The present document describes techniques for providing a context-based user interface. These techniques include an electronic device having a user interface that dynamically adapts to a context of a visitor or a type of visitor. Characteristics associated with the visitor are detected, using sensors, and used to determine a context of the visitor. The user interface is then populated with curated, customized context-based options that correspond to the context of the visitor. The context-based options represent possible reasons for the visitor's visit and are estimated based on the detected characteristics. The visitor interacts with the user interface to select an appropriate context-based option to convey their intent for visiting an occupant of a building associated with the electronic device. Then, a notification associated with the selected context-based option is provided.
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
G06F 3/0485 - Défilement ou défilement panoramique
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
G06V 40/16 - Visages humains, p. ex. parties du visage, croquis ou expressions
H04N 7/18 - Systèmes de télévision en circuit fermé [CCTV], c.-à-d. systèmes dans lesquels le signal vidéo n'est pas diffusé
2.
Maximizing Generalizable Performance by Extraction of Deep Learned Features While Controlling for Known Variables
Provided are systems and methods for the generation of machine-learning features by clustering deep learning embeddings and selecting embedding cluster data while controlling for known associations. In particular, a computing system can use a pre-trained machine learning model (e.g., an image embedding model) to obtain embeddings of input images. The computing system can train a clustering algorithm (e.g., a k-means algorithm) to cluster these embeddings into one of a number (e.g., k) clusters. The computing system can then perform a selection process to select one or more (e.g., the top n) clusters that boost performance in a prediction model (e.g., a logistic regression model) trained with a combination of the selected clusters and one or more baseline features. In such fashion, the computer system can enable an improved combination of extracted deep learned features and baseline features. This can maximize generalizable performance while controlling for known variables.
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 10/762 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant le regroupement, p. ex. de visages similaires sur les réseaux sociaux
G06V 10/766 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant la régression, p. ex. en projetant les caractéristiques sur des hyperplans
G06V 10/776 - ValidationÉvaluation des performances
G06V 20/69 - Objets microscopiques, p. ex. cellules biologiques ou pièces cellulaires
G16H 30/40 - TIC spécialement adaptées au maniement ou au traitement d’images médicales pour le traitement d’images médicales, p. ex. l’édition
G16H 50/20 - TIC spécialement adaptées au diagnostic médical, à la simulation médicale ou à l’extraction de données médicalesTIC spécialement adaptées à la détection, au suivi ou à la modélisation d’épidémies ou de pandémies pour le diagnostic assisté par ordinateur, p. ex. basé sur des systèmes experts médicaux
3.
Techniques for Presenting Graphical Content in a Search Result
Techniques for presenting a search result with an improved user interface. A computer system can receive, from a user device, a request for a content item. Additionally, the system can select, based on the request, a first content item from a plurality of content items. The first content item can be associated with an organization image and an organization name of an organization. Moreover, the system can process, using one or more machine-learned model, the organization image to determine whether the organization image is acceptable to be presented in the search result. Subsequently, the system can transmit, to the user device, the first content item and the organization image to be presented in the search result.
G06F 16/955 - Recherche dans le Web utilisant des identifiants d’information, p. ex. des localisateurs uniformisés de ressources [uniform resource locators - URL]
G06V 10/776 - ValidationÉvaluation des performances
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium. In one aspect, a method includes the actions of receiving a request to perform computations for a neural network on a hardware circuit having a matrix computation unit, the request specifying a transpose operation to be performed on a first neural network matrix; and generating instructions that when executed by the hardware circuit cause the hardware circuit to transpose the first neural network matrix by performing first operations, wherein the first operations include repeatedly performing the following second operations: for a current subdivision of the first neural network matrix that divides the first neural network matrix into one or more current submatrices, updating the first neural network matrix by swapping an upper right quadrant and a lower left quadrant of each current submatrix, and subdividing each current submatrix into respective new submatrices to update the current subdivision.
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
G06F 7/78 - Dispositions pour le réagencement, la permutation ou la sélection de données selon des règles prédéterminées, indépendamment du contenu des données pour changer l'ordre du flux des données, p. ex. transposition matricielle ou tampons du type pile d'assiettes [LIFO]Gestion des occurrences du dépassement de la capacité du système ou de sa sous-alimentation à cet effet
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for hotword detection on multiple devices are disclosed. In one aspect, a method includes the actions of receiving, by a first computing device, audio data that corresponds to an utterance. The actions further include determining a first value corresponding to a likelihood that the utterance includes a hotword. The actions further include receiving a second value corresponding to a likelihood that the utterance includes the hotword, the second value being determined by a second computing device. The actions further include comparing the first value and the second value. The actions further include based on comparing the first value to the second value, initiating speech recognition processing on the audio data.
In some implementations, the method may include disposing an infrared (IR) absorbing material at one or both of a first surface of a first transparent body composed of a polymer or a second surface of a second transparent body composed of the polymer. In addition, the method may include positioning the first transparent body adjacent to the second transparent body so that the first surface abuts the second surface. The method may include bonding the first transparent body to the second transparent body through reflow of the polymer at an interface between the first surface and the second surface by emitting light, via a first light source, into the first transparent body and which is converted to heat energy by the IR absorbing material.
Implementations relate to training a model that can be used to process values for defined features, where the values are specific to a user account, to generate a predicted user measure that reflects both popularity and quality of the user account. The model is trained based on losses that are each generated as a function of both a corresponding generated popularity measure and a corresponding generated quality measure of a corresponding training instance. Accordingly, the model can be trained to generate, based on values for a given user account, a single measure that reflects both quality and popularity of the given user account. Implementations are additionally or alternatively directed to utilizing such predicted user measures to restrict provisioning of content items that are from user accounts having respective predicted user measures that fail to satisfy a threshold.
A head-mounted device comprises a frame; a lens coupled to the frame, the lens being configured to reflect infrared light from an interior side of the lens and pass visible light; and a camera configured to capture the infrared light reflected from the interior side of the lens and to capture the visible light passing through the lens.
The present disclosure provides systems, methods, and computer program products for performing automated non-linear editing style transfer. A computer-implemented method may include determining one or more shot boundaries in a video, analyzing identified content in each of one or more shots in the video based on performing object detection, determining an editing style for each of the one or more shots in the video based at least in part on measuring motion across frames within the respective shots, determining a content segment to adjust from a set of target content based on analyzing the set of target content in view of the identified content and the determined editing style of a shot from the video, and automatically adjusting the content segment from the set of target content based at least in part on modifying the content segment with the determined editing style of the shot from the video.
G11B 27/031 - Montage électronique de signaux d'information analogiques numérisés, p. ex. de signaux audio, vidéo
G11B 27/19 - IndexationAdressageMinutage ou synchronisationMesure de l'avancement d'une bande en utilisant une information détectable sur le support d'enregistrement
10.
System And Method For Storing And Providing Routes
In one aspect, a system and method is provided whereby map-related requests from mobile devices are used to store and aggregate routes. The routes are then used to determine optimum directions in response to subsequent requests.
A method including receiving first data including a feature corresponding to an application, receiving second data including a specification of a component included in a device, analyzing a performance of the device based on the first data and the second data using a model, and modifying the specification based on the performance of the device.
A method is disclosed for detecting feature outages in a user interface by observing user behaviors in response to interactions with the user interface. The method involves calculating aggregated user behavior metrics for a most recent detection period and comparing them with aggregated user behavior metrics for a prior detection period to determine if they fall within an expected range. If the aggregated user behavior metrics for the most recent detection period are found to be outside the expected range, an action is initiated. This method enables the timely detection of feature outages in the user interface based on predictive user behaviors, allowing for prompt remedial actions to be taken.
