Abstract: An information processing device (10) includes: a morphological analysis unit (11a, 11b) performing morphological analysis to divide each of an article body text included in an article and a caption of each of images into morphemes; a phrase acquiring unit (12) dividing the article body text into phrases on a basis of a result of the morphological analysis performed by the morphological analysis unit (11b); and a correspondence determining unit (13). The correspondence determining unit (13) determines correspondence between each of the phrases of the article body text and the images by calculating a correlation between the caption and each of the phrases of the article body text on a basis of the result of the morphological analysis performed by the morphological analysis unit (11a).

Abstract: A method may include obtaining multiple search paths, each search path including a previous search query and multiple search materials. The method may include generating multiple relevancy scores corresponding to the search paths. The method may include obtaining a current search query of a new search. The method may include identifying one or more previous search queries that match the current search query. The method may include identifying a first search path and a second search path based on the first search path and the second search path corresponding to the matching previous search queries. The method may include comparing a first relevancy score of the first search path with a second relevancy score of the second search path. The method may include presenting the search materials of the first search path in response to the first relevancy score being greater than the second relevancy score.

Abstract: Descriptive data relating to at least a subset of a plurality of entities on a website is retrieved over a network. Endorsement data relating to the plurality of entities is retrieved from the website. A first set of probabilities is determined reflecting a probability that endorsements can be attributed to specific aspects. A second set of probabilities is determined reflecting a probability that terms can be attributed to aspects. Using the first set of probabilities and the second set of probabilities, a subset of the terms that are most probably associated with each entity are selected. Tags are then generated for each entity using the selected terms.

Abstract: Systems and methods create an inverted index for a set of documents utilizing a heap data structure. The documents can be divided into a series of n-grams. The n-grams can be hashed, producing hashed n-gram values. A first hashed n-gram value can be placed into the heap data structure. Operations performed using the heap data structure obtain document identifiers that are associated with documents that include a hashed n-gram value that matches the top n-gram value in the heap.

Abstract: A web page personalization system comprises a profile database and a profile manager. The profile database stores profiles for users. The profiles are comprised of segments of profile information for the users. The profile manager receives a request over an Internet for a group of segments of profile information about a user from a requestor. The request includes an anonymized identifier stored on a device for the user. The profile manager identifies a profile from the profiles for the user in the profile database using the anonymized identifier. The profile is comprised of the segments of the profile information about the user. The profile manager sends a portion of the profile information corresponding to the group of segments in an anonymized form in a reply over the Internet to the requestor. The requestor uses the group of segments to generate a personalized web page for the user.

Abstract: Multiple devices are detected in an environment and a user input is received to define a relationship between two or more devices in the plurality of devices. A system can determine that a first of the two or more devices includes a sensor resource and a second of the two or more devices includes an actuator resource. Data is identified describing outputs of the first device corresponding to the sensor resource and inputs of the second device corresponding to the actuator resource. A model is generated modeling interoperation of the sensor resource and actuator resource based at least in part on the data.

Abstract: Text data transmitted by a user device to a first server is retrieved. The text data is processed to determine whether an information recommendation rule set includes an information recommendation rule matching the text data. The information recommendation rule is set based on a recommendation information. If the information recommendation rule set includes the information recommendation rule matching the text data, the recommendation information is retrieved from a second server. A recommendation based on the recommendation information is transmitted to the user device.

Abstract: A method, computer program product, and a system where a processor(s), subject to obtaining permission, monitors browsing activity of an application browsing sources, including analyzing the sources to identify keywords and calculate densities of the keywords in content accessed at the sources. The processor(s) retains the keywords and the densities of the keywords in the content accessed at the sources in an historical record. The processor(s) downloads a resource of data and metadata from a source. The processor(s) updates the metadata of the resource based on keywords and densities of the keywords in the resource and source. The processor(s) determines a destination for the downloaded resource, based on selecting the destination comprising a highest percentage of attributes matching the updated metadata.

