Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media relate to a method for providing video communications with dynamic virtual backgrounds within a communication platform. The system establishes a connection with the calendar account of a user. The calendar account maintains historic and planned meeting details for the user. The system may evaluate the calendar account of the user and automatically generate use rules for virtual backgrounds to be used for planned meetings. Based on contextual information of a planned meeting, the system may apply one of the generated rules and select a virtual background to be used for video communications during the meeting.

Abstract: An apparatus for updating a user profile based on a user file is included. Apparatus may include a processor and a memory communicatively connected to processor. Memory may contain instructions configuring processor to identify a plurality of profile sections in a user profile comprising a profile content; receive a user file; parse document content in user file by identifying a plurality of document sections in user file, categorizing a first document section of plurality of document sections of user file, identifying at least a document subsection of first document section, and categorizing document content in a first document subsection of at least a document subsection; and insert document content in at least one of the plurality of profile sections based on categorization of first document section and categorization of first document subsection.

Abstract: Methods, systems, and media for presenting related media content items are provided.

Abstract: Embodiments of the present disclosure are directed to a system, methods, and computer-readable media for a self-regulating and self-adjusting reconciliation of a cumulative contribution amount and a cumulative delivery value determined for instances associated with an entity.

Abstract: Systems and methods are disclosed for managing electronic communications. According to certain embodiments, an enterprise directory is provided for listing a plurality of enterprises. In one embodiment, the enterprise directory may include an enterprise profile for each enterprise identifying, among other things, a mode of communication for the enterprise. Enterprises that wish to communicate with one another may form partnerships with one another. In one embodiment, a partnership may be formed between two enterprises when one enterprise accepts a partnership request submitted by the other enterprise. Information regarding partnerships between enterprises may be stored in a database. Further, an enterprise user may request to electronically communicate (e.g., via IM, voice, or email) with a user associated with a different enterprise. Users associated with different enterprises may be allowed to communicate electronically with one another if their respective enterprises are in a partnership with one another.

Abstract: Software User Assistance (UA) is afforded from captured User Interface (UI) screen images, with reference to persisted Machine Learning (ML) models. The captured screen images are processed—e.g., using rasterization, Optical Character Recognition (OCR), and/or establishment of a coordinate system—with individual UI elements being determined therefrom. Referencing the persisted ML models, the software application/application state for the captured image is identified. UA data relevant to that application/application state is generated from the model, and then provided to the user (e.g., in a text box overlying the UI screen). Through the capture and processing of UI screen images, embodiments afford a homogenous UA experience for installation, maintenance, and/or upgrade of heterogeneous members of a larger overall landscape, over software lifecycles. Embodiments may be deployed locally on a frontend computer, in order to avoid exporting UI images due to privacy and/or security concerns.

Abstract: A communication platform may comprise different systems for helping a user discover features of the platform. However, the systems may generate different results. An application programming interface (API) may receive such outputs and may be configured to select between the outputs based on detecting a state at a user's computing device and/or using a machine-learned model to weight the outputs and/or probabilities associated therewith using a target metric. The API may then rank the outputs and select from among them based at least in part on the target metric.

Abstract: Systems and methods for digital property authentication and management are disclosed. A document representing a trade secret may be requested to be registered with a trade secret registry. A document obfuscation value corresponding to the document may be generated and may be registered with a blockchain. A record of the registration may be generated for the trade secret registry. The registry may be searchable and/or offer functionality such as valuation, insurance provision, and/or verification, among other benefits and functionalities.

Abstract: The present disclosure comprises a situational awareness system comprising a range of security features. The method can comprise receiving, by a first wireless network device comprising a processor, identity data associated with a second device utilizing a telephone number of a telecommunications network. The method can also comprise determining by the first wireless network device that a fraudulent action associated with the telephone number has occurred, based on the received identity data. The method can further comprise preventing, by the first wireless network device, the second device from utilizing a mobile application associated with the telecommunications network, in response to the determining that the fraudulent action has occurred.