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for performing image restoration tasks using a diffusion neural network.
A method includes receiving a query to determine anomalies in a set of multivariate time series data values including an endogenous variable and an exogenous variable. The method includes determining an impact of the exogenous variable on the endogenous variable. The method includes determining a set of univariate time series data values and training one or more models using the univariate time series data values. The method includes determining an expected data value for a respective time series data value and determining a difference between the expected data value and the respective time series data value. The method includes determining that the difference between the expected data value for a particular time series data value and the particular time series data value satisfies a threshold. In response, the method includes determining that the particular time series data value is anomalous and reporting the anomalous value to a user.
A heatsink cooling system includes a liquid reservoir; a boiling chamber configured to boil a liquid when heated from an external heat source adjacent the boiling chamber, a pump in fluid communication with the liquid reservoir and the boiling chamber; and a vapor space in fluid communication with the liquid reservoir separated from the boiling chamber by a membrane, wherein vapor evaporated from the boiling chamber is configured to pass through the membrane into the vapor space, condense into a liquid within the vapor space, and return to the liquid reservoir.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an encoder that generates a watermark and a decoder that decodes a data item encoded within the watermark. The training comprises obtaining a plurality of training images and data items. For each training image, a first watermark is generated using an encoder and a subsequent second watermark is generated by tiling two or more first watermarks. The training image is watermarked using the second watermark to generate a first error value and distortions are added to the watermarked image. A distortion detector predicts the distortions based on which the distorted image is modified. The modified image is decoded by the decoder to generate a predicted data item and a second error value. The training parameters of the encoder and decoder are adjusted based on the first and the second error value.
H04N 19/467 - Inclusion d’information supplémentaire dans le signal vidéo pendant le processus de compression caractérisée par le caractère invisible de l’information incluse, p. ex. un filigrane
G06T 1/00 - Traitement de données d'image, d'application générale
A method for improving integration testing quality includes accessing a software module and determining a plurality of critical user journeys (CUJs) in the software module. The method also includes obtaining a set of CUJ tests corresponding to the software module, each CUJ test of the set of CUJ tests testing at least one CUJ. The method also includes, for a first CUJ of the plurality of CUJs, determining that the set of CUJ tests fails to include a CUJ test that tests the first CUJ, and, in response to determining that the set of CUJ tests fails to include the CUJ test that tests the first CUJ, generating, a first CUJ test testing the first CUJ. The method includes adding the first CUJ test to the set of CUJ tests. The method also includes testing the plurality of CUJs using the set of CUJ tests.
Techniques for operating an environmental sensing system are described. In an example, a cloud-based server system receives a first indication that a first type of air pollutant is present within a first structure from a first plurality of indoor air quality (IAQ) sensing devices positioned within the first structure. A second structure within a predefined distance to the first structure is then identified by the server system. The server system then determines that the first type of air pollutant is not present within the second structure. The server system then causes a second plurality of IAQ sensing devices positioned within the second structure to change an operating mode from a normal sensitivity mode to a high-sensitivity mode.
Techniques for creating health assessments based on Volatile Organic Compound (VOC) detection are described. In an example, a VOC sensor measures a concentration of a VOC within an enclosed space during a time period. An accumulation of carbon dioxide is detected within the space during the time period. Based on the accumulation of carbon dioxide it is determined that a human is present within the space and that the space is substantially sealed. The VOC sensor then detects that the concentration of the VOC within the space increased during the time period. A health assessment for the human is generated based on the detected increase in the VOC and a notification including the assessment is issued to an electronic device.
A61B 5/083 - Mesure du taux de métabolisme en utilisant un essai respiratoire, p. ex. mesure du taux de consommation d'oxygène
A61B 5/00 - Mesure servant à établir un diagnostic Identification des individus
A61B 5/0205 - Évaluation simultanée de l'état cardio-vasculaire et de l'état d'autres parties du corps, p. ex. de l'état cardiaque et respiratoire
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
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 50/30 - TIC spécialement adaptées au diagnostic médical, à la simulation médicale ou à l’extraction de données médicalesTIC spécialement adaptées à la détection, au suivi ou à la modélisation d’épidémies ou de pandémies pour le calcul des indices de santéTIC spécialement adaptées au diagnostic médical, à la simulation médicale ou à l’extraction de données médicalesTIC spécialement adaptées à la détection, au suivi ou à la modélisation d’épidémies ou de pandémies pour l’évaluation des risques pour la santé d’une personne
Disclosed implementations for generating personalized audio. In response to receiving sensor data corresponding with a physical characteristic of a user, a first function is determined based on a similarity between the physical characteristic of the user and a first model and a second function is determined based on a similarity of the physical characteristic between the user and a second model. A modified function, representing an audio response, is generated by combining the first function and the second function. An audio stream is generated based on the modified function.
The technology is generally directed to reducing the impact of power fluctuations caused by workloads. The workloads may be executed by a machine, such as a server within a datacenter. The workloads may be memory and/or processing intensive workloads, such as artificial intelligence (AI) workloads. Such AI workloads have become more frequent with the integration of AI into computer based applications. The power fluctuations may occur at a given frequency, such as every “N” seconds. The power fluctuations may be smoothed by increasing the rise and/or fall time of the fluctuation and/or by reducing the magnitude of the fluctuation. Smoothing the fluctuations may be done by an energy supply injecting power into and/or absorbing power from the power system of the rack.
Methods, systems and apparatus for measuring the energy of a quantum chemical system. In one aspect, a method includes obtaining a Hamiltonian describing the chemical system, where the Hamiltonian is expressed in an orthonormal basis; decomposing the Hamiltonian into a sum of terms where each term comprises a respective operator that effects a respective single particle basis rotation, and one or more particle density operators; repeatedly, for each group comprising terms with a same operator that effects a respective single particle basis rotation, measuring expectation values of the terms included in the group, comprising: performing the respective single particle basis rotation on a qubit system encoding a state of the chemical system; and measuring Jordan-Wigner transformations of the one or more particle density operators in the group to obtain a respective measurement result for the group; and determining the energy of the chemical system using the obtained measurement results.
G16C 10/00 - Chimie théorique computationnelle, c.-à-d. TIC spécialement adaptées aux aspects théoriques de la chimie quantique, de la mécanique moléculaire, de la dynamique moléculaire ou similaires
G06N 5/01 - Techniques de recherche dynamiqueHeuristiquesArbres dynamiquesSéparation et évaluation
G06N 10/60 - Algorithmes quantiques, p. ex. fondés sur l'optimisation quantique ou les transformées quantiques de Fourier ou de Hadamard
A computer-implemented method that provides watermark-based image reconstruction to compensate for lossy encoding schemes. The method can generate a difference image describing the data loss associated with encoding an image using a lossy encoding scheme. The difference image can be encoded as a message and embedded in the encoded image using a watermark and later extracted from the encoded image. The difference image can be added to the encoded image to reconstruct the original image. As an example, an input image encoded using a lossy JPEG compression scheme can be embedded with the lost data and later reconstructed, using the embedded data, to a fidelity level that is identical or substantially similar to the original.
Methods and systems for asynchronous updates for media item access history embeddings are provided herein. An embedding that represents a media item access history associated with a client device with respect to a first set of media items previously accessed by the client device is identified. A determination is made of whether one or more embedding relevance criteria are satisfied with respect to the media item access history of the client device. Responsive to a determination that the one or more embedding relevance criteria are satisfied, a media item is selected of a second set of media items not yet accessed by the client device based on the embedding. The client device is provided with access to the selected media item.
