Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework that provides advancements in electronic messages are presented to users, as well as how users are capable of interacting with such messages, and the content included and/or referenced therein. The disclosed framework provides novel mechanisms for displaying messages in a modified manner that provides users with previously non-native functionality for viewing compiled summaries of the email content within the displayed inbox, message item without having to open the message. The disclosed functionality enables the triaging of emails without having to interact (e.g., open, forward, reply, and the like), all from the inbox listing of a user's account.
Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework that provides advancements in electronic messages are presented to users, as well as how users are capable of interacting with such messages, and the content included and/or referenced therein. The disclosed framework provides novel mechanisms for modifying how an electronic message is displayed within an account inbox, whereby such modifications enable interactions with the content in the message as well as the electronic/network resources associated with such message/content without requiring the message to be opened. Thus, streamlined mechanisms are provided that enable advanced capabilities for inbox management and interactions therefrom, which can reduce resource expenditure by the device accessing the inbox and the system hosting the inbox, as well increase in user experience.
A method, implemented on at least one computing device each of which has at least one processor, storage, and a communication platform connected to a network for presenting a search result in a search result card, the method includes receiving from a user, an input associated with a search query; fetching one or more search results in accordance with the search query; generating a search result card for each of the one or more search results; and presenting to the user, one or more search result cards as a response to the search query, the one or more search result cards corresponding to the one or more search results, respectively.
G06F 16/248 - Présentation des résultats de requêtes
G06F 3/0482 - Interaction avec des listes d’éléments sélectionnables, p. ex. des menus
G06F 3/04883 - 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 pour l’entrée de données par calligraphie, p. ex. sous forme de gestes ou de texte
G06F 16/22 - IndexationStructures de données à cet effetStructures de stockage
G06F 16/438 - Présentation des résultats des requêtes
G06F 16/951 - IndexationTechniques d’exploration du Web
G06F 16/9535 - Adaptation de la recherche basée sur les profils des utilisateurs et la personnalisation
G06F 16/9538 - Présentation des résultats des requêtes
4.
METHOD AND SYSTEM FOR PREFETCHING TARGETED CONTENT
In the embodiments, a novel prefetch service implemented on a prefetch server is provided to execute content (either targeted or selected) fetch requests in parallel with other requests thereby reducing the overall latency of a content delivery system. In some aspects, a method is provided to receive a prefetch request to prefetch a targeted content item to be presented prior to presenting a primary content item on a user device, the prefetch request including prefetch request parameters; generate, a callback URL associated with the prefetch request; transmit, to a primary content server, the callback URL; obtain a targeted content configuration corresponding to the prefetch request parameters; obtain the targeted content item based on the targeted content configuration; receive, a request to provide the targeted content item, the request including the callback URL; and transmit the targeted content item.
H04N 21/231 - Opération de stockage de contenu, p. ex. mise en mémoire cache de films pour stockage à court terme, réplication de données sur plusieurs serveurs, ou établissement de priorité des données pour l'effacement
H04N 21/234 - Traitement de flux vidéo élémentaires, p. ex. raccordement de flux vidéo ou transformation de graphes de scènes du flux vidéo codé
5.
SYSTEM AND METHOD FOR PROVIDING CONTEXT OF WEB CONTENT
The present teaching relates to providing contextual information to web content. Relevant information is extracted from a current article that a user is reviewing. Contextual information associated with the current article is retrieved from a database based on the extracted relevant information. A zoom-out summary of the contextual information is automatically generated to characterize the background of the current article. A zoom-out option is presented to the user that allows the user to review, once the option is activated, the zoom-out summary to understand the background of the current article.
In an example, in connection with a search clustering system, a grouping component retrieves a timestamp set of news queries and determines a time-stable set of news query groups by performing the first stage of a two-stage clustering technique. A clustering component determines a time-stable set of news query groups clusters by performing the second stage of the two-stage clustering technique. The performance of the two-stage clustering technique is aided by a least recently used caching component. The time-stable set of news query groups clusters may be served to a web page in order to generate a trending topic list for display.
G06F 16/2457 - Traitement des requêtes avec adaptation aux besoins de l’utilisateur
G06F 16/955 - Recherche dans le Web utilisant des identifiants d’information, p. ex. des localisateurs uniformisés de ressources [uniform resource locators - URL]
The present teaching relates to recommending content by analyzing the streamed data. A request is received from a user requesting one or more recommendations from a set of items. A first distribution indicative of an interest distribution of the user in a plurality of topics is obtained. For each item, a second distribution indicative of a classification distribution of the item with respect to the plurality of topics is obtained. A score is estimated based on the first distribution and the second distribution, wherein the score indicates likelihood that the user is interested in the item. The scores associated with the set of items are ranked. The one or more recommendations are presented based on the ranked scores.
G06F 16/735 - Filtrage basé sur des données supplémentaires, p. ex. sur des profils d'utilisateurs ou de groupes
G06F 16/2457 - Traitement des requêtes avec adaptation aux besoins de l’utilisateur
G06F 16/435 - Filtrage basé sur des données supplémentaires, p. ex. sur des profils d'utilisateurs ou de groupes
G06F 16/738 - Présentation des résultats des requêtes
G06F 16/78 - Recherche de données caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement
The present teaching relates to providing a query suggestion. In one example, a request is received for query suggestions with respect to a query prefix input by a user. A plurality of query suggestions is determined based on the query prefix and a preceding query input by the user. A degree of popularity of the preceding query is determined. One or more query suggestions are selected from the plurality of query suggestions based on the degree of popularity of the preceding query. The one or more query suggestions are provided as a response to the request.
In some implementations, the techniques described herein relate to a method including: (i) training, by a processor, a machine learning model to create composite images from background scenes and foreground objects, (ii) identifying, by the processor, a digital image file that comprises a background scene and an additional digital image file that comprises a foreground object, (iii) compositing, by the machine learning model executed by the processor, the digital image file that comprises the background scene and the additional digital image file that comprises the foreground object to produce a composite digital image file that comprises the foreground object and the background scene by performing at least one of a channel concatenation step and a reverse diffusion sampling step, and (iv) causing display, by the processor, of the composite image file that comprises the foreground object and the background scene.
One or more computing devices and/or methods are provided. In an example, a feature-sensitive query may be received. A first language model may be used to generate an executable feature constraint determination command based upon a set of information including the feature-sensitive query. The executable feature constraint determination command may be executed to determine a feature constraint associated with the feature-sensitive query. The data structure may be analyzed based upon the feature constraint to identify a subset of data, of the data structure, relevant to the feature constraint. A response to the feature-sensitive query may be generated based upon the subset of data.
One or more computing devices and/or methods are provided. In an example, a query may be received. A set of content items associated with the query may be identified. A first language model may be used to determine a plurality of sets of contextual information based upon the set of content items. For example, a first set of contextual information of the plurality of sets of contextual information is determined based upon the query and a first content item of the set of content items. A second set of contextual information is determined based upon the query and a second content item of the set of content items. A second language model may be used to determine a response to the query based upon the plurality of sets of contextual information.
Methods, systems and programming for providing query suggestions based on user feedback. In one example, a prefix of a query is first received. An input including a prefix of a query is received from a user in a search session. A plurality of query suggestions are fetched based on the prefix of the query. Rankings of the plurality of query suggestions are determined based, at least in part, on the user's previous interactions in the search session with respect to at least one of the plurality of query suggestions. The at least one of the plurality of query suggestions has been previously provided to the user in the search session. The plurality of query suggestions are provided in the search session based on their rankings as a response to the input.
One or more computing devices, systems, and/or methods for determining activity patterns based upon user activity and/or performing operations based upon the activity patterns are provided. For example, activity performed using a communication interface associated with a user account may be detected. The activity may be analyzed to determine an activity pattern associated with a first set of conditions. The activity pattern may be stored in a user profile associated with the user account. The user profile may comprise a plurality of activity patterns. Each activity pattern of the plurality of activity patterns may be associated with a set of conditions of a plurality of sets of conditions. It may be determined that the first set of conditions are met. Responsive to determining that the first set of conditions are met, one or more operations associated with the activity pattern may be performed.