Abstract: A computer-implemented method for optimizing search query results is disclosed. The computer-implemented method includes receiving a first natural language query, selecting a plurality of search query patterns based on the first natural language query, assigning a weight to each search query pattern in the plurality of search query patterns, generating one or more weighted keyword queries from each search query pattern based on the weight assigned to each search query pattern and one or more keywords from the first natural language query, evaluating a relevancy of one or more search results returned by each of the one or more weighted keyword queries for the first natural language query, and iteratively altering the weight assigned to a search query pattern until an optimal number of relevant search results are returned from the search query pattern for the first natural language query.

Abstract: An analysis application utilizes interactivity signals to generate relationships and promote content. One or more interactivity applications, such as a social networking application, are queried to retrieve interactivity signals. Interactivity signals include an interaction pattern that indicates a relationship between a user and relations of the user. A relationship graph is constructed based on the interactivity signals. Content associated with a user is promoted based on the relationship graph. A weight of the interactivity signals is adjusted to improve a ranking of the relationship graph and a ranking of the content.

Abstract: Disclosed are techniques for processing user profiles using data structures that are specialized for processing by a GPU. More particularly, the disclosed techniques relate to systems and methods for evaluating characteristics of user profiles to determine whether to offload certain user profiles to the GPU for processing or to process the user profiles locally by one or more central processing units (CPUs). Processing user profiles may include comparing the interest tags included in the user profiles with logic trees, for example, logic trees representing marketing campaigns, to identify user profiles that match the campaigns.

Abstract: According to an aspect of an embodiment, operations include controlling a user device to display a plurality of task-specific questions onto an electronic user interface (UI) of the user device. Each task-specific question corresponds to a check for presence of a bias in one of a sequence of development phases of a machine learning (ML) model. The operations further include receiving a first input comprising a plurality of user responses corresponding to the displayed plurality of task-specific questions and determining a set of biases associated with the ML model based on the received first input. The operations further include controlling the user device to display the determined set of biases and a set of plausible actions to mitigate an effect of the determined set of biases on the ML model.

Abstract: An analysis application utilizes interactivity signals to generate relationships and promote content. One or more interactivity applications, such as a social networking application, are queried to retrieve interactivity signals. Interactivity signals include an interaction pattern that indicates a relationship between a user and relations of the user. A relationship graph is constructed based on the interactivity signals. Content associated with a user is promoted based on the relationship graph. A weight of the interactivity signals is adjusted to improve a ranking of the relationship graph and a ranking of the content.

Abstract: A method includes receiving one or more search terms at a mobile computing device while the mobile computing device is located at a particular location. A search query that includes the one or more search terms and a location history of the mobile computing device is transmitted to a server. The method also includes receiving one or more search results in response to the search query, where the one or more search results include content identified based on a predicted destination of the mobile computing device. An interface identifying the one or more search results is displayed at the mobile computing device.

Abstract: Disclosed are systems and methods for an electronic framework that enables un-biasing of personalizations for users. The disclosed framework provides controls that can enable users to selectively escape from previously conceived notions of a user's preferred tastes and/or interests. Upon a user requesting content, the disclosed framework can analyze the type of request as well as the modeled behavior and preferences of the user, and automatically un-bias or depersonalize content for the user, thereby availing the user to a broader range of content from a larger pool of content then previously made available to the user.

Abstract: An apparatus for goal generation is disclosed. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to receive a goal datum related to a user, wherein the goal datum comprises behavioral parameters. The memory additionally instructs the processor to classify the goal datum to a user goal. The classification comprises training a goal classifier using a goal training data. Goal training data contains a plurality of data entries containing a plurality of goal datum inputs correlated to a plurality of goal outputs. The classification also comprises classifying the goal datum to the goal using the goal classifier. The classifier assigns the goal as a function of the classification. A goal path is generated as a function of the classification of the goal datum to a goal, wherein the goal path is divided into waypoints.