Techniques and apparatuses are described for overcoming memory, bandwidth, and/or power constraints in a processing-in-memory architecture. Example techniques include on-the-fly type conversion and/or sparsity support. On-the-fly type conversion converts data of a first numerical data type to a second numerical data type that matches an expected numerical data type of a logic circuit of a memory device. With on-the-fly type conversion, the memory device can conserve memory and realize a higher effective internal bandwidth while having a flexible design that can support a variety of different memory architectures and/or different machine-learned models. With sparsity support, the processing-in-memory can avoid performing operations that involve data having values equal to zero to conserve power. Also, sparsity support can increase an effective bandwidth for transferring data and conserve memory. With the described techniques, the memory device can utilize processing-in-memory to perform larger and more complex operations for implementing features associated with artificial intelligence.
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
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
26.
RADAR-BASED MOTION-ACTIVATED LIGHTING AND TRACKING
Various arrangements of radar-based lighting and tracking systems are presented herein. Radar signals may be output into an environment. Based on reflected radar signals, a target may be identified. Various characteristics of the target can be analyzed. In response to characteristics, lighting may be activated and aimed at the target. A camera may be used to capture and record images of the illuminated target.
G01S 7/41 - Détails des systèmes correspondant aux groupes , , de systèmes selon le groupe utilisant l'analyse du signal d'écho pour la caractérisation de la cibleSignature de cibleSurface équivalente de cible
G01S 7/02 - Détails des systèmes correspondant aux groupes , , de systèmes selon le groupe
G01S 13/66 - Systèmes radar de poursuiteSystèmes analogues
G01S 13/86 - Combinaisons de systèmes radar avec des systèmes autres que radar, p. ex. sonar, chercheur de direction
27.
METHODS, SYSTEMS, AND MEDIA FOR SYNCHRONIZED MEDIA CONTENT PLAYBACK ON MULTIPLE DEVICES
A method for synchronizing media content playback on multiple devices includes receiving a first request of a first user device of a first user to concurrently watch a media item with at least one second user of a second user device, receiving a first communication from the first user device to begin presenting the media item on the first user device, receiving a second communication from the second user device to begin presenting the media item on the second user device, in response to receiving the first communication and the second communication, initiating a synchronized media playback session, in response to a first request of the second user to pause playback of the media item on the second user device, causing a rate of delivery of the media item to the second user device to be changed from a first rate of delivery to a second rate of delivery, and in response to a second request of the second user to resume playback of the media item on the second user device, causing the second rate of delivery of the media item to the second user device to be changed to a third rate of delivery to allow the second user device to catch up to the first user device in the synchronized media playback session.
H04N 21/43 - Traitement de contenu ou données additionnelles, p. ex. démultiplexage de données additionnelles d'un flux vidéo numériqueOpérations élémentaires de client, p. ex. surveillance du réseau domestique ou synchronisation de l'horloge du décodeurIntergiciel de client
H04N 21/234 - Traitement de flux vidéo élémentaires, p. ex. raccordement de flux vidéo ou transformation de graphes de scènes du flux vidéo codé
28.
Emotionally Intelligent Responses to Information Seeking Questions
A method for generating emotionally intelligent responses to information seeking questions includes receiving audio data corresponding to a query spoken by a user and captured by an assistant-enabled device associated with the user, and processing, using a speech recognition model, the audio data to determine a transcription of the query. The method also includes performing query interpretation on the transcription of the query to identify an emotional state of the user that spoke the query, and an action to perform. The method also includes obtaining a response preamble based on the emotional state of the user and performing the identified action to obtain information responsive to the query. The method further includes generating a response including the obtained response preamble followed by the information responsive to the query.
G06F 16/683 - Recherche de données caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu
G10L 13/10 - Règles de prosodie dérivées du texteIntonation ou accent tonique
G10L 15/26 - Systèmes de synthèse de texte à partir de la parole
G10L 15/30 - Reconnaissance distribuée, p. ex. dans les systèmes client-serveur, pour les applications en téléphonie mobile ou réseaux
G10L 25/63 - 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 pour estimer un état émotionnel
Systems and methods related to intelligent grippers with individual cup control are disclosed. One aspect of the disclosure provides a method of determining grip quality between a robotic gripper and an object. The method comprises applying a vacuum to two or more cup assemblies of the robotic gripper in contact with the object, moving the object with the robotic gripper after applying the vacuum to the two or more cup assemblies, and determining, using at least one pressure sensor associated with each of the two or more cup assemblies, a grip quality between the robotic gripper and the object.
Provided is an advanced framework designed for the reconstruction of shape, material, and illumination from images captured with varying lighting, pose, and background. This framework addresses the challenge in computer vision and graphics of inverse rendering based on unconstrained image collections by optimizing over shape, radiance, and pose. The proposed framework can utilize a unique implicit shape representation based on a hybrid encoding scheme that includes both a multi-resolution hash encoding and Fourier feature encodings. This hybrid encoding scheme allows for rapid and robust shape reconstruction with joint camera alignment optimization.
A method (300) includes receiving a task prompt (162) representative of a user input (106) from a user and identifying, based on the task prompt, a context (212) of the user input. The task prompt specifies a task for a large language model (LLM) (150) to perform responsive to the user input. The method also includes determining, based on the context of the user input, a user correction prompt (202) including one or more user changes (232) made by the user to one or more prior outputs (152) of the LLM. The method also includes providing, as input to the LLM, the task prompt conditioned on the user correction prompt to cause the LLM to generate a personalized response (152) to the user input and providing the personalized response to the user input for output from a user device (10) associated with the user.
Method comprising: receiving, by a computing device, an indication to launch a voice-based television assistant; displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending, by the computing device and to a server computer, the first voice data for the first query; receiving a response to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation. Method for providing a personalized description of a media content item and method for providing a trivia game related to a media content item.
G10L 15/22 - Procédures utilisées pendant le processus de reconnaissance de la parole, p. ex. dialogue homme-machine
H04H 60/33 - Dispositions de contrôle du comportement ou des opinions des utilisateurs
H04H 60/65 - 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 utilisateurs
H04H 60/46 - 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 reconnaître les préférences des utilisateurs
33.
ARBITRARY RESOLUTION DIFFUSION SUPER RESOLUTION ON RAY TRACED IMAGES
Tracing and super resolution diffusion are utilized to generate high quality imagery via a trained model. This approach limits the number of tracing iterations to avoid issues with computational complexity. This includes applying a low-resolution image of a first size via a tracing tracing process to a denoise diffusion SR model to generate a resultant high-resolution image of a larger size. The process includes retrieving, at least a portion of imagery data (502) and performing an iterative tracing operation in a plurality of iterations to generate an initial image having a first resolution (504). Then using the first image and a target scaling factor, an iterative super-resolution operation is performed with diffusion and denoising to generate a final image having a second resolution greater than the first resolution, in which the iterative super-resolution operation has multiple iterations that each generate a respective intermediate image having a corresponding noise value (506).
G06T 3/4053 - Changement d'échelle d’images complètes ou de parties d’image, p. ex. agrandissement ou rétrécissement basé sur la super-résolution, c.-à-d. où la résolution de l’image obtenue est plus élevée que la résolution du capteur
Implementations utilize a smaller LLM to generate content responsive to a user query and cause a portion of the generated content to be rendered as an immediate response to the user query. Implementations further utilize a larger LLM to generate content that starts with the portion of the generated content and that includes a refined portion succeeding the portion of the generated content. The refined portion can be rendered succeeding the portion of the generated content. In some implementations, instead of using the smaller LLM, alternatively, the portion of the generated content rendered as the immediate response can be generated based on a default text string or a template, where the template can be determined/selected from a plurality of predefined templates based on a natural language understanding of the user query.