In some implementations, the techniques described herein relate to a method including: identifying, by a processor, a digital image file that includes a background scene and an additional digital image file that includes a foreground object; compositing, by a machine learning model executed by the processor, the digital image file and the additional digital image file to produce a composite digital image file that includes the foreground object placed in front of the background scene by: identifying a location within the background scene in the digital image file for placement of the foreground object from the additional digital image file; transforming at least one aspect of the foreground object to harmonize with the background scene; and creating a composite image file that includes the harmonized foreground object in the location within the background scene; causing display, by the processor, of the composite image file.
One or more computing devices, systems, and/or methods for generating a user-specific transaction interface are provided. In an example, a datastore of a user may be searched for an indication of a potential transaction. The datastore may include an email mailbox and/or a record of web browsing. In response to identifying the potential transaction, the datastore of the user, a partnership datastore and/or a network may be searched for an opportunity associated with the potential transaction. In response to identifying the opportunity associated with the potential transaction, a user-specific transaction interface may be generated. The user-specific transaction interface may include one or more selectable inputs for engaging in a version of the potential transaction. The user-specific transaction interface may be provided for display on a device of the user.
G06Q 20/40 - Autorisation, p. ex. identification du payeur ou du bénéficiaire, vérification des références du client ou du magasinExamen et approbation des payeurs, p. ex. contrôle des lignes de crédit ou des listes négatives
G06Q 20/38 - Protocoles de paiementArchitectures, schémas ou protocoles de paiement leurs détails
16.
SYSTEMS AND METHODS FOR USING AI TO FACILITATE IMAGE EDITING
In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, an image. (ii) receiving, by the processor, natural language instructions for editing the image, the natural language instructions including a location within the image and an editing instruction, (iii) editing, by a machine learning model executed by the processor, the location within the image based on the natural language instructions by (a) identifying a region within the image that corresponds to the location in the natural language instructions and (b) editing the identified region by applying the editing instruction to the identified region to generate an edited image, and (iv) causing, by the processor, display of the edited image.
Systems and methods are disclosed for providing a value analysis. One method comprises receiving an original set of one or more records, an exchange portion of the original set, a selected record set of one or more selected records, a time period, and an interval length from a user, computing original set data of the original set, determining base set data for a base set for the interval length over the time period, comparing the original set and the base set to determine an exchange value, determining an updated exchange value for the selected record set, updating the base set and the base set data to include the selected record set and the updated exchange value, and displaying at least one model of the original set data and the updated base set data for each selected record of the selected record set on a user interface of the user device.
The present teaching relates to predicting a temporal attention region corresponding to an event of interest in a video clip. Training data is obtained with training samples, each of which includes a historic video clip with a temporal attention region in consecutive frames to represent an event of interest captured in the temporal attention region and is used for training, via machine learning, a temporal attention zone model for predicting a temporal attention zone in a video clip representing an event of interest. The trained model is used to predict, from an input video clip, a temporal attention zone represented by consecutive frames in the input video clip that capture the event of interest.
Improved systems and methods for enhancing the performance of network based computerized content rendering and hosting and providing of devices, systems and/or platforms by modifying the capabilities and providing non-native functionality to such devices, systems and/or platforms through a novel and improved application, networked based enforcement of geographical compliance, data processing and networking framework.
The present teaching relates to identify events of interests. Given each of video clips, each capturing an event of interest, spatial attention regions are identified therefrom, each of which includes objects that meet a first condition. A temporal attention region is determined in each video clip according to a second condition. An action that causes an event of interest in the temporal attention region is labeled. The video clips, the respective spatial/temporal attention regions, and the action labels are then used to generate training data for machine learning of models for automatically determining, from an input video clip, a temporal attention zone for an event of interest and an action that causes the event of interest.
G06V 20/40 - ScènesÉléments spécifiques à la scène dans le contenu vidéo
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”
Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework for compiling and leveraging reliable sequence taggings for input queries related to executed searches. The disclosed framework can compile a trained computer model to fulfill partially labeled queries tagged by AI models as fully labeled queries. The disclosed framework can further leverage other AI models (e.g., deep neural networks, knowledge graphs, and the like), so that cross-checks can be performed between different models to guarantee high quality of labeled tokens. Thus, the framework can automatically generate and implement reliable training data to train a sequence tagging model for search query understanding. Thus, the search engine operating on such tagging model can provide improved results.
The present teaching relates to merging data sketches from different data sketch sources. To satisfy performance metrics specified with respect to quality of a merged sketch, sketch merging parameters are generated, which include a first set of parameters for creating obfuscated keys of the data sketches and a second set of parameters for identifying matching obfuscated keys. Keys of the data sketches are obfuscated using the first set of sketch merging parameters. The data sketches are merged by identifying matching obfuscated keys in accordance with the second set of sketch merging parameters to generate a merged sketch.
In accordance with the present disclosure, one or more computing devices and/or methods are provided. In an example, a query may be received from a client device. In response to the query, a plurality of search results corresponding to a plurality of internet resources associated with the query may be generated. A plurality of content items may be generated based upon the plurality of search results. The plurality of content items may be generated using a plurality of content extraction tools. A language model may be used to generate a plurality of summaries of the plurality of content items. Summary scores of the plurality of summaries may be determined. A first summary may be selected from the plurality of summaries based upon the summary scores. In response to selecting the first summary, the first summary may be provided for display on the client device.
In accordance with the present disclosure, one or more computing devices and/or methods are provided. In an example, a first group of content items may be identified. A content interface may be provided for display on a client device. The content interface may comprise a first selectable input for accessing a first content item of the first group of content items, a second selectable input for accessing a second content item of the first group of content items, and/or a question and answer interface. A query may be received via the question and answer interface. Using a generative AI tool, a response to the query may be generated based upon the first group of content items. A representation of the response to the query may be displayed via the question and answer interface.
The present teaching relates to detecting households and content recommendation thereto. Based on information related to user online activities, component graphs are generated to represent corresponding candidate households. The component graphs are classified via a classification model to identify those component graphs representing households. Such component graphs representing households are adapted over time according to the dynamics of the user online activities.
H04L 12/28 - Réseaux de données à commutation caractérisés par la configuration des liaisons, p. ex. réseaux locaux [LAN Local Area Networks] ou réseaux étendus [WAN Wide Area Networks]
26.
SYSTEM AND METHOD FOR DOMAIN GENERALIZATION AND APPLICATIONS THEREOF
The present teaching relates to attribute extraction from textual content. A domain-invariant attribute extraction model is trained for extracting predetermined attributes from textual content from multiple domains based on training data having a plurality of training samples, each with textual content, some of the predetermined attributes in the textual content, and a label indicating one of the multiple domains that produces the textual content. The domain-invariant attribute extraction model learns via training the semantics of the predetermined attributes across the multiple domains so that when a new textual content from any of the multiple domains, some predetermined attributes are extracted according to semantics thereof via the domain-invariant attribute extraction model.
The present teaching relates to content recommendation. Content is selected from multiple pieces of content for recommending to a user based on a user embedding and contextual information. Performance of the user with respect to the recommended content is obtained. The user embedding for the user is adapted based on the performance information via a memory-dependency aware model previously trained to learn past interests of the user and intensities of such past interests. An updated user embedding is generated to represent current interests of the user via the adapted user embedding produced by the memory-dependency aware model according to the known intensities of the past interests of the user as well as user's interest exhibited in the recommended content.
In some aspects, the techniques described herein relate to a method including: obtaining, by a computing device, a set of messages, each message including message metadata and message structure, at least one message of the set of messages comprising a digital asset; clustering, by the computing device, the set of messages based on the message metadata and the message structure; classifying, by the computing device, the clusters into categories; determining, by the computing device, a digital asset structure from at least one message cluster; and generating, by the computing device, at least one mapping rule based on the digital asset structure.