Abstract: Systems and methods are provided for operating a user-controllable parameter. An item pool is accessed, where the item pool contains a plurality of items, and where each item is associated with a parameter. A baseline position is identified, where the baseline position is associated with a particular value of the parameter. A user-controllable parameter is received, where the user-controllable parameter indicates a user preference for a next item relative to the baseline position. The next item is selected based on the baseline position and the user-controllable parameter, and the next item is provided via a computer network.

Abstract: Methods and systems are presented for dynamically modifying electronic content presented on a user device by third-party content providers based on goals associated with one or more entities. A content modification system may receive inputs related to goals for a user. The content modification system may synthesize the goals associated with the user. When the user uses a user device to request content from a third-party server, the content modification system may obtain the content and extract items included within the content. The content modification system may modify the content based on the synthesized goals, such as re-arranging the items, highlighting some of the items, or adding and/or removing items. The content modification system may cause the user device to present the modified content.

Abstract: A method includes receiving a training metric, the training metric indicating a parameter to be optimized by content recommendations. A machine learning algorithm maybe used to determine a plurality of different combinations of the recommendation algorithms in the experiment, and each of one or more of the plurality of combinations may be used to generate a content recommendation for one or more visitors. The statistical performance of each of the one or more combinations in optimizing the parameter (based on the content recommendations generated by those combinations) may be monitored and a higher percentage of visitors may be allocated to a combination that generates content recommendations that are the most effective at optimizing the parameter.

Abstract: The disclosure relates to a method for displaying information, device, system, electronic device, and storage medium. The method includes acquiring, user tag of a user account in response to a trigger operation on an information page, the user tag corresponding to one or more types of media files of the user account. The method includes displaying the user tag on the information page. The method includes displaying an associated user account corresponding to the user tag in response to an operation of selecting target user tag from the user tag.

Abstract: In some examples, a database management node updates object metadata with indicators of access frequencies of a plurality of objects in a data store that is remotely accessible by the database management node over a network. The database management node selects a subset of the plurality of objects based on the indicators, and caches the subset in the local storage.

Abstract: A computer-implemented method for customizing training contents for a user, including: establishing a user profile and a personal learning corpus for the user; generating a first baseline indicating that the user is interested and a second baseline indicating that the user is not interested; monitoring the user's reactions when the user is consuming contents related to a second topic, wherein the reactions include the one or more of biometrical indicators, facial expressions, and body language; comparing the reactions with the first baseline and the second baseline to determine an interest level; and recommending additional contents related to the second topic if the interest level is higher than a predefined threshold.

Abstract: Methods, systems, and apparatus for receiving a query; selecting one or more entities responsive to the query; providing, for display on a map portion of an interface, map-based representations of the one or more entities; providing, for display on a list portion of the interface, list-based representations of one or more of the entities; generating an additional query based on selection of a particular map-based representation of a particular entity; determining that, when the particular map-based representation was selected, a particular list-based representation was visible on the list portion; adjusting a ranking score for the particular entity; ranking the particular entity among one or more other entities identified as responsive to the additional query; and providing, for display on the list portion, list-based representations of at least one of the one or more other entities, including the particular list-based representation which remains visible on the list portion.

Abstract: A method, computer system, and computer program product for eliminating confirmation bias in a user search query is provided. The present invention may include receiving a user-entered search query from an open ended-search tool. The invention may also include identifying a field associated with the received user-entered search query. The invention may further include creating a dictionary based on the identified field. The invention may also include determining the received user-entered search query relates to an effect by parsing the created dictionary. The invention may further include identifying one or more causes associated with the effect by parsing the created dictionary. The invention may also include generating a plurality of suggested search queries based on the one or more identified causes.

Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.

Abstract: A system that transforms electronic messages into annotated messages that include contextual information to aid a recipient in utilizing the electronic message, understanding its meaning, and responding to the message. Annotations are additions or modifications to the original message with contextual information that is related to the features and contents of the original message. Message features are extracted and used to search one or more sources of contextual information. Relevant items are retrieved and added to the message, for example as attachments, hyperlinks, or inline notes. Machine learning techniques may be used to generate or refine modules for feature extraction and information selection. Feedback components may be used to track the usage and value of annotations, in order to iteratively improve the annotation system.