Presenting the goods of third parties provided via a
searchable website; comparison shopping services;
advertising and promoting the goods and services of others
via a global computer network; online advertising services
for others; promoting the goods and services of others,
namely, providing special offers, price-comparison
information, product reviews, links to the retail websites
of others, discount information, and online catalogs
featuring a wide variety of consumer goods of others;
promoting the goods and services of others via wireless
network, mobile telecommunication devices, and global
computer network.
36.
Single Image 3D Photography with Soft-Layering and Depth-aware Inpainting
A method includes determining, based on an image having an initial viewpoint, a depth image, and determining a foreground visibility map including visibility values that are inversely proportional to a depth gradient of the depth image. The method also includes determining, based on the depth image, a background disocclusion mask indicating a likelihood that pixel of the image will be disoccluded by a viewpoint adjustment. The method additionally includes generating, based on the image, the depth image, and the background disocclusion mask, an inpainted image and an inpainted depth image. The method further includes generating, based on the depth image and the inpainted depth image, respectively, a first three-dimensional (3D) representation of the image and a second 3D representation of the inpainted image, and generating a modified image having an adjusted viewpoint by combining the first and second 3D representation based on the foreground visibility map.
A method performed by a first user device coordinating with one or more other user devices to facilitate communications with a wireless communication network includes pairing with a second user device to establish a pairing link, and receiving, from the wireless communication network, configuration parameters for communicating with the wireless communication network via one or more frequencies. The method further includes transmitting the configuration parameters to the second user device via the pairing link, receiving an activation message from the wireless communication network and, in response to receiving the activation message, transmitting, via the pairing link, an activation signal that indicates to the second user device to start communicating with the wireless communication network using the one or more frequencies in accordance with the configuration parameters.
H04W 72/25 - Canaux de commande ou signalisation pour la gestion des ressources entre terminaux au moyen d’une liaison sans fil, p. ex. liaison secondaire
H04L 5/00 - Dispositions destinées à permettre l'usage multiple de la voie de transmission
The present disclosure provides systems and methods for determining the orientation of a device based on visible and/or non-visible orientation cues. The orientation cues may be a geographically located objects, such as a park, body of water, monument, building, landmark, etc. The orientation cues may be visible or non-visible with respect to the location of the device. The device may use one or more image sensors to detect the visible orientation cues. Non-visible orientation cues may be associated with map data. Using the location of the orientation cue and the distance of the orientation cue to the device, the orientation of the device may be determined. The device may then provide an output indicating the orientation of the device.
This document describes systems and techniques for protecting the security of information in content selection and distribution. In one aspect, a method includes receiving, by a first computing system of MPC systems, a digital component request including distributed point functions that represent a secret share of a respective point function that indicates whether a user of the client device is a member of a first user group. Selection values are identified. Each selection value corresponds to a respective digital component, a set of contextual signals, and a respective second user group identifier for a respective second user group to which the respective digital component is eligible to be distributed. A determination is made, for each selection value and using the distributed point functions in a secure MPC process, a candidate parameter that indicates whether the second user group identifier matches a user group that includes the user as a member.
Implementations set forth herein relate to assigning users to cohorts and generating assistant content for presenting to the user based on their respectively assigned cohort and to reduce user churn out. Each cohort can belong to a plurality of cohorts that vary according to the level of experience, proficiency, and/or engagement that a user has historically exhibited with respect to a particular application and/or feature. A user can be assigned to multiple cohorts in circumstances in which a user may be proficient with respect to certain features of an application but not other features. When a user is estimated to be churning out or otherwise disengaging with respect to a particular feature, assistant content associated with that particular feature can be generated and rendered at a particular time that may not distract the user and may result in further engagement with the particular feature.
Systems and methods for video query contextualization can include a router model that determines how to process and respond to the query associated with the video. The systems and methods can include obtaining an input query and video data, processing the input query and the video data with the router model to generate a video clip and routing data, and the routing data can then be utilized to determine which processing system to utilize to process the video clip and the input query. The video clip can then be processed with the determined processing system to generate a query response that may be provided to the user.
Artificial intelligence (AI) functionality is becoming pervasive in electronic devices, including mobile ones in which interior volume and printed circuit board (PCB) area are constrained. AI processing also taxes computing hardware differently. Some tasks are relatively compute-bound, and some tasks are relatively memory-bound. Balancing these competing factors is challenging. In example implementations, AI engines are disposed in various locations to facilitate compute-bound and memory-bound AI tasks while efficiently utilizing area of a PCB. For example, a first package assembly can include nonvolatile memory and DRAM with processor-in-memory realized as at least one AI processing unit for memory-bound tasks. The first package assembly can also include an AI engine with greater processing capabilities for compute-bound tasks. Further, a second package assembly, which is coupled to the first package assembly, can include an SoC with a still more-capable AI engine. This enables AI tasks to be assigned to an appropriate AI engine.
H01L 25/18 - Ensembles consistant en une pluralité de dispositifs à semi-conducteurs ou d'autres dispositifs à l'état solide les dispositifs étant de types prévus dans plusieurs différents groupes principaux de la même sous-classe , , , , ou
H05K 1/18 - Circuits imprimés associés structurellement à des composants électriques non imprimés
H10B 80/00 - Ensembles de plusieurs dispositifs comprenant au moins un dispositif de mémoire couvert par la présente sous-classe
Techniques and apparatuses are described that provide radar sensing for multiple applications. In an example aspect, middleware is coupled between multiple applications and a radar system. The middleware performs translation services, conflict resolution and/or resource management to configure the radar system in a manner that can provide radar sensing to at least a substantial subset of the applications during a given time interval. Also, the middleware can dynamically adjust the operation of the radar system as different applications request radar sensing. The middleware enables the radar system to provide radar sensing for a larger quantity of diverse applications without integrating additional radar systems into the computing device and/or without the applications needing to communicate and/or negotiate with each other. In this way, the middleware can expand the utilization of the radar system, thereby providing additional features to enhance the user experience.
Techniques and apparatuses are described for overcoming memory, bandwidth, and/or power constraints in a processing-in-memory architecture. In example aspects, a memory device includes a logic circuit that is coupled to at least two banks. The memory device receives commands for concurrently performing at least a portion of a page operation and at least a portion of a processing-in-memory computation. The processing-in-memory computation is performed using the logic circuit and using data that was previously read from one of the active banks. The page operation is performed on another one of the banks that is idle to enable the logic circuit to access the data within this other bank for a later processing-in-memory computation. By performing the page operation during a same time as the processing-in-memory computation, a latency associated with the page operation can be effectively masked, thereby improving an overall efficiency of the memory device.
G11C 11/4093 - Dispositions d'interface d'entrée/sortie [E/S, I/O] de données, p. ex. mémoires tampon de données
G11C 11/4096 - Circuits de commande ou de gestion d'entrée/sortie [E/S, I/O] de données, p. ex. circuits pour la lecture ou l'écriture, circuits d'attaque d'entrée/sortie ou commutateurs de lignes de bits
45.
Learning with Label Differential Privacy via Projections
Aspects of the disclosure are directed to implementing a projection-based stochastic gradient descent technique that maintains label differential privacy when training one or more machine learning models. The technique includes denoising gradients by exploiting projections when training the machine learning models to improve performance of the trained machine learning models while maintaining label differential privacy. For instance, the projection-based stochastic gradient descent technique can improve performance of machine learning models in higher-privacy regimes, such as digital content management.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. One of the methods includes receiving training data comprising a plurality of unlabeled training inputs and a plurality of labeled training inputs; generating augmented training data, comprising generating, for each of the plurality of unlabeled training inputs, a respective augmented training input by applying a data augmentation technique to the unlabeled training input; and training the machine learning model on the augmented training data. In particular, but not exclusively, the model may be trained for perceptual tasks (e.g., tasks relating to vision or speech).
