improving instruction following capabilities of large language models (LLMs) using instruction decomposition, self-evaluation, and optionally progressive refinement. Processor(s) of a system can: obtain natural language (NL) based input, generate a plurality of candidate responses and evaluate the candidate responses based on instructions included in the NL based input, using an LLM, and progressively refine the candidate responses until it is determined that one or more termination criteria are satisfied. In some implementations, the NL based input can be received from a client device. In these implementations, a given candidate response that is progressively refined can be rendered for presentation at the client device and responsive to the NL base input. In additional or alternative implementations, the NL based input can be obtained from database(s). In these implementations, a given candidate response that is progressively refined can be utilized in fine-tuning of the LLM.
Systems and methods for calibrating a qubit parameter for a qubit in a quantum computing system are provided. In one example, a method includes obtaining, by one or more computing devices, data associated with a set of one or more qubit parameters for a qubit in a quantum computing system. The method includes obtaining, by the one or more computing devices, calibration data associated with at least one qubit parameter in the set of one or more qubit parameters. The method includes determining, by the one or more computing devices, a value for the at least one qubit parameter based at least in part on the calibration data using a de-corrupting autoencoder.
Methods, systems, and apparatus for producing CCZ states and T states. In one aspect, a method for transforming a CCZ state into three T states includes obtaining a first target qubit, a second target qubit and a third target qubit in a CCZ state; performing a X−1/2 gate on the third target qubit; performing an X gate on the first target qubit and the second target qubit using the third target qubit as a control; performing a Z gate on the first target qubit and the second target qubit using the third qubit as a X axis control; performing a Z−1/4 gate on the third target qubit; and performing a Z gate on the first target qubit and the second target qubit using the third qubit as a X axis control to obtain the three T states.
G06N 10/00 - Informatique quantique, c.-à-d. traitement de l’information fondé sur des phénomènes de mécanique quantique
G06N 10/20 - Modèles d’informatique quantique, p. ex. circuits quantiques ou ordinateurs quantiques universels
G06N 10/40 - Réalisations ou architectures physiques de processeurs ou de composants quantiques pour la manipulation de qubits, p. ex. couplage ou commande de qubit
H03K 19/003 - Modifications pour accroître la fiabilité
H03M 13/00 - Codage, décodage ou conversion de code pour détecter ou corriger des erreursHypothèses de base sur la théorie du codageLimites de codageMéthodes d'évaluation de la probabilité d'erreurModèles de canauxSimulation ou test des codes
H03M 13/03 - Détection d'erreurs ou correction d'erreurs transmises par redondance dans la représentation des données, c.-à-d. mots de code contenant plus de chiffres que les mots source
H03M 13/29 - Codage, décodage ou conversion de code pour détecter ou corriger des erreursHypothèses de base sur la théorie du codageLimites de codageMéthodes d'évaluation de la probabilité d'erreurModèles de canauxSimulation ou test des codes combinant plusieurs codes ou structures de codes, p. ex. codes de produits, codes de produits généralisés, codes concaténés, codes interne et externe
94.
Search System Having Task-Based Machined-Learned Models
A task-based search system is described. The computing system can receive, from a user device, a first user query associated with a task. The system can determine, using one or more machine-learned models, a first subtask having a first interaction score and a second subtask having a second user interaction score. Additionally, the system can perform a first query search for the first subtask to obtain a first content item associated with the first subtask. Moreover, the system can perform a second query search for the second subtask to obtain a second content item associated with the second subtask. Furthermore, the system can cause a presentation, on a display of the user device, of the first content item and the second content item. The first content item can be displayed above the second content item based on the first user interaction score being higher than the second user interaction score.
A method for turn detection in a speech-to-speech model includes receiving, as input to the speech-to-speech (S2S) model, a sequence of acoustic frames corresponding to an utterance. The method further includes, at each of a plurality of output steps, generating, by an audio encoder of the S2S model, a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames, and determining, by a turn detector of the S2S model, based on the higher order feature representation generated by the audio encoder at the corresponding output step, whether the utterance is at a breakpoint at the corresponding output step. When the turn detector determines that the utterance is at the breakpoint, the method includes synthesizing a sequence of output audio frames output by a speech decoder of the S2S model into a time-domain audio waveform of synthesized speech representing the utterance spoken by the user.
Systems and methods for generating a domain-specific conversational automated assistant. In some examples, a conversational language model is used to generate a target answer and a target action recommendation in response to each of a set of in-domain training questions. In some examples, the conversational language model is further used to generate follow-up questions to one or more of its generated target answers, and to then generate a target answer and target action recommendation to each generated follow-up question. In some examples, the processing system also generates a set of out-of-domain training examples including an out-of-domain question, a predetermined target answer, and a predetermined target action recommendation. The automated assistant may then be trained to predict the generated target answers and target action recommendations based on the associated training question or generated follow-up question, as well as any prior questions and answers in the conversation.
G06F 40/40 - Traitement ou traduction du langage naturel
G06N 3/006 - Vie artificielle, c.-à-d. agencements informatiques simulant la vie fondés sur des formes de vie individuelles ou collectives simulées et virtuelles, p. ex. simulations sociales ou optimisation par essaims particulaires [PSO]
A method includes determining a first state associated with a particular task, and determining, by a task policy model, a latent space representation of the first state. The task policy model may have been trained to define, for each respective state of a plurality of possible states associated with the particular task, a corresponding latent space representation of the respective state. The method also includes determining, by a primitive policy model and based on the first state and the latent space representation of the first state, an action to take as part of the particular task. The primitive policy model may have been trained to define a space of primitive policies for the plurality of possible states associated with the particular task and a plurality of possible latent space representations. The method further includes executing the action to reach a second state associated with the particular task.
The disclosed technology includes a timer logic architecture to reduce dynamic power dissipation by a group of multi-bit (M-bit) timers that operate to, for example, maintain command-to-command timing. The timer logic includes a global free running counter (FRC) that provides snapshots to individual timers and a clock gate logic. The timer logic causes the individual timers to be activated and dissipate power during fewer clock cycles. The disclosed technology may take the form of a device, system or method.
A method for generating a new video from a source video includes obtaining a source video, identifying video segments, in the source video, that each include a respective plurality of consecutive frames, obtaining frame subsets each corresponding to a different one of the video segments, generating, by a generative artificial intelligence (AI) model, new video segments each corresponding to a different one of the frame subsets by providing the frame subsets as inputs to the generative AI model, and generating a new video that includes the plurality of new video segments.
Methods and systems for artificial intelligence (AI) AI-based techniques for secondary content of electronic documents. Primary content provided by a user associated with an electronic document is identified. The primary content is included in a first region of the document. The primary content is included as an input to an AI model. One or more outputs of the AI model are obtained. The one or more outputs include secondary content corresponding to at least one of a style, a format, or a context of the primary content. The document is provided for presentation via a client device associated with the user. The primary content is included in the first region of the document and the secondary content is included in at least one of a background of the primary content in the first region or at a second region of the document that is adjacent to the first region.