Abstract: Media content search results ranked by popularity is described. In embodiment(s), a search request for television media content can be initiated by a viewer, and television media content that is relevant to the search request can be identified. The relevant television media content can then be ranked based on a popularity rating and the relevant television media content can be displayed in an ordered list that is ordered by popularity rankings.

Abstract: A system and method is provided for dynamically managing advertiser affiliate links for online marketing. A global redirect server accepts a visitor's web browser request for a product or non-product webpage associated with an affiliate network advertiser URL, and returns a corresponding product or non-product webpage to the visitor that is corrected for the visitor's geographic region if such a webpage exists, or returns the originally requested webpage if it does not. The server determines the visitor's geographic region based upon request metadata, and can generate a corrected webpage that affords analytic and commission tracking even if no corresponding affiliate network exists in the determined geographic region. The server includes a database for locating products within the determined geographic region that are comparable to the product of the product webpage request, in the event that the exact product is not available in the geographic region.

Abstract: A passenger state analysis method and apparatus, a vehicle, an electronic device and a storage medium. The method includes: obtaining a video stream of a rear seat area in a vehicle; performing face and/or body detection on at least one image frame in the video stream; determining state information of a passenger in the rear seat area according to a face and/or body detection result; and in response to the fact that the state information of the passenger satisfies a predetermined condition, outputting prompt information to a driver area or a specified device in the vehicle.

Abstract: A system and method are provided for indexing and mining content of multiple data sources. The method includes: providing a database of learned content of multiple data sources learned using text analysis, the learned content identifying one or more concepts to which a data source relates, wherein the concepts are cognitively associated with the data source and include concepts not explicitly referenced in the data source and providing an index of the learned content including associations between concepts with mappings between concepts and the multiple data sources. The method further includes receiving input of a query and using text analysis to analyze the query to determine one or more query concepts to which it relates and mining the indexed concepts in response to the query concepts to return a list of referenced data sources.

Abstract: A search system that is configured to generate personalized ranked lists of search results for end users is disclosed. The search system provides backend search services to several websites of different organizations, where the websites are configured to offer goods for acquisition to the end users. The search system is configured to construct profiles for users that interact with webpages of the websites, and is further configured to construct personalized re-rankers based upon such profiles.

Abstract: A system to provide dynamic placement of new images in an electronic file presented on an electronic device according to various attributes associated with a user operating the electronic device. A scanning mechanism is implemented to scan each image within the electronic file to identify tagged objects. A selection mechanism is implemented to select the new images of various products based on geographic and demographic attributes associated with the user. A placement mechanism is implemented to fittingly replace all the tagged objects with the new images. The electronic file is updated to include the selected products rather than the tagged objects. While the user is accessing the electronic file on the electronic device, the user is able to view the selected products rather than the tagged objects in the electronic file.

Abstract: A system and method are provided for interacting with a web site having a plurality of web pages delivering user services and content sources including a web search service, electronic messaging service and web content page. Each web page includes portal script executable by a web browser to enable unique functions within the web site accessed using different types of selection of selectable items of the web pages.

Abstract: A receiver of television signals received via air, cable, internet, or by way of connection to an external device. The receiver includes a memory means wherein contents are stored, received through said receiver. The receiver also includes a data management means configured to organize and display the contents of the memory means. The data management means carries out an authentication procedure that allows for a determined user to be associated to his/her profile, that allows for storing and/or accessing private data of said memory means, that are associated uniquely to said determined user, and that do not appear to exist when exploring the contents of said memory means, if beforehand said authentication procedure has not been carried out by said determined user.