G06F 18/21 - Conception ou mise en place de systèmes ou de techniquesExtraction de caractéristiques dans l'espace des caractéristiquesSéparation aveugle de sources
G06F 18/214 - Génération de motifs d'entraînementProcédés de Bootstrapping, p. ex. ”bagging” ou ”boosting”
A method includes executing an initial instance of a change log process for a distributed system, each instance of the change log process configured to store a transaction history of transactions executed on the distributed system. The method also includes receiving transaction requests for executing corresponding transactions on the distributed system and determining a change log load based on the received transaction requests. The method includes executing at least one subsequent instance of the change log process when the change log load satisfied a threshold load. When multiple instances of the change log process are executing, the method includes ceasing execution of the at least one subsequent instance of the change log process and merging the transaction history of the initial instance of the change log process and the transaction history of the at least one subsequent instance of the change log process.
G06F 9/46 - Dispositions pour la multiprogrammation
G06F 16/27 - Réplication, distribution ou synchronisation de données entre bases de données ou dans un système de bases de données distribuéesArchitectures de systèmes de bases de données distribuées à cet effet
48.
PROCESSING VIDEO AND TEXT INPUTS USING CO-TOKENIZATION
Generally, the present disclosure is directed to systems and methods that perform adaptive optimization with improved convergence properties. The adaptive optimization techniques described herein are useful in various optimization scenarios, including, for example, training a machine-learned model such as, for example, a neural network. In particular, according to one aspect of the present disclosure, a system implementing the adaptive optimization technique can, over a plurality of iterations, employ an adaptive learning rate while also ensuring that the learning rate is non-increasing.
Various implementations are directed towards fine-tuning a large language model (LLM) using search engine feedback (e.g., responsive content generated based on a reference source material such as a set of search engine results). Additionally or alternatively, a supervision signal can be generated based on comparing search engine conditioned LLM output with unconditioned LLM output. In many implementations, the supervision signal(s) can be used in training a reward model using reinforcement learning, where the trained reward model can be used in fine-tuning the LLM.
A computer platform for generating a video includes one or more memories to store instructions and one or more processors to execute the instructions to perform operations, the operations including: receiving a query from a user relating to a location; in response to receiving the query, generating conditioning parameters based at least in part on the query, wherein the conditioning parameters provide values for one or more conditions associated with a scene to be rendered at the location; generating, using a generative machine-learned model, the video, wherein the video depicts the scene at the location and with the values for the one or more conditions; and providing the video for presentation to the user.
Implementations relate to utilizing generative model(s) to generate a personalized summary of content that is interactive. Processor(s) of a system can: select a plurality of sources of content to be utilized in generating the summary of the content, cause the summary of the content to be generated using the generative model(s), and cause the summary of the content to be rendered. In some implementations, the processor(s) can proactively determine to cause the summary of the content to be generated and rendered (e.g., based on one or more triggering criteria being satisfied). In other implementations, the processor(s) can reactively determine to cause the summary of the content to be generated and rendered (e.g., based on user input being received). In various implementations, while the summary of the content is being rendered, a user can interrupt the rendering of the summary of the content, and the processor(s) can handle the interruption accordingly.
G06F 40/58 - Utilisation de traduction automatisée, p. ex. pour recherches multilingues, pour fournir aux dispositifs clients une traduction effectuée par le serveur ou pour la traduction en temps réel
Implementations utilize a smaller LLM to generate content responsive to a user query and cause a portion of the generated content to be rendered as an immediate response to the user query. Implementations further utilize a larger LLM to generate content that starts with the portion of the generated content and that includes a refined portion succeeding the portion of the generated content. The refined portion can be rendered succeeding the portion of the generated content. In some implementations, instead of using the smaller LLM, alternatively, the portion of the generated content rendered as the immediate response can be generated based on a default text string or a template, where the template can be determined/selected from a plurality of predefined templates based on a natural language understanding of the user query.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for preserving user privacy when selecting content are described. In some aspects, a method includes receiving a data element identifying a set of candidate digital components and, for each candidate digital component, a set of distribution parameters for the candidate digital component. For each candidate digital component, encrypted selection data for the candidate digital component is provided as input to a cryptographic analysis application running in a trusted hardware module of a client device. The encrypted selection data represents the set of distribution parameters for the candidate digital component and is encrypted using a zero-knowledge proof protocol. The cryptographic analysis application is configured to determine a measure of match between the selection data and user attributes of a user of 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
G06F 21/10 - Protection de programmes ou contenus distribués, p. ex. vente ou concession de licence de matériel soumis à droit de reproduction
Techniques and apparatuses are described for machine-learning architectures for broadcast and multicast communications. A network entity processes broadcast or multicast communications using a deep neural network (DNN) to direct the one or more broadcast or multicast communications to a targeted group of user equipments (UEs) using the wireless communication system. The network entity receives feedback from at least one user equipment (UE) of the targeted group of UEs. The network entity determines a modification to the DNN based on the feedback. The network entity transmits an indication of the modification to the targeted group of UEs. The network entity updates the DNN with the modification to form a modified DNN. The network entity processes the broadcast or multicast communications using the modified DNN to direct the broadcast or multicast communications to the targeted group of UEs using the wireless communication system.
Implementations are directed to generating synthetic labeled/preference data by extracting preference pairs from sets of N outputs to a given unlabeled input to a generative model. A plurality of generative outputs are generated by a generative model from a set of input data. A reward model is used to determine a plurality of reward values for the plurality of generative outputs. Based on the reward values, a pair of generative outputs from the plurality of generative outputs is selected for inclusion in a training example. The pair of outputs include a positive training example and a negative training example, where the reward values indicate that the positive training example is preferred over the negative training example. The process can be repeated for a plurality of sets of input data to generate a plurality of training examples for inclusion in a training dataset, which can be used to update reward model(s).
This document describes systems and techniques directed at bezel-less display mounts for foldable electronic devices. In aspects, a foldable electronic device includes a housing with a display recess that includes an inwardly projecting ledge. A foldable display structure, which includes a display panel and a cover layer, is positioned in the display recess. In aspects, the cover layer includes a variable thickness along at least one dimension. The cover layer defines an extension portion that extends beyond one or more edges of the display panel. A back adhesive portion is disposed between the bottom face of the display panel and the bottom of the housing and a perimeter adhesive portion is disposed between the extension portion of the cover layer and the ledge. In this way, the foldable electronic device can do away with a bezel (e.g., display trim) that would otherwise surround a perimeter of the display panel.
Implementations utilize a LLM to generate content responsive to a user query directed to a video and cause audio data for the generated content to be rendered as a response to the user query. Implementations extract a subset of frames from all frames of the video as key frame(s) for the video, and utilize a vision-language model in generating a natural language description for the key frame(s) of the video. A prompt can be generated based on a transcription of the user query and based on the natural language description for the key frame(s) of the video. The prompt is processed as input, using the LLM, to generate the content responsive to the user query directed to the video.
G06F 16/583 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu
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
59.
DYNAMIC PROBABILITIES BASED INTERMIXING FOR TELEVISION RECOMMENDATIONS
According to an aspect, a method may include determining, by a server computer, category affinity score criteria for a user for a plurality of media content categories. A method may calculate a probability for the user for each of the plurality of media content categories based on the category affinity score criteria. A method may associate at least one media content category with each media content provider of a plurality of media content providers. A method may categorize each media content item of the plurality of media content items into at least one media content category of the plurality of media content categories. A method may create a ranked list of a plurality of media content items sourced by the plurality of media content providers.