In an example, in connection with a search clustering system, a grouping component retrieves a timestamp set of news queries and determines a time-stable set of news query groups by performing the first stage of a two-stage clustering technique. A clustering component determines a time-stable set of news query groups clusters by performing the second stage of the two-stage clustering technique. The performance of the two-stage clustering technique is aided by a least recently used caching component. The time-stable set of news query groups clusters may be served to a web page in order to generate a trending topic list for display.
G06F 16/2457 - Traitement des requêtes avec adaptation aux besoins de l’utilisateur
G06F 16/955 - Recherche dans le Web utilisant des identifiants d’information, p. ex. des localisateurs uniformisés de ressources [uniform resource locators - URL]
30.
ELECTRONIC INFORMATION EXTRACTION USING A MACHINE-LEARNED MODEL ARCHITECTURE METHOD AND APPARATUS
Techniques for automatic intelligent information extraction from an electronic document are disclosed. In one embodiment, a computerized method is disclosed comprising training a label prediction model to generate a set of label predictions, obtaining an electronic document, analyzing the electronic document and determining a set of features for each of a set of information items identified in the electronic document, obtaining model output from the label prediction model for each information item, the model output comprising, for a respective information item, a set of probabilities corresponding to a set of information classes, and generating an information extraction comprising a set of labels corresponding to the set of information items.
G06F 18/21 - Conception ou mise en place de systèmes ou de techniquesExtraction de caractéristiques dans l'espace des caractéristiquesSéparation aveugle de sources
The present teaching relates to dynamically generating a card. In one example, a request is received for generating a card to be provided to a user. Dynamic information related to the request is obtained. One or more modules are selected to be put into the card based on the dynamic information. The card is generated based on the selected one or more modules.
One or more computing devices, systems, and/or methods are provided. In an example, a review initiation request may be received from a first email account. The review initiation request may indicate proposed email content and/or a reviewer of the proposed email content. An email may be generated based upon the review initiation request. The email may include the proposed email content and/or an email review interface including a feedback entry field and/or an approval selectable input. The email may be transmitted to a reviewer email account of the reviewer. A review response may be received, via the email review interface, from the reviewer email account. The review response may indicate (i) feedback, indicating one or more suggestions associated with the proposed email content, submitted via the feedback entry field, and/or (ii) an approval indicator, indicating approval of the proposed email content, submitted via the approval selectable input.
Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework for demand-side platforms (DSPs) to effectively plan, launch, optimize and monitor the performance of content campaigns over a network on network resources. The disclosed framework operates to perform strategic and data-driven processes for DSP initiatives that can define campaign parameters, and in real-time, monitor the effectiveness of campaigns such that their modifications and/or alterations can be dynamically performed so as to adapt to the changing landscapes of how the campaign is being disseminated over a network and received by users. The framework can implement AI/ML and/or LLM models and functionality to provide DSPs with comprehensive tools for managing, curating and analyzing content related to content campaigns for optimal and accurate performance and impact.
Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework for deterministically identifying and extracting content from network resources, and generating focused content based therefrom for delivery to electronic users. The framework enables real-time customization of extraction tasks, which can cause tailored, accurate results that are contextually relevant and tied into the purpose of the extraction task. This data can then be compiled and/or leveraged to generate content campaigns that can target specific sets of users, geographies, time periods, trends and the like. The framework can leverage a large language model (LLM) to seamlessly extract relevant information from network resources, which enables the generation and execution of extraction requests that can be dynamically executed and updated, which can enable the framework to “drill-down” on contextual and/or topical aspects of categories of data.
The present teaching relates to learning a model. Supervised training data with samples having feature values and a label is received. Unlabeled data be classified is received having samples with values of the same features. Un-stationary features in the supervised training data are detected based on respective feature values from the supervised training data and the unlabeled data. If un-stationary feature exists, adjusted training data set is created based on the supervised training data and the un-stationary features and used to train a stationary classification model. Otherwise, the supervised training data is used to train the stationary classification model.
Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework for performing contextual mapping between hosted and provided content, from which curated digital content and/or associated content campaigns can be implemented. The disclosed framework can be implemented by supply-side platforms (SSPs), demand-side platforms (DSPs) and/or content delivery platforms (CDPs), which can leverage the contextual mapping and content curation tools provided by the disclosed framework to effectively plan, launch, optimize and monitor the performance of content campaigns implemented over a network on network resources. The disclosed strategic and data-driven processes rendered capably by the disclosed framework for SSP and/or DSP initiatives can define campaign parameters, and in real-time, monitor the effectiveness of campaigns such that their modifications and/or alterations can be dynamically performed so as to adapt to the changing landscapes of how the campaign is being disseminated over a network and received by users.
In some implementations, the techniques described herein relate to a method including: (i) obtaining, by a processor, at least one statistic related to a recent history of a fantasy athletic team managed by a user within a fantasy athletic league, (ii) creating, by the processor, a prompt for a large language model (LLM), the prompt comprising, the at least one statistic and a set of constraints configured to produce as output from the LLM a fantasy team recap that conforms to at least one predetermined guideline, (iii) providing, by the processor, the prompt to the LLM as input, and (iv) causing display, by the processor, of the fantasy team recap output by the LLM in response to the prompt.
Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework for demand-side platforms (DSPs) to effectively, plan, launch, optimize and monitor the performance of content campaigns. The disclosed framework operates to perform strategic and data-driven processes for DSP initiatives that can define campaign parameters, and in real-time, monitor the effectiveness of campaigns such that their modifications and/or alterations can be dynamically performed so as to adapt to the changing landscapes of how the campaign is being disseminated over a network and received by users. Accordingly, the framework's mechanisms are implemented for new and/or existing campaigns, across various platforms and/or websites, in order to optimize visibility while increasing user experience, which benefits both DSPs as well as the targeted audience. The framework can implement AI/ML and/or LLM models and functionality to provide a comprehensive approach to managing, curating and analyzing content campaigns for optimal performance and impact.
One or more computing devices, systems, and/or methods for providing customized podcasts are provided. In an example, a request to provide a podcast to a client device is received. The request is indicative of a podcast customizing feature. Based upon the request, a set of content items is determined. A summary of the set of content items is generated based upon the podcast customizing feature. The podcast is generated to comprise an auditory representation of the summary. The podcast is provided to the client device.
G10L 13/08 - Analyse de texte ou génération de paramètres pour la synthèse de la parole à partir de texte, p. ex. conversion graphème-phonème, génération de prosodie ou détermination de l'intonation ou de l'accent tonique
In some implementations, the techniques described herein relate to a method including: (i) receiving, by a processor, text content from an entity that stores the text content as a data object associated with the entity, (ii) generating, by the processor, a prompt for a large language model that comprises the text content and directions for modifying the text content, (iii) providing, by the processor, the prompt to the large language model, (iv) executing, by the processor, the large language model, the execution causing creation of modified text content in accordance with the directions for modifying the text content from the prompt; (v) receiving, by the processor from the large language model, the modified text content, and (vi) creating, by the processor, a new data object that stores the modified text content in association with the entity.
The disclosed systems and methods provide a framework for a proactive prediction of the toxic propensity of an article. Prior to the publication and/or reception of comments to online content, the disclosed framework determines the toxic propensity of the content's context and/or specific words, sentences, sentiments, tone or other messages receivable from consumption of the content. Thus, disclosed framework performs proactive forecasting of the content's toxicity propensity”, which quantifies how likely the content is prone to incur or attract toxic comments. The framework can function and/or be configured to operate in a manner that can perform specifically adherent moderation actions that correspond to the content and control how the content can be interacted with, based on the toxic propensity determination, prior to the content's publication in an effort to thwart, prevent or stop toxic environments surrounding or stemming from the content from coming into existence.