Abstract: A system and method is provided for dynamically managing advertiser affiliate links for online marketing. A global redirect server accepts a visitor's web browser request for a product or non-product webpage associated with an affiliate network advertiser URL, and returns a corresponding product or non-product webpage to the visitor that is corrected for the visitor's geographic region if such a webpage exists, or returns the originally requested webpage if it does not. The server determines the visitor's geographic region based upon request metadata, and can generate a corrected webpage that affords analytic and commission tracking even if no corresponding affiliate network exists in the determined geographic region. The server includes a database for locating products within the determined geographic region that are comparable to the product of the product webpage request, in the event that the exact product is not available in the geographic region.

Abstract: A system for multi-channel digital marketing optimization includes a memory for storing a marketing optimization program code, and a marketing optimization data; and a processor communicatively coupled to the memory. The processor executes the marketing optimization program code to create a cluster template by creating and storing within the marketing optimization data an individual business template for each of a plurality of businesses, classifying the plurality of businesses into a cluster based at least in part on one or more marketing objectives, creating and storing within the marketing optimization data a cluster template based at least in part on a combination of captured and calculated data for the plurality of businesses within the cluster. The processor executes the marketing optimization program code further to repeat the cluster template creation steps for a plurality of clusters; and to mathematically combine the cluster templates to create a plurality of target marketing templates.

Abstract: A system for automated classifying of electronic messages is disclosed. The system may receive an electronic message comprising a text including a message body and a metadata. The system may determine a case status based on the metadata and extract a set of events form the message body in response to the case status. The system may determine a case type based on the set of events and a set of case types. The system may generate a new case event in a case management system based on the case type.

Abstract: A computing device is programmed to receive, first and second user indicia of interest for media content. The computing device is further programmed to receive first user data related to a media content item. Based at least in part on the first and second user indicia of interest and the first user data, the computing device is further programmed to generate output that the first user recommend the media content item to the second user.

Abstract: Methods and systems are provided for providing an insights page that is displayed at a user interface of a computing device in response to a call. The caller who is making a call and/or the callee that is receiving the call can be identified along with one or more relevant organizations. A customer relationship management (CRM) application can then be launched at the computing device, and relevant records that are relevant to the call can be automatically determined at a server system. The relevant records can include records that are determined to be relevant to the call from any organization that a user has access privileges to. The insights page displayed at the user interface of the computing device includes user interface elements for accessing the relevant records. Each user interface element is selectable to open a relevant record that has been determined to be relevant to the call.

Abstract: A computer-implemented method includes identifying a plurality of hyperlinks on a first webpage. The computer-implemented method further includes determining, for each hyperlink in the plurality of hyperlinks, a degree of likelihood that a user will select a given hyperlink in the plurality of hyperlinks. The computer-implemented method further includes initiating a first bid request for a first ad space for a second webpage that is accessible by a first hyperlink in the plurality of hyperlinks based on the first hyperlink having a degree of likelihood above a given threshold level. The computer-implemented method further includes determining a selection of the first hyperlink by the user. The computer-implemented method further includes displaying a first advertisement associated with a first winning bid on the second webpage. A corresponding computer system and computer program product are also disclosed.

Abstract: A method includes receiving a first set of documents that correspond to data discovery documents. The method further includes generating a map of terms and words based on the first set of documents, the map of terms and words corresponding to concepts. The method further includes receiving from a first user an initial document relating to a data discovery issue. The method further includes requesting the user to provide an identification of at least one of an initial name of a first person, an initial date, and an initial keyword related to the legal issue. The method further includes generating at least one of a similar name of a second person, a similar date, and a similar keyword based on the map of terms and words. The method further includes identifying a review document based on the review document including at least one of the similar name of the second person, the similar date, and the similar keyword.