H04N 21/25 - Opérations de gestion réalisées par le serveur pour faciliter la distribution de contenu ou administrer des données liées aux utilisateurs finaux ou aux dispositifs clients, p. ex. authentification des utilisateurs finaux ou des dispositifs clients ou apprentissage des préférences des utilisateurs pour recommander des films
H04N 21/258 - Gestion de données liées aux clients ou aux utilisateurs finaux, p. ex. gestion des capacités des clients, préférences ou données démographiques des utilisateurs, traitement des multiples préférences des utilisateurs finaux pour générer des données collaboratives
H04N 21/262 - Ordonnancement de la distribution de contenus ou de données additionnelles, p. ex. envoi de données additionnelles en dehors des périodes de pointe, mise à jour de modules de logiciel, calcul de la fréquence de transmission de carrousel, retardement de la transmission de flux vidéo, génération de listes de reproduction
A method (500) includes receiving a query (20) to determine anomalies in multivariate time series data (152) including an endogenous variable (152D) and an exogenous variable (152X). The method includes determining an impact (164) of the exogenous variable on the endogenous variable. The method includes determining univariate time series data (152U) and training one or more models (172) using the univariate time series data. The method includes determining an expected value (152E) for a respective time series value and determining a difference between the expected value and the respective time series value. The method includes determining that the difference between the expected value for a particular time series value and the particular time series value satisfies a threshold. In response, the method includes determining that the particular time series data value is anomalous and reporting the anomalous value (152A) to a user (12).
Implementations described herein relate to utilizing a large language model (LLM) to determine whether a natural language (NL) based input is grammatically incorrect and notifying a user based on the determination. A structured LLM query may be generated, based on the NL based input, that includes an LLM prompt to cause the LLM to generate an LLM response including an indication of whether the NL based input is grammatically incorrect. An LLM response may be generated, based on causing the structured LLM query to be processed using the LLM, that includes the indication of whether the NL based input is grammatically incorrect. Responsive to determining that the NL based input is grammatically incorrect based on the LLM response, a feedback output may be caused to be rendered at the client device, or an additional client device, that indicates the NL based input is grammatically incorrect.
A multimodal search system is described. The system can receive image data from a user device. Additionally, the system can receive a prompt associated with the image data. Moreover, the system can determine, using a computer vision model, a first object in the image data that is associated with the prompt. Furthermore, the system can receive, from the user device, a user indication on whether the image data includes the first object. Subsequently, in response to receiving the user indication, the system can generate a response using a large language model.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting images generated by artificial intelligence using trained neural networks. In one aspect, a method comprises receiving a input media asset, processing the input media asset using a trained embedding neural network to generate an embedding, processing the embedding using a classifier to generate a respective score for each of the multiple categories, where two or more of the multiple categories each correspond to a different generative model of multiple generative models, and determining whether the input media asset was generated by one of the multiple generative models based on the respective scores.
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
Implementations are directed to generating synthetic labeled/preference data by extracting preference pairs from sets of N outputs to a given unlabeled input to a generative model. A plurality of generative outputs are generated by a generative model from a set of input data. A reward model is used to determine a plurality of reward values for the plurality of generative outputs. Based on the reward values, a pair of generative outputs from the plurality of generative outputs is selected for inclusion in a training example. The pair of outputs include a positive training example and a negative training example, where the reward values indicate that the positive training example is preferred over the negative training example. The process can be repeated for a plurality of sets of input data to generate a plurality of training examples for inclusion in a training dataset, which can be used to update reward model(s).
Various implementations are directed towards fine-tuning a large language model (LLM) using search engine feedback (e.g., responsive content generated based on a reference source material such as a set of search engine results). Additionally or alternatively, a supervision signal can be generated based on comparing search engine conditioned LLM output with unconditioned LLM output. In many implementations, the supervision signal(s) can be used in training a reward model using reinforcement learning, where the trained reward model can be used in fine-tuning the LLM.
42 - Services scientifiques, technologiques et industriels, recherche et conception
Produits et services
Providing on-line non-downloadable software for computer security and threat detection, monitoring, and prevention; Software as a service (SAAS) services featuring software for computer security and threat detection, monitoring, and prevention.
72.
SECURITY BREACH DETECTION AND MITIGATION IN A CLOUD-BASED ENVIRONMENT
Methods and systems for security breach detection and mitigation in a cloud-based environment are provided herein. Event data associated with client devices of a cloud-based environment are provided as input to a trained artificial intelligence (AI) model. The event data indicates activities performed with respect to the client devices. One or more outputs of the AI model are obtained, the one or more outputs indicating activities, of the event data, that is indicative of a security breach, one or more security actions to be taken at the cloud-based environment in response to the activities, and for each of the one or more security actions, a level of confidence that a respective security action will mitigate the security breach. A security action having a level of confidence that satisfies a confidence criterion is determined. A set of operations to initiate the determined security action at the cloud-based environment is performed.
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
73.
MODIFYING SUBPORTIONS OF LARGE LANGUAGE MODEL OUTPUTS
Implementations are described herein for using LLMs to modify less than the entirety of rendered LLM outputs. In various implementations, a first LLM response is used by a client application to provide first rendered LLM output. The client application may provide (i) an indication of a subportion of the first rendered LLM output that is selected by a user, and (ii) a request to modify the selected subportion. A subportion of the first LLM response corresponding to the selected subportion of the first rendered LLM output may be used to assemble a second LLM prompt, which may be processed using one or more LLMs to generate a second LLM response. The second LLM response may be operable to provide second rendered LLM output that includes at least part of the first rendered LLM output outside of the selected subportion and the modified selected subportion.
A method including during a calibration operation, establishing communication with a test fixture, via a communication channel between the test fixture and a head mounted device (HMD), during the calibration operation, obtaining inertial measurement unit (IMU) data based on output from an IMU in the HMD generated based on movement of the HMD caused by a text fixture to which the HMD is coupled, during the calibration operation, generating IMU calibration data for the HMD based on the IMU data, during the calibration operation, store the IMU calibration data in the HMD, and after the calibration operation is completed (or in response to completing the calibration operation), implement at least one technical measure to prevent subsequent modification of the IMU calibration data.
G01P 21/00 - Essai ou étalonnage d'appareils ou de dispositifs couverts par les autres groupes de la présente sous-classe
G01C 25/00 - Fabrication, étalonnage, nettoyage ou réparation des instruments ou des dispositifs mentionnés dans les autres groupes de la présente sous-classe
75.
Scheduling-Based Idle Power Reduction For Machine Learning Accelerator Systems
A method and system for controlling a supply voltage provided to a processor by generating a voltage setting command by a workload scheduler; and responding to the voltage setting command by instructing a voltage regulator that provides the supply voltage, at a supply voltage level, to set the supply voltage level to one of at least an idle voltage level or an active voltage level that is higher than the idle voltage level.
Systems, devices, methods, and non-transitory, machine-readable media may correspond to in-ear acoustic devices, such as an earbud, with transparency and noise-cancellation. The earbud may include one or a combination of the following. A housing may include a first section and a second section. A speaker may be housed by the housing. A first volume may be partially defined by the speaker and the first section. A second volume may be partially defined by the speaker and the second section. A bypass duct may fluidically connect the first volume with the second volume. The bypass duct may include a vent to outside of the housing.
Aspects of the disclosure are directed to an architecture including a dynamic serialization buffer and/or dynamic deserialization buffer coupled between a vector processing unit and a matrix multiplication unit. The dynamic serialization buffer and/or dynamic deserialization buffer allow for streaming any integer of vectors per cycle when performing acceleration of matrix multiplication operations. The matrix multiplication unit receives vectors equivalent to an amount of data from the vector processing unit at an arbitrary rate of vectors per cycle. The matrix multiplication unit processes the vectors to generate resulting vectors that are output at the arbitrary rate.