Techniques for electronic document content bookmarking are disclosed. In one embodiment, a method is disclosed comprising receiving user input indicating selection of a portion of the electronic document, receiving a request to bookmark the selected portion of the electronic document, generating a bookmark card for the selected portion of the electronic document, the bookmark card comprising information identifying the electronic document, the selected portion of the electronic document as bookmarked content and the at least one user-defined information item, receiving, via the computing device, a bookmark view request via the GUI, and causing display of the bookmark view via the GUI in response to the bookmark view request, the bookmark view comprising an entry corresponding to the generated bookmark card and providing the bookmarked content from the generated bookmark card, the bookmark view providing a number of actions selectable by the user in connection with the entry from the bookmark view.
G06F 16/383 - 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
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
H04L 51/42 - Aspects liés aux boîtes aux lettres, p. ex. synchronisation des boîtes aux lettres
43.
SYSTEMS AND METHODS FOR AUTOMATICALLY ADDING TEXT CONTENT TO GENERATED IMAGES
In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, a generative machine learning model trained on image data, (ii) generating, by the generative machine learning model executed by the processor, an image based on at least one parameter, (iii) editing, by an image-editing algorithm executed by the processor, the image to comprise a specified string of text in a selected area of the image, and (iv) causing display, by the processor, of the edited image.
In some aspects, the techniques described herein relate to a method including: receiving a set of messages; filtering the set of messages to identify a set of newsletters in response to a selection of a newsletter control within a messaging application; rendering a newsletter view within the messaging application, the newsletter view displaying a plurality of tiles corresponding to the set of newsletters; receiving a section of a given tile in the plurality of tiles from a user; and rendering a newsletter reader view, the newsletter reader view including a subject and body of a selected newsletter corresponding to the given tile.
The present teaching relates to trending term identification. Information in different categories from different sources associated with each of terms being evaluated for trendiness is obtained within a recent period and linked to generate a data group for each term. Features are extracted for each term based on information in the corresponding data group and are used to compute a trendiness score in accordance with a scoring model. Trending terms are selected from the terms based on their trendiness scores.
One or more computing devices, systems, and/or methods for evaluating email activity and/or controlling, based upon the email activity, transmission of instructions associated with quality are provided. A first email, transmitted by an email account associated with an entity to a plurality of email accounts, may be identified. First activity associated with the first email may be detected. A first set of activity information associated with the first activity may be stored in an entity profile associated with the entity. The entity profile may comprise a plurality of sets of activity information associated with a plurality of emails transmitted by one or more email accounts associated with the entity. A quality score corresponding to the first entity may be generated based upon the entity profile. A notification may be generated based upon the quality score. The notification may be transmitted to the first client device.
The present teaching relates to communication related to predictions. A communication chain is created with multiple chain units, each operating independently to provide prediction services related to a prompt with embedded information therein associated with predictions for the prompt to enable prediction services. A request is received for a requested operation related to a query prompt on one of prediction solicitation, prediction entry, verification entry, and prediction access. If a chain unit for the query prompt, the request is directed to the chain unit to perform the requested operation. If not, a new chain unit is created for the query prompt and the request is forwarded to the new chain unit to carry out the requested operation.
Various embodiments of this disclosure relate generally to generating a customized output based on account data of a user. The method comprises receiving, by one or more processors, user data from one or more databases, wherein the user data includes user browser history and user account data, creating a user record based on the user account data, wherein the user record includes one or more stocks, determining a stock subset of the one or more stocks, retrieving one or more relevant segments from a vector database, wherein the one or more relevant segments correspond to one or more relevant events that are relevant to the stock subset, generating a personalized output script based on the one or more relevant segments, creating an output based on the personalized output script, and displaying the output on one or more user interfaces of a user device.
In some implementations, the techniques described herein relate to a method including (i) receiving, by a processor, user input describing at least one parameter for a query image, (ii) generating, via a generative machine learning model executed by the processor, the query image based at least in part on the user input describing the at least one parameter for the query image, (iii) providing, by the processor, the query image as input to an image-based search algorithm, and (iv) returning a result received by the processor from the image-based search algorithm.
Various embodiments of this disclosure relate generally to utilizing a machine-learning model to determine an electronic communication priority. The method comprises receiving an electronic communication dataset reflecting an electronic communication inbox of a user from one or more databases, wherein the electronic communication dataset includes a plurality of electronic communications, utilizing a trained machine-learning model to determine a priority for at least one of the plurality of electronic communications based on the electronic communication dataset, wherein the priority corresponds to an importance level of the at least one of the plurality of electronic communications, filtering the electronic communication dataset according to the priority, and displaying the filtered electronic communication dataset via an electronic communication interface of a user device, wherein the electronic communication interface corresponds to an electronic communication application.
The present teaching relates to content categorization. Supervised training data and unlabeled data clusters are used to generate augmented training data. Each unlabeled data cluster includes data samples with varying features. Weakly labeled training data is created based on supervised training data and the unlabeled data clusters with data samples therein with cluster labels via consistent self-training so that a labeled data sample in the supervised training data and a data sample in the weakly labeled training data with the same label have varying characteristics. Augmented training data is created from the supervised and the weakly labeled training data and is used to train a robust content categorization model via machine learning.
The present teaching relates to content categorization. Supervised training data and unlabeled data clusters are used to generate augmented training data. Each unlabeled data cluster includes data samples with varying features. Weakly labeled training data is created with new data samples generated via generative augmentation based on supervised training data and the unlabeled data clusters. Each new data sample is assigned a label from a corresponding data sample from the supervised training data with generated varying characteristics. Augmented training data is created from the supervised and the weakly labeled training data and is used to train a robust content categorization model via machine learning.
In some implementations, the techniques described herein relate to a method including: (i) receiving, by a processor that executes a digital messaging application, an image that comprises a depiction of a user, (ii) selecting, by the processor, an event theme, (iii) creating, by a generative machine learning model, a generated image that comprises the depiction of the user and the event theme, and (iv) transmitting, by the processor, the generated image to one or more digital contacts of the user via the digital messaging application.
G06F 3/048 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI]
G06F 3/0482 - Interaction avec des listes d’éléments sélectionnables, p. ex. des menus
G06T 11/60 - Édition de figures et de texteCombinaison de figures ou de texte
H04L 51/07 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel caractérisée par l'inclusion de contenus spécifiques
54.
SYSTEMS AND METHODS FOR GENERATING IMAGES OF LOCATIONS AFFECTED BY WEATHER CONDITIONS
In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, a geographic location and a current time, (ii) retrieving, by the processor from a database, a weather condition of the geographic location at the current time, (iii) retrieving, by the processor from an image database, an image based on the geographic location, (iv) creating, via a generative machine learning model executed by the processor that takes the image of the geographic location and the weather condition as input, a digital image depicting the geographic location being visibly affected by the weather condition, and (v) causing display, by the processor, of the digital image in an application.
G06F 16/587 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des informations géographiques ou spatiales, p. ex. la localisation
G06T 13/80 - Animation bidimensionnelle [2D], p. ex. utilisant des motifs graphiques programmables
55.
RATIO PREDICTION USING MACHINE LEARNING MODELS EMPLOYING STRICT CONVEX LOSS FUNCTIONS AND PROXIMAL POINT OPTIMIZATION
In some implementations, the techniques described herein relate to a method including: receiving a training data set, the training data set including data representing consumer interactions and actions taken by consumers after the consumer interactions; executing a training run using a predictive model, the predictive model including a plurality of trainable parameters; computing a loss of the training run using a loss function, the loss function including a strict convex function; optimizing the plurality of trainable parameters based on an output of the loss function; storing the trainable parameters as an inference model; and predicting a future ratio using the inference model.