Abstract: Systems, methods, and computer-readable media for generating group-based sequential point-of-interest (POI) recommendations are disclosed. A primitive graph or sparse transition matrix is constructed that represents relationships between users, between POIs, and between users and POIs. A loss data prediction algorithm is executed on the primitive graph to obtain a filled graph, which may be a filled user-POI bipartite graph. A group sequential recommendation engine then performs an iterative sequential recommendation process that involves performing, at each iteration, various manipulations on the filled graph to obtain first a homogenous node type graph and then a minimum spanning tree. A next POI to recommend in a sequence of POIs is then determined from the minimum spanning tree. The iterative process continues until stopping criteria is met.

Abstract: A method includes detecting a keyword within an audio stream. The keyword is one of multiple keywords in a database, in which each of the multiple keywords relates to at least one of multiple domains in the database. The database stores a first confidence weight for each of the multiple keywords that are related to a first domain among the multiple domains. Each first confidence weight indicates a probability that a corresponding keyword relates to the first domain. The method includes determining whether a first confidence weight of the keyword is at least equal to an activation threshold value associated with the first domain. The method includes, in response to the first confidence weight of the keyword meeting the activation threshold value, activating a DS-ASR engine corresponding with the first domain to perform speech-to-text conversion on the audio stream.

Abstract: Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for providing content. A first call for content to be published on a resource associated with a publisher is received from a requesting device. A determination is made when the publisher has authorized additional content item calls to be automatically generated responsive to receipt of the first call. A first content item responsive to the first call is determined. A message including call parameters is generated that define publisher or serving system criteria for the additional content items. The first content item and message responsive to the first call are provided. A second call for content, in conformance with the call parameters, is received after processing the message. A second different content item that is responsive to the second call is provided for publication on the resource along with the first content item.

Abstract: Systems and methods are provided for identifying and managing trusted sources in online and networked content. URLs and other objects are vetted and identified as trusted sources based on the documents in which these objects are used or otherwise acted upon and not on the content of the URLs or other objects themselves. When a URL or other object is used in a document, the URL is given a score based on the use activity, attributes of the document itself, and, optionally, user history of the user. As users use that same URL with respect to their documents, the scores from those activities are accrued to that URL. A URL with an accrued score (value) above (or equal to) a threshold value can be added to a corpus of trusted sources that can be accessed when conducting research and/or by other applications and search engines.

Abstract: In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products for receiving, by a computing system, a query that was specified by user input at a computing device. The computing system identifies one or more results to the query. The computing system provides the one or more results for presentation by the computing device. The computing system receives an indication that user input at the computing device provided input to save a user-selected result, of the one or more results, for later presentation. The computing system receives a request to present the computing device with a display of saved results to search queries. The computing device presents the display of saved results to search queries, including a presentation of the user-selected result and a second user-selected result.

Abstract: A search engine is modified to perform increasingly precise image searching using iterative Natural Language (NL) interactions. From an NL search input, the modification extracts a set of input features, which includes a set of response features corresponding to an NL statement in the NL search input and a set of image features from a seed image in the NL search input. The modification performs image analysis on an image result in a result set of a query including at least some of the input features. In a next iteration of NL interactions, at least some of the result set is provided. An NL response in the iteration is added to a cumulative NL basis, and a revised result set is provided, which includes a new image result corresponding to a new response feature extracted from the cumulative NL basis.

Abstract: In one implementation, a method for providing a user with an assessment of website quality includes receiving, at a computer system, identification of a website; retrieving, by the computer system, content that comprises the website; and automatically analyzing, by the computer system, the content. The method can further include determining, by the computer system, (i) a search engine optimization (SEO) sub-score for the website, (ii) an accessibility sub-score for the website, and (iii) a quality assurance score for the website based on the analysis of the content. The method can additionally include determining, by the computer system, a quality score for the website based on a combination of the SEO sub-score, the accessibility sub-score, and the quality assurance sub-score; and transmitting, by the computer system, the quality score to a client computing device for presentation in a user interface.

Abstract: An information processing device, including an acquiring unit that acquires relationship information indicating a relationship between a plurality of first objects indicated by symbols input by a user, and a file control unit that generates display information related to display of second objects including position information indicating positions of the second objects corresponding to the first objects in a document file on the basis of the relationship information.