G06F 15/80 - Architectures de calculateurs universels à programmes enregistrés comprenant un ensemble d'unités de traitement à commande commune, p. ex. plusieurs processeurs de données à instruction unique
The subject matter described herein provides systems and techniques to address the challenges of growing hardware and workload heterogeneity using a Warehouse-Scale Computer (WSC) design that improves the efficiency and utilization of WSCs. The WSC design may include an abstraction layer and an efficiency layer in the software stack of the WSC. The abstraction layer and the efficiency layer may be designed to improve job scheduling, simplify resource management, and drive hardware-software co-optimization using machine learning techniques and automation in order to customize the WSC for applications at scale. The abstraction layer may embrace platform/hardware and workload diversity through greater coordination between hardware and higher layers of the WSC software stack in the WSC design. The efficiency layer may employ machine learning techniques at scale to realize hardware/software co-optimizations as a part of the autonomous WSC design.
Training and/or using both a high-level policy model and a low-level policy model for mobile robot navigation. High-level output generated using the high-level policy model at each iteration indicates a corresponding high-level action for robot movement in navigating to the navigation target. The low-level output generated at each iteration is based on the determined corresponding high-level action for that iteration, and is based on observation(s) for that iteration. The low-level policy model is trained to generate low-level output that defines low-level action(s) that define robot movement more granularly than the high-level action—and to generate low-level action(s) that avoid obstacles and/or that are efficient (e.g., distance and/or time efficiency).
G05D 1/00 - Commande de la position, du cap, de l'altitude ou de l'attitude des véhicules terrestres, aquatiques, aériens ou spatiaux, p. ex. utilisant des pilotes automatiques
Methods, systems, and apparatus, for image difference generation. In some implementations, raw image data is obtained for an image. Compressed image data is obtained for the image. A decoded frame is generated from the compressed image data. Differences in pixel values between at least a portion of the raw image data and the decoded frame are computed. An image file is generated that includes both the compressed image data and a representation of the differences in pixel values.
The technology generally relates to preventing unwanted tracking using wireless finding devices. For example, wireless finding devices may contain one or more protection features to prevent improper use or unwanted tracking. The wireless finding device may monitor the voltage and current waveforms applied at and/or to the notification mechanism to determine if the notification mechanism has been tampered with. If the wireless finding device determines that the notification mechanism has been tampered with, the wireless finding device may activate a protection feature inhibiting tracking of the wireless finding device. For example, in response to determining the output device has been tampered with and/or failed, the wireless finding device may disable or degrade tracking. Disabling and/or degrading the tracking of the wireless finding device may prevent unwanted tracking.
A user equipment (UE) is configured to initiate a packet-switched call via a first radio access technology (RAT) and start a plurality of session initiation protocol (SIP) timers responsive to initiating the call. Responsive to at least one condition being present with initiation of a fallback process for the call, the UE is configured to restart a set of the plurality of SIP timers for the fallback process, wherein the set can include some or all of the plurality of SIP timers started with initiation of the call. Each SIP timer has a corresponding default timer duration, and in some instances restarting a SIP timer of the set includes restarting the SIP timer with a starting duration equal to a sum of the default timer duration and an offset so that the restarted SIP timer provides for a greater duration than when originally started to better accommodate the fallback process.
A method includes receiving a task prompt representative of a user input from a user and identifying, based on the task prompt, a context of the user input. The task prompt specifies a task for a large language model (LLM) to perform responsive to the user input. The method also includes determining, based on the context of the user input, a user correction prompt including one or more user changes made by the user to one or more prior outputs of the LLM. The method also includes providing, as input to the LLM, the task prompt conditioned on the user correction prompt to cause the LLM to generate a personalized response to the user input and providing the personalized response to the user input for output from a user device associated with the user.
The technology described herein is directed to spatial interface for multi-modal input to artificial intelligence (AI) powered tools. The interface allows for a first mode of input, such as selection of one or more objects using a movable window that can be resized and reshaped by a user. In addition, the interface allows for a second mode of input, such as text or voice commands. The AI powered tools accept the inputs from the first and second modes and dynamically generates a response.
Decoding using motion vector prediction with derived motion trajectory includes obtaining, from previously reconstructed reference frames available for reconstructing a current frame, reference frame motion fields data for reconstructing the current frame, obtaining, using the reference frame motion fields data, trajectory mapping data for reconstructing the current frame, accessing, from the encoded bitstream, current encoded block data for a current block of the current frame; obtaining a motion vector prediction for the current block in accordance with the trajectory mapping data, obtaining a differential motion vector from the current encoded block data, obtaining a motion vector for the current block by adding the motion vector prediction and the differential motion vector, decoding the current block using the motion vector to obtain decoded block data for the current block, and obtaining reconstructed frame data for the current frame using the decoded block data.
H04N 19/139 - Analyse des vecteurs de mouvement, p. ex. leur amplitude, leur direction, leur variance ou leur précision
H04N 19/105 - Sélection de l’unité de référence pour la prédiction dans un mode de codage ou de prédiction choisi, p. ex. choix adaptatif de la position et du nombre de pixels utilisés pour la prédiction
H04N 19/176 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c.-à-d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p. ex. un objet la zone étant un bloc, p. ex. un macrobloc
86.
DETECTING ERRORS IN CHAT BOT OUTPUTS USING LANGUAGE MODEL NEURAL NETWORKS
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting errors in chat bot outputs. For example, the errors can be hallucination errors, coverage errors, or both.
A method for a data escrow service includes receiving, from a user device, an access query requesting generation of an access request for allowing a user associated with the user device access to one or more datasets of a plurality of datasets. The access query includes natural language text describing information associated with the one or more datasets of the plurality of datasets. The method includes determining, using a large language model (LLM) and the access query, the one or more datasets. The method includes generating the access request requesting the user gain temporary access to the one or more datasets. The method also includes providing, to the user device, a notification of the one or more datasets and the access request. The notification does not include any data from the one or more datasets.
A flexible annotation framework normalizes auxiliary information from diverse sources, ranks the information for an individual search result, and provides a lightweight or full display of the auxiliary information in an annotation for the search result. An annotation thus displays information not typically part of the details included in the search result. An example method comprises, for at least one item in a search result page, identifying at least one annotation of a first annotation type in an annotation data store that references the item, identifying at least one annotation for a second annotation type in an annotation data store that references the item, ranking the annotation of the first annotation type and the annotation of the second annotation type and providing the highest ranked annotation as part of a search result for the item in the search result page.
Techniques are described herein for providing smart suggestions for image zoom regions. A method includes: receiving a search query; performing a search using the search query to identify search results that include image search results including a plurality of images that are responsive to the search query; for a given image of the plurality of images included in the image search results, determining at least one zoom region in the given image; and providing the search results including the image search results, including providing the given image and an indication of the at least one zoom region in the given image.
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 10/20 - 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
91.
Tracking Subsea Telecommunications Asset Capacity and Spectrum
A method includes generating a first asset token that represents control, by a first entity, of a portion of a physical communication asset. The method includes publishing, to a distributed ledger, ownership of the first asset token and receiving, from a second entity, a request to control the portion of the physical communication asset represented by the first asset token. In response to receiving the request, the method includes removing the first asset token from circulation on the distributed ledger and generating a second asset token representing control, by the second entity, of the portion of the physical communication asset. The method also includes publishing, to the distributed ledger, ownership of the second asset token and transferring, using the distributed ledger, ownership of the second asset token to the second entity.