Techniques for automatically generating a natural language (NL) translation of computer code are disclosed. In one embodiment, a computer-implemented method is disclosed comprising receiving, from a user, a code translation request in connection with code generated by a code generation system based on natural language (NL) input, analyzing the computer-generated code and generating a natural language (NL) translation of the computer-generated code based on the analysis, generating a graphical user interface (GUI) comprising the NL input, the NL translation of the computer-generated code and GUI control elements for receiving input from the user in connection with at least one of the NL input and the NL translation; causing the GUI to be displayed at a client device of the user, and receiving input from the user via at least one GUI control element and causing performance of at least one operation in response to the input.
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
57.
SYSTEMS AND METHODS FOR INSTRUCTIONS BASED MESSAGING INBOX USING A LANGUAGE MODEL
Various embodiments of this disclosure relate generally to utilizing a machine-learning model to process natural language email instructions. The method comprises receiving, by one or more processors, at least one instruction from a user via an email interface displayed on a user device, the email interface corresponding to an email application, processing, by a trained machine-learning model, the at least one instruction to determine at least one response, wherein processing the at least one instruction includes applying at least one persona of the user to the at least one instruction, performing, by the one or more processors, at least one action or at least one query corresponding to the at least one response, and displaying, by the one or more processors, a confirmation on the email interface of the user device that the at least one response was completed.
H04L 51/07 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel caractérisée par l'inclusion de contenus spécifiques
G06F 3/0481 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] fondées sur des propriétés spécifiques de l’objet d’interaction affiché ou sur un environnement basé sur les métaphores, p. ex. interaction avec des éléments du bureau telles les fenêtres ou les icônes, ou avec l’aide d’un curseur changeant de comportement ou d’aspect
G06F 3/0484 - 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 40/47 - Traduction assistée par ordinateur, p. ex. utilisant des mémoires de traduction
58.
SYSTEM AND METHOD FOR DYNAMIC CREATIVE OPTIMIZATION VIA GENERATIVE AI
The present teaching relates to displaying ads. A generative artificial intelligence (AI) model for creating advertisement assets is obtained, via machine learning, based on training data generated based on online feedback information on previously displayed advertisements. Base advertisement information associated with an advertisement of a product specifying some attributes characterizing the product is received. Using the generative AI model, multiple advertisement assets are created with respect to some attribute of the advertisement. Each advertisement asset is a representation of an attribute. These advertisement assets are used to form different asset combinations, each of which can be used to display the advertisement.
The present teaching relates to online advertising. A diagonal vector d is determined based on supply and demand data identified from ad auction related data. A predicted performance (P-P) metric is computed based on the diagonal vector d via low rank field weighted factorization machines (FwFM) for each of candidate ads included in the ad auction related data. The candidate ads are ranked based on their corresponding P-P metrics. A winning ad is selected from the ranked candidate ads according to a predetermined selection criterion.
The present teaching relates to online advertising. Bids directed to a display ad opportunity are received, where the display ad opportunity involves a user and an associated context and each bid includes a candidate advertisement. Auxiliary features are obtained for each bid based on a code generated by an autoencoder based on the bid and a predicted performance metric is determined for the candidate advertisement associated with the bid based on the auxiliary features associated with the bid. A winning advertisement is selected from candidate advertisements of the bids according to a ranking determined based on the respective predicted performance metrics of the candidate advertisements.
Systems and methods are disclosed for determining one or more chance predictions for a predictive user. One method comprises receiving a bullish threshold, a bearish threshold, and one or more time periods from at least one user, receiving a plurality of predictions from one or more prediction databases, receiving one or more basis sets, based on the plurality of predictions, determining, at least one p-score for each of the one or more time periods, calculating a null distribution of successful predictions based on the one or more basis sets and the one or more time periods, determining a prediction user p-value based on the null distribution and the at least one p-score, selecting a classification for the at least one prediction user based on the prediction user p-value, and displaying at least one graphical widget corresponding to the classification on one or more interfaces of a user device.
G06Q 40/04 - TransactionsOpérations boursières, p. ex. actions, marchandises, produits dérivés ou change de devises
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
62.
COALITION NETWORK IDENTIFICATION USING CHARGES ASSIGNED TO PARTICLES
One or more computing devices, systems, and/or methods are provided. Event information associated with a plurality of events may be identified. The plurality of events may be associated with first entities corresponding to a first entity type and second entities associated with a second entity type. A first network profile associated with the first entities and the second entities may be generated based upon the event information. An arrangement of particles corresponding to the first entities and the second entities may be generated. Charges associated with the particles may be determined based upon the first network profile. The particles may be rearranged to a second arrangement of particles based upon the charges. One or more clusters of particles in the second arrangement of particles may be identified. One or more coalition networks associated with fraudulent activity may be identified based upon the one or more clusters of particles.
One or more computing devices, systems, and/or methods for facilitating communications with service providers are provided. In an example, a first request for a service may be received from a first email account. The first request may be updated using a language model to generate an updated request for the service, wherein the updated request includes one or more supplemental parameters. A set of service providers may be determined for the service. A first message may be generated based upon the updated request. The first message may be provided to the set of service providers associated with the service. A second message may be received from a first service provider of the set of service providers. Content may be provided to the first user based upon the second message.
Techniques for intelligently managing service requests using a service request outcome prediction and a dynamically determined probability threshold are disclosed. In one embodiment, a computer-implemented method is disclosed comprising receiving a request for service directed to an online service provider, determining a feature vector for the received service request, the feature vector determination comprising identifying information associated with the request and a response of the service provider, the feature vector being based on the identified information, analyzing the received request using a trained outcome prediction model and the feature vector, and determining a win probability based on the analysis, the win probability indicating a likelihood of a predefined outcome in connection with the service request and the service provider's response, making a request throttling determination based on the win probability and a threshold probability, and managing the service request based on the request throttling determination.
H04L 67/63 - Ordonnancement ou organisation du service des demandes d'application, p. ex. demandes de transmission de données d'application en utilisant l'analyse et l'optimisation des ressources réseau requises en acheminant une demande de service en fonction du contenu ou du contexte de la demande
65.
SYSTEMS AND METHODS FOR LLM-ASSISTED EMAIL AUTOMATION
In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, an electronic message addressed to an inbox of a user that comprises a confirmation of a transaction involving a platform, (ii) searching, by the processor, for an additional electronic message addressed to the inbox indicating an alteration applicable to the transaction, (iii) causing display, by the processor, of a prompt informing the user of the alteration applicable to the transaction, (iv) composing, by a large language model (LLM) executed by the processor, a potential electronic message to an operator of the platform requesting the alteration be retroactively applied to the transaction, and (v) in response to receiving user input regarding the potential electronic message, sending, by the processor, a subsequent electronic message to the operator of the platform requesting the alteration be retroactively applied to the transaction.
A method for presenting personalized content to a user includes receiving user data corresponding to a user having a user profile, the user data including at least one or more messages in a user mailbox and a user web browser history within a network, extracting one or more data tags from the received user data, associated at least one data tag with a message, finding information in the network that corresponds to the associated data tag, generating a notification for the user, the notification including the found information in the network, and outputting the generated notification to a user interface of a device of the user.
H04L 51/224 - Surveillance ou traitement des messages en fournissant une notification sur les messages entrants, p. ex. des poussées de notifications des messages reçus
G06F 16/909 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des informations géographiques ou spatiales, p. ex. la localisation
H04L 51/222 - Surveillance ou traitement des messages en utilisant des informations de localisation géographique, p. ex. des messages transmis ou reçus à proximité d'un certain lieu ou d'une certaine zone
H04L 51/42 - Aspects liés aux boîtes aux lettres, p. ex. synchronisation des boîtes aux lettres
Systems and methods are disclosed for using heuristic refinement and a deep learning model to identify at least one high-quality user search query. One method comprises filtering one or more queries, determining at least one candidate query based on the filtered queries, the determining including: determining heuristic candidate queries by applying heuristic processes to the filtered queries, generating model candidate queries based on one or more deep learning model processes, and selecting the candidate query from the heuristic candidate queries or the model candidate queries based on a corresponding aggregated token frequency, and displaying the candidate query.
The present teaching relates to method, system, medium, and implementations for online advertising. Bids are solicited from multiple bidders for an online ad display opportunity. A current value of a budget factor is retrieved and used for computing, for each advertisement corresponding to a respective bid, a wrapper function value based on the current value of the budget factor and a flow type of the advertisement. Based on the wrapper function value for each advertisement, a ranking score is determined and used to rank the advertisements associated with the bids. A winning bid is accordingly selected based on the ranking scores.
The present teaching relates to method, system, medium, and implementations for machine learning. Machine learning is performed based on training data via a dual loop learning process that includes a first loop for data decoding learning and a second loop for label decoding learning. In the first loop, first parameters associated with decoding are updated to generate updated first parameters based on a first label, estimated via the decoding using the first parameters, and a second label, predicted via the label decoding using second parameters. In the second loop, the second parameters associated with the label decoding are updated to generate updated second parameters based on a third label, obtained via the decoding using the updated first parameters, and a ground truth label.
G06F 18/214 - Génération de motifs d'entraînementProcédés de Bootstrapping, p. ex. ”bagging” ou ”boosting”
G06F 9/30 - Dispositions pour exécuter des instructions machines, p. ex. décodage d'instructions
G06F 18/213 - Extraction de caractéristiques, p. ex. en transformant l'espace des caractéristiquesSynthétisationsMappages, p. ex. procédés de sous-espace
The present teaching relates to method, system, medium, and implementations for setting a dynamic bid floor. To conduct a bidding process for an ad opportunity to display an ad at a current placement venue, a dynamic bid floor is determined in a non-parametric manner to maximize revenue based on bid-floor (BF)/revenue dependency information. The dynamic bid floor is used to control the bidding process. A winning bid is selected from multiple bids received during the bidding and a corresponding winning advertisement is displayed at the placement venue.
In some implementations, the techniques described herein relate to a method including: parsing, by a processor, a generated text to identify statements included within a generated text; querying, by the processor, a remote data source to identify sources for each statement in the statements; determining, by the processor, trustworthiness values for each statement, a trustworthiness value for a given statement determined by computing trustworthiness labels for each source corresponding to a given statement: generating, by the processor, a label for the generated text based on an aggregated trustworthiness of each of the statements; and displaying, by the processor, the generated text and the label within a user interface displayed to a user.
G06F 16/38 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement
A method of adaptive online user profiles includes displaying a website for a particular topic of interest based on a user request, receiving a request from the user to display user profile data, obtaining the user profile data, the user profile data including topic-area-specific user-specific profile information for multiple topic areas, comparing a topic area of the displayed website to a topic area for each topic-area-specific user-specific profile information, and displaying the user profile data such that the topic-area-specific user-specific profile information most closely matching the topic area of the displayed website is displayed most prominently.
One or more computing devices, systems, and/or methods for performing entity actions based upon inputs received via email interfaces are provided. For example, an email received by an email account may be identified. The email may be associated with an entity action corresponding to a first entity. A selectable input corresponding to performing the entity action may be displayed via an email interface associated with the email account. A request to perform the entity action may be received via a selection of the selectable input. Responsive to receiving the request, an action interface corresponding to performing the entity action may be displayed within the email interface. One or more inputs associated with the entity action may be received via the action interface. Responsive to determining that the entity action is completed, a confirmation message, indicative of the entity action being completed, may be displayed using the email interface.
The present teaching relates to method, system, medium, and implementations for personalized content service. Information related to a user is first obtained with a user profile indicative of multiple interests of the user. User embeddings are computed with respect to some interests of the user based on interest embeddings of such interests to capture semantics of such interests as well as additional interests temporally related to the interests. Personalized content is identified based on the user embeddings and is provided to the user.
Disclosed are embodiments for providing a domain-specific visualization of message content. Unclassified messages are received for a sender and a real-time classifier is used to assign categories to the messages. User interactions with email can then be used to generate a ranked list of domain-specific senders. This ranked list of senders and classified emails can then be used to provide a domain-specific view to a user. Further features (e.g., aggregated content pages by sender, dynamic call-to-action buttons, message previews etc.) can then be built on top of the ranked senders and messages.
One or more computing devices, systems, and/or methods for generating a user-specific interface are provided. In an example, a user-specific machine learning model, for a user of an email application, may be trained based upon one or more interactions of the user with a device upon which the email application is installed. A determination may be made that an email message has been received by an email account of the user. A user-specific message interface may be generated based upon (i) the trained user-specific machine learning model and (ii) content of the email message. A notification of the email message may be provided for display on the device of the user. In response to the user selecting the notification of the email message, the user-specific interface may be provided for display on the device of the user.
H04L 51/42 - Aspects liés aux boîtes aux lettres, p. ex. synchronisation des boîtes aux lettres
G06F 3/048 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI]
G06F 3/0481 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] fondées sur des propriétés spécifiques de l’objet d’interaction affiché ou sur un environnement basé sur les métaphores, p. ex. interaction avec des éléments du bureau telles les fenêtres ou les icônes, ou avec l’aide d’un curseur changeant de comportement ou d’aspect
G06F 3/0483 - Interaction avec des environnements structurés en pages, p. ex. métaphore livresque
H04L 51/07 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel caractérisée par l'inclusion de contenus spécifiques
H04M 1/72436 - Interfaces utilisateur spécialement adaptées aux téléphones sans fil ou mobiles avec des moyens de soutien local des applications accroissant la fonctionnalité avec des moyens interactifs de gestion interne des messages pour la messagerie textuelle, p. ex. services de messagerie courte [SMS] ou courriels
H04M 1/72484 - Interfaces utilisateur spécialement adaptées aux téléphones sans fil ou mobiles où les fonctions sont activées par la réception d’une démarche de communication
77.
METHOD AND SYSTEM FOR DETERMINING ALPHA AND BETA VALUES OF A CANDIDATE RELATIVE TO A CLASS
Disclosed are systems and methods for determining a beta value of at least one candidate relative to a class. The method comprises receiving historical data for the at least one candidate and historical data for the class; determining a first set of regression coefficients for the historical data for the at least one candidate, and a second set of regression coefficients for the historical data for the class; and calculating the beta value for the at least one candidate relative to the class based on the first set of regression coefficients and the second sets of regression coefficients. The method may further include generating an indication that the beta value for the candidate is one of positive, negative, or zero; and transmitting to at least one display window of a graphical user interface (GUI) a graphical symbol corresponding to the indication of the beta value for the candidate.
The present teaching relates to method, system, medium, and implementations for product recommendation. For each media article, it is determined whether the media article corresponds to commerce content. If so, the media article may be combined with information about a product promoted in the media article to generate combined content. An integrated content to be sent to the user is generated to include combined content for each media article that is commerce content and each media article that is not commerce content. Such integrated content is then sent to the user.
Disclosed are systems and methods utilizing neural contextual bandit for improving interactions with and between computers in content generating, searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to make item recommendations using latent relations and latent representations, which can improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods use neural network modeling in automatic selection of a number of items for recommendation to a user and using feedback in connection with the recommendation for further training of the model(s).
G06Q 30/0282 - Notation ou évaluation d’opérateurs commerciaux ou de produits
G06Q 50/00 - Technologies de l’information et de la communication [TIC] spécialement adaptées à la mise en œuvre des procédés d’affaires d’un secteur particulier d’activité économique, p. ex. aux services d’utilité publique ou au tourisme
80.
SYSTEM AND METHOD FOR IDENTIFYING APPROXIMATE K-NEAREST NEIGHBORS IN WEB SCALE CLUSTERING
The present teaching relates to method, system, medium, and implementations for identifying k nearest neighbors. One or more KNN lists corresponding to one or more source data points are received. Each KNN list includes K neighbors of a source data point and each of the K neighbors is a data point represented by an index. Neighbor pairs and reverse neighbor pairs are generated based on the one or more KNN lists. The neighbor pairs and reverse neighbor pairs having the same source data point are grouped to generate a grouped pairs of neighbors for the source data point. A local join operation is performed based on grouped pairs of neighbors for each source data point to generate a combined neighborhood for the source data point, which is then sent to a KNN server, where combined neighborhoods generated by multiple local join executors are integrated to update a plurality of global KNN lists.