H04L 9/00 - Dispositions pour les communications secrètes ou protégéesProtocoles réseaux de sécurité
H04B 13/02 - Systèmes de transmission dans lesquels le milieu de propagation est constitué par la terre ou une grande masse d'eau la recouvrant, p. ex. télégraphie par le sol
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
92.
RENDERING AUGMENTED REALITY CONTENT BASED ON POST-PROCESSING OF APPLICATION CONTENT
Implementations relate to an automated assistant that provides augmented reality content, via a display interface of computerized glasses, resulting from post-processing of application content. The application content can be identified based on prior interactions between a user and one or more applications, and the application content can be processed to determine objects, and/or object classifications, that may be associated with the application content. When the user is wearing the computerized glasses, and the object is detected within a field of view of the computerized glasses, the automated assistant can cause certain content to be rendered at the display interface of the computerized glasses. In some implementations, the content can be generated to supplement, and/or be different from, existing content that the user may have already accessed, in furtherance of preventing duplicative usage of applications and/or preserving computational resources.
Restoring a clustered database having a plurality of nodes each having database from a failed storage device by receiving a request to restore a backup image of a failed shared storage device associated with the clustered database to a time; performing a preflight check including at least one checklist process; terminating the restore when any checklist process fails; when each checklist process succeeds completing the restore by creating at least one flashcopy associated with the backup image, mapping to each of the plurality of nodes an associated portion of the at least one flashcopy, mounting the at least one flashcopy to the node as a diskgroup, and switching the clustered database to run from the diskgroup.
G06F 11/14 - Détection ou correction d'erreur dans les données par redondance dans les opérations, p. ex. en utilisant différentes séquences d'opérations aboutissant au même résultat
A method of encoding and decoding user interface interactions includes receiving a query from a user captured by an assistant-enabled device associated with the user. The query includes a user intent for interacting with an application. The method includes obtaining, for the application, a set of categorized actions. Each categorized action of the set of categorized actions is associated with one or more parameters and represents a high-level description of the user intent of the user interacting with the application. For each respective categorized action of the set of categorized actions, the method includes selecting a respective script associated with the respective categorized action that performs one or more low-level interactions with the application and executing the respective script to represent the user intent for interacting with the application.
G06F 3/0484 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] pour la commande de fonctions ou d’opérations spécifiques, p. ex. sélection ou transformation d’un objet, d’une image ou d’un élément de texte affiché, détermination d’une valeur de paramètre ou sélection d’une plage de valeurs
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
Aspects of the disclosure provide for a system for navigating a conversation graph using a language model trained to generate Application Programming Interface (API) calls in response to natural language input from a user computing device. A conversational agent implementing a state handler and a language model (LM) communicates with a user computing device through a user frontend. Rather than communicating directly with a user with output in natural language, the agent uses a (LM) trained as described herein to navigate a conversation graph. The state handler receives API calls generated by the LM and updates the state of a conversation with a user as indicated in the graph. After the update, the state handler can perform one or more predetermined actions associated with a node indicating the current state of the conversation.
A method may include measuring an optical property of a display panel for an input gray level at a first refresh rate. The method may also include measuring the optical property for a plurality of candidate gray levels at a second refresh rate. The method may further include selecting, based on the measured optical properties of the display panel, a corresponding gray level for the input gray level, wherein the corresponding gray level is selected from the plurality of candidate gray levels. The method may also include storing, at the device, the corresponding gray level for the input gray level, wherein subsequent to the storing, the device is configured to adjust input display data using the corresponding gray level for the input gray level when the display panel is transitioning from the first refresh rate to the second refresh rate.
G09G 3/20 - Dispositions ou circuits de commande présentant un intérêt uniquement pour l'affichage utilisant des moyens de visualisation autres que les tubes à rayons cathodiques pour la présentation d'un ensemble de plusieurs caractères, p. ex. d'une page, en composant l'ensemble par combinaison d'éléments individuels disposés en matrice
97.
SELECTION AND PROVISION OF DIGITAL COMPONENTS DURING DISPLAY OF CONTENT
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for the selection, provision and display of one or more digital components during display of content. Methods can include identifying a plurality of digital components that can be presented on the client device. A maximum number of digital components that can be presented in a slot of a content and the time duration of the slot is determined. For each digital component a score is generated based on the duration, a position requirement and the number of times the digital component is available for provision within the slot is generated. A first set of digital component is selected based on the scores and provided to the client device.
A method includes receiving, by a processing device of a content delivery network, a first request for desired content from a client device. The first request comprises one or more resource locators for accessing the desired content and a partial trust metric generated, by a content sharing platform, in response to a second request for the desired content from the client device. A client device trust status is determined based on the partial trust metric. Responsive to the client device trust status indicating that the client device is authorized to receive the desired content, playback of the desired content is provided to 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
G06N 5/01 - Techniques de recherche dynamiqueHeuristiquesArbres dynamiquesSéparation et évaluation
H04N 21/258 - Gestion de données liées aux clients ou aux utilisateurs finaux, p. ex. gestion des capacités des clients, préférences ou données démographiques des utilisateurs, traitement des multiples préférences des utilisateurs finaux pour générer des données collaboratives
99.
Method For Detecting And Classifying Coughs Or Other Non-Semantic Sounds Using Audio Feature Set Learned From Speech
A method of detecting a cough in an audio stream includes a step of performing one or more pre-processing steps on the audio stream to generate an input audio sequence comprising a plurality of time-separated audio segments. An embedding is generated by a self-supervised triplet loss embedding model for each of the segments of the input audio sequence using an audio feature set, the embedding model having been trained to learn the audio feature set in a self-supervised triplet loss manner from a plurality of speech audio clips from a speech dataset. The embedding for each of the segments is provided to a model performing cough detection inference. This model generates a probability that each of the segments of the input audio sequence includes a cough episode. The method includes generating cough metrics for each of the cough episodes detected in the input audio sequence.
G10L 25/66 - 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 pour extraire des paramètres en rapport avec l’état de santé
A61B 5/00 - Mesure servant à établir un diagnostic Identification des individus
A61B 5/08 - Dispositifs de mesure pour examiner les organes respiratoires
G10L 15/02 - Extraction de caractéristiques pour la reconnaissance de la paroleSélection d'unités de reconnaissance
G10L 15/04 - SegmentationDétection des limites de mots
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
G10L 25/30 - Techniques d'analyse de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par la technique d’analyse utilisant des réseaux neuronaux
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
G10L 25/78 - Détection de la présence ou de l’absence de signaux de voix
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
100.
SYSTEMS AND TECHNIQUES FOR RETRAINING MODELS FOR VIDEO QUALITY ASSESSMENT AND FOR TRANSCODING USING THE RETRAINED MODELS
A trained model is retrained for video quality assessment and used to identify sets of adaptive compression parameters for transcoding user generated video content. Using transfer learning, the model, which is initially trained for image object detection, is retrained for technical content assessment and then again retrained for video quality assessment. The model is then deployed into a transcoding pipeline and used for transcoding an input video stream of user generated content. The transcoding pipeline may be structured in one of several ways. In one example, a secondary pathway for video content analysis using the model is introduced into the pipeline, which does not interfere with the ultimate output of the transcoding should there be a network or other issue. In another example, the model is introduced as a library within the existing pipeline, which would maintain a single pathway, but ultimately is not expected to introduce significant latency.
G06V 10/98 - Détection ou correction d’erreurs, p. ex. en effectuant une deuxième exploration du motif ou par intervention humaineÉvaluation de la qualité des motifs acquis
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 20/40 - ScènesÉléments spécifiques à la scène dans le contenu vidéo