The present teaching relates to method, system, medium, and implementations for content serving. A user's profile characterizing the user's long-tail interest with respect to some long-tail topics may be obtained. Each long-tail topic in the user's profile is associated with a long-tail topic score representing a degree of the user's interest in the long-tail topic. Long-tail content in some long-tail topics may be identified for the user and sent to the user. When information about online activities of the user directed to the long-tail content is received, corresponding long-tail topic scores in the user profile associated with the long-tail topics are updated based on the user's online activities.
In an example, a first set of text may be received from a client device. A set of content items may be selected from among content items based upon the first set of text and a plurality of sets of content item text associated with the content items. A set of terms may be determined based upon the first set of text and the set of content items. A similarity profile associated with the set of terms may be generated. The similarity profile is indicative of similarity scores associated with similarities between terms of the set of terms. Relevance scores associated with the set of terms may be determined based upon the similarity profile. One or more search terms may be selected from among the set of terms based upon the relevance scores. A search may be performed based upon the one or more search terms.
Disclosed are systems and methods for improving interactions with and between computers in content communicating, displaying, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods determine and display message content within a portion of a message inbox in a manner that is specific to the type message content. According to some embodiments, when a message is received in a message inbox of a user, the message content can be opened for display within a dedicated portion of the inbox, thereby enabling improved message content retrieval, access and navigation within a message platform or message application.
The present teaching relates to a method, system, and programming for searching content. A sketch of an object is obtained from a user. The sketch is processed by a neural network to generate an image corresponding to the sketch of the object. One or more features are extracted from the image, and one or more images previously stored are identified that have features similar to the one or more features. The one or more images are provided to the user.
Disclosed are systems and methods for generating recommendations to users based on historical travel information and electronic communication data. The disclosed systems and methods provide a novel framework for automating the transmission of electronic travel-related recommendations to users by consistently monitoring electronic messages received at an electronic communication mailbox corresponding to a user. The disclosed framework operates by leveraging historical user data, data parsed from electronic communication mailbox corresponding to a user, or various vendor information, and using the aforementioned data as inputs for travel-related recommendation models, in order to generate and transmit the optimal travel-related recommendations to a user.
Method, system, and programs for measuring user engagement with content items. In one example, a query is received. A set of content items related to the query is obtained. A presentation of at least one content item of the set of content items is provided on a user interface. A user activity related to the at least one content item is determined. An amount of time between a time at which the presentation of the at least one content item is provided on the user interface and a time at which the user activity occurred is determined. A score associated with the content item is determined based on the amount of time. Information related to user engagement with the set of content items is generated based on the score.
G06F 11/34 - Enregistrement ou évaluation statistique de l'activité du calculateur, p. ex. des interruptions ou des opérations d'entrée–sortie
G06F 3/0482 - Interaction avec des listes d’éléments sélectionnables, p. ex. des menus
G06F 16/435 - Filtrage basé sur des données supplémentaires, p. ex. sur des profils d'utilisateurs ou de groupes
G06F 16/907 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement
G06F 16/9535 - Adaptation de la recherche basée sur les profils des utilisateurs et la personnalisation
G06F 16/9538 - Présentation des résultats des requêtes
87.
COMPUTERIZED SYSTEM AND METHOD FOR FINE-GRAINED EVENT DETECTION AND CONTENT HOSTING THEREFROM
The disclosed systems and methods provide a novel framework that provides mechanisms for performing cost-effective, accurate and scalable detection and recognition of fine-grained events. The framework functions by training high precision and high recall object/optical character recognition (OCR) models and aligning video frames to text commentaries of the videos (e.g., licensed play-by-play). The disclosed framework operates as a single algorithm that performs multimodal alignments between events/actions within videos and their prescribed text. Thus, the disclosed framework is able to scale to fine-grained action categories across different venues by delving into the key frames and key aspects of a video to identify particular actions performed by particular actors, thereby providing the novelty of fine-granted action detection and recognition.
09 - Appareils et instruments scientifiques et électriques
35 - Publicité; Affaires commerciales
41 - Éducation, divertissements, activités sportives et culturelles
42 - Services scientifiques, technologiques et industriels, recherche et conception
Produits et services
(1) Downloadable podcasts in the fields of technology, technology innovation, consumer products, electronics, the Internet, computers, social media, entrepreneurship, startup companies, and business; downloadable software in the nature of a mobile application for delivering, accessing and viewing information, news, analysis, and commentary in the fields of technology, technology innovation, consumer products, electronics, the Internet, social media, computers, entrepreneurship, startup companies and business (1) Providing consumer product information and reviews in the fields of technology, electronics, computers and the internet; providing consumer product information in the nature of consumer product commentary in the fields of technology, electronics, computers and the internet; arranging and conducting conventions and conferences for business purposes in the fields of technology, technology innovation, consumer products, electronics, the internet, computers, social media, entrepreneurship, startup companies, business, marketing, design, finance, recruitment, intellectual property and leadership; providing an online searchable database featuring employment opportunities; providing online employment information in the field of job listings; business advisory and support services, namely, business consulting to social enterprises and existing for-profit and non- profit businesses working to foster diversity and inclusion in the technology industry; advertising and promotional services; marketing services, namely, email marketing, consumer research, and branded sponsorships; business marketing; business networking; business research; general business networking referral services, namely, promoting the goods and services of others by passing business leads and referrals among group members; market research services; business networking services; online advertising and marketing services; providing an online searchable database featuring classified ad listings and employment opportunities; promoting the goods and services of others by arranging for sponsors to affiliate their goods and services with an awards program; conducting public opinion polls; conducting public opinion online polls
(2) Providing information, news, analysis, and commentary in the field of current events relating to technology, technology innovation, consumer products, electronics, the Internet, social media, computers, entrepreneurship, startup companies and business; providing online journals, namely, blogs in the field of technology, technology innovation, consumer products, electronics, the Internet, social media, computers, entrepreneurship, startup companies, and business; entertainment services, namely, providing ongoing video series and continuing programs in the fields of technology, technology innovation, consumer products, electronics, the Internet, computers, social media, entrepreneurship, startup companies and business; providing a website featuring podcasts, non-downloadable videos and continuing programs in the fields of technology, technology innovation, consumer products, electronics, the Internet, computers, social media, entrepreneurship, startup companies, and business; arranging and conducting educational conferences; educational services, namely, arranging and conducting conventions, conferences, seminars, and workshops in the fields of technology, Internet products and services, start-up companies, entrepreneurship, marketing, design, finance, recruitment, intellectual property and leadership; providing online newsletters via e-mail featuring information in the fields of technology, technology innovation, consumer products, electronics, the Internet, social media, computers, entrepreneurship, startup companies and business; entertainment in the nature of competitions in the field of new product development technology; providing recognition and incentives by the way of awards to demonstrate excellence in the fields of technology, Internet products and services and entrepreneurship; arranging and conducting workshops and training meet-ups in the field of technology, Internet products and services and software development; entertainment services, namely, providing an ongoing radio program in the field of technology, technology innovation, consumer products, electronics, the Internet, computers, social media, entrepreneurship, startup companies and business; entertainment services, namely, providing ongoing audio and video programs featuring technology, technology innovation, consumer products, electronics, the Internet, computers, social media, entrepreneurship, startup companies and business; entertainment services, namely, providing podcasts in the field of technology, technology innovation, consumer products, electronics, the Internet, computers, social media, entrepreneurship, startup companies and business; subscription services, namely, providing subscription-based online publications, newsletters, information and networking opportunities in the field of current events relating to technology, technology innovation, consumer products, electronics, the Internet, social media, computers, entrepreneurship, startup companies and business; providing subscription-based business networking services in the field of current events relating to technology, technology innovation, consumer products, electronics, the Internet, social media, computers, entrepreneurship, startup companies, and business
(3) Computer services, namely, hosting online web facilities for others for organizing and conducting online meetings, gatherings and interactive discussions; computer services, namely, hosting and maintaining an online website for others to exchange information concerning technology and Internet products and services; product testing; application service provider featuring software for providing an online database in the field of transaction processing to upload transactional data, provide statistical analysis and produce notifications and reports; computer services, namely, acting as an application service provider in the field of knowledge management to host computer application software for creating searchable databases of information and data; computer services, namely, providing search engines for obtaining data on a global computer network; technology research in the field of Internet products and services, mobile communications and information technology
89.
Automatic electronic message filtering method and apparatus
Disclosed are systems and methods for improving interactions with and between computers in electronic messaging and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The disclosed systems and methods provide systems and methods for generating electronic message filters and for using electronic message filters comprising item category filtering criteria and having an automatically-determined expiration. The discloses systems and methods filter electronic messages using the item category filtering criteria while an electronic message filter remains active as determined using the automatically-determined expiration information.
In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, a plurality of electronic messages addressed to a user, (ii) analyzing, by a large language model executed by the processor, the plurality of electronic messages to identify potential actions, (iii) suggesting, by the processor, to the user, a potential action identified by the large language model, (iv) receiving, by the processor, user input related to the potential action, and (v) performing, by the processor, on behalf of the user, a subsequent action conforming to the user input.
G06F 40/40 - Traitement ou traduction du langage naturel
H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
H04L 51/216 - Gestion de l'historique des conversations, p. ex. regroupement de messages dans des sessions ou des fils de conversation
91.
Systems and methods for focused user account inboxes
In some implementations, the techniques described herein relate to a method including: (i) accessing, by a processor, a plurality of messages for a user, (ii) analyzing, by a large language model executed by the processor, the plurality of messages to extract a context of each message, (iii) determining, by the processor, a current context of interest to the user, (iv) identifying, by the processor, a subset of the plurality of messages that each comprises a context related to the current context of interest to the user, and (v) causing display, by the processor, of the subset of the plurality of messages in a digital message inbox.
G06F 40/40 - Traitement ou traduction du langage naturel
G06Q 10/1093 - Ordonnancement basé sur un agenda pour des personnes ou des groupes
H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
H04L 51/04 - Messagerie en temps réel ou quasi en temps réel, p. ex. messagerie instantanée [IM]
H04L 51/046 - Interopérabilité avec d'autres applications ou services réseau
H04L 51/216 - Gestion de l'historique des conversations, p. ex. regroupement de messages dans des sessions ou des fils de conversation
H04L 51/42 - Aspects liés aux boîtes aux lettres, p. ex. synchronisation des boîtes aux lettres
H04W 4/02 - Services utilisant des informations de localisation
92.
COMPUTERIZED SYSTEMS AND METHODS FOR AN ELECTRONIC INBOX DIGEST
Disclosed embodiments are directed toward a computer-implemented system and method for providing an email digest in association with an interface display of an electronic inbox. The disclosed digest includes non-native inbox functionality related to a summary data structure that includes an interactive portion, whereby upon generation of electronic prompts via a large language model (LLM), the digest can leverage functionality of the LLM to determine how electronic inbox content can be rendered for display.
Disclosed are systems and methods for receiving a meeting request via an electronic account of a user; determining a conflict between the meeting request and a pre-existing meeting, extracting and comparing information associated with each meeting based on an analysis of each meeting; determining a priority associated with each meeting based on the analysis of the information of each meeting; and utilizing a machine learning model to generate an output associated with the priority of each meeting to the electronic account of the user.
In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, electronic files stored in association with a user account, (ii) analyzing, by a large language model (LLM) executed by the processor, the electronic files and identifying, based on the LLM analysis, at least one file that is a candidate for deletion, (iii) compiling, by the processor, an electronic message comprising an output indicating deletion of the at least one file, (iv) causing display, by the processor, the electronic message, (v) receiving, by the processor, user input related to the at least one file, (vi) analyzing, by the LLM executed by the processor, the user input, and (vii) performing, by the processor based on the analysis of the user input via the LLM, an action on the at least one file conforming to the user input.
In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, an electronic message that comprises content generated by a user, (ii) predicting, by the processor, a potential action for the user by inputting the content of the electronic message into a large language model, (iii) suggesting, by the processor, the potential action to the user, (iv) receiving, by the processor, user input related to the potential action, and (v) performing, by the processor, on behalf of the user, a subsequent action conforming to the user input.
H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
G06Q 10/1093 - Ordonnancement basé sur un agenda pour des personnes ou des groupes
H04L 51/046 - Interopérabilité avec d'autres applications ou services réseau
96.
ENHANCED MAIL OPERATIONS USING LARGE LANGUAGE MODELS
The example embodiments are directed toward leveraging the power of large language models (LLMs) in a messaging application. In a first embodiment, LLMs are utilized to generate message content (both original and reply). In a second embodiment, LLMs are utilized to provide enhanced semantic search functionality. In a third embodiment, LLMs are utilized to provide intelligent actions to take based on message content.
One or more computing devices, systems, and/or methods are provided. A machine learning model may be trained using a plurality of sets of information. One or more pruning operations may be performed in association with the training to generate a machine learning model with a sparse set of field weights associated with feature fields associated with features of the plurality of sets of auction information. A request for content associated with a client device may be received. A set of features associated with the request for content may be determined. Positive signal probabilities associated with a plurality of content items may be determined using the machine learning model based upon field weights, of the machine learning model, associated with the set of features. A content item may be selected from the plurality of content items for presentation via the client device based upon the positive signal probabilities.
In an example, first-tier Internet Protocol (IP) address reputation scores, including a first first-tier IP address reputation score associated with a first first-tier IP address group and a second first-tier IP address reputation score associated with a second first-tier IP address group, may be determined based upon a plurality of events. A second-tier IP address reputation score associated with a second-tier IP address group may be determined based upon the plurality of first-tier IP address reputation scores. The second-tier IP address group may include the first first-tier IP address group and the second first-tier IP address group. An IP address reputation profile may be generated based upon the first-tier IP address reputation scores and the second-tier IP address reputation score. Whether or not a request for content associated with a first IP address is fraudulent may be determined based upon the IP address reputation profile and the first IP address.
In the embodiments, a novel prefetch service implemented on a prefetch server is provided to execute content (either targeted or selected) fetch requests in parallel with other requests thereby reducing the overall latency of a content delivery system. In some aspects, a method is provided to receive a prefetch request to prefetch a targeted content item to be presented prior to presenting a primary content item on a user device, the prefetch request including prefetch request parameters; generate, a callback URL associated with the prefetch request; transmit, to a primary content server, the callback URL; obtain a targeted content configuration corresponding to the prefetch request parameters; obtain the targeted content item based on the targeted content configuration; receive, a request to provide the targeted content item, the request including the callback URL; and transmit the targeted content item.
H04N 21/231 - Opération de stockage de contenu, p. ex. mise en mémoire cache de films pour stockage à court terme, réplication de données sur plusieurs serveurs, ou établissement de priorité des données pour l'effacement
H04N 21/234 - Traitement de flux vidéo élémentaires, p. ex. raccordement de flux vidéo ou transformation de graphes de scènes du flux vidéo codé
100.
COMPUTERIZED SYSTEMS AND METHODS FOR LOCATION-BASED CONTENT FILTERING AND DELIVERY
The disclosed systems and methods provide novel mechanisms for a location-based and content-relevant recommendation framework. The disclosed framework involves a hierarchical artificial intelligence/machine learning (AI/ML) based solutions that maximizes content quality and user engagement. The framework can identify local news content and accurately match the local content to users based on a user-based location proximity and relevancy. Accordingly, such content can then be provided to each user, which can be based on each user's preference settings for receiving recommended content.