Abstract: An analytics mediator facilitates operations of an analytics engine and a corresponding analytics user interface (UI) in analyzing operations of a plurality of microservices. The analytics mediator enables the analytics engine to execute various types of conventional and new types of analyses with respect to the microservices, and to present the results of such analyses using the analytics UI, in a manner that is highly convenient and efficient for a user of the analytics engine, while also maintaining an independence, scalability, and other advantageous features of the microservices.

Abstract: Technology is directed to text message based concierge services (“the technology”). A user interacts with a concierge service (CS) via text messages to obtain a specific concierge service. For example, the user can send a text message to the CS, e.g., to a contact number provided by the CS, requesting for a recommendation of a restaurant, and the CS can respond by sending the recommendation as a text message. The CS determines a context of the request and generates recommendations that are personalized to the user and is relevant to the context. The CS can use various techniques, e.g., artificial intelligence, machine learning, natural language processing, to determine a context of the request and generate the recommendations accordingly. The CS can also receive additional information from a person associated with the CS, such as a concierge, to further customize or personalize the recommendations to the user.

Abstract: Zero-shot content detection includes building/training a semantic space by embedding word-based document descriptions of a plurality of documents into a multi-dimensional space using a semantic embedding technique; detecting a plurality of features in the multimodal content by applying feature detection algorithms to the multimodal content; determining respective word-based concept descriptions for concepts identified in the multimodal content using the detected features; embedding the respective word-based concept descriptions into the semantic space; and in response to a content detection action, (i) embedding/mapping words representative of the content detection action into the semantic space, (ii) automatically determining, without the use of training examples, concepts in the semantic space relevant to the content detection action based on the embedded words, and (iii) identifying portions of the multimodal content responsive to the content detection action based on the concepts in the semantic space det

Abstract: There is provided systems and methods for mapping of text phrases to a taxonomy. In an aspect, the method including: receiving the corpus and the taxonomy; mapping the text phrases in the corpus to a set of word embeddings in a word embedding space, where each sequence of word embeddings corresponds to individual words in one of the text phrases; vectorizing the taxonomy to a set of node embeddings in a node embedding vector space; mapping the set of word embeddings to the set of node embeddings using a mapping function, the mapping function outputting points in the node embedding space associated with sequences in the word embeddings; and outputting the mapping function.

Abstract: A unified notification platform for offline creation and distribution of notification content from a variety of data sources is described. The notification platform provides data adaptors that are reusable for generating notifications of different types, specifically, for generating notifications of different types that have features that have meaning across different notification types such that these features can be used to generate comparable relevance scores with respect to candidate profiles. The relevance score calculated for a notification with respect to a member profile is used to determine whether the notification is to be presented to the member represented by the member profile.

Abstract: The disclosed computer-implemented method for categorizing electronic messages for compliance reviews may include (1) identifying, as part of a compliance review for an organization, an uncategorized electronic message sent or received by a supervised user within the organization, (2) comparing the uncategorized electronic message with information gathered from previously categorized electronic messages sent or received by supervised users within the organization, (3) determining, based at least in part on the comparison, a relevance level of the uncategorized electronic message with respect to the compliance review, (4) receiving, from a compliance reviewer, feedback indicating whether the determined relevance level is correct, and (5) updating the previously gathered information based on the feedback from the compliance reviewer. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: User behaviors are monitored, by machine logic, during a visit to a venue by a user, the user behaviors associated with user interactions with items in the venue, a location of the items being tracked. In real-time, based, at least in part, on the user behaviors and the items, a subsequent behavior of the user is predicted, by machine logic, the predicting resulting in predicted behavior(s). Cognitive recommendations are provided, by machine logic, to the user in real-time during the visit, the cognitive recommendations corresponding to additional item(s) based, at least in part, on the predicted behaviors and the items. Machine learning is used to train a system for facilitating the noted aspects, as well as to update training.

Abstract: Described are computer-based methods and apparatuses, including computer program products, comprising the steps of, or structure for, storing a plurality of expert profiles in a database, each of the plurality of expert profiles comprising information associated with a person having knowledge in a particular category, subject or topic; receiving search criteria over a network from a query source; selecting at least one of the plurality of expert profiles comprising information that satisfy the search criteria; and transmitting expert profile data for each of the selected expert profiles to the remote search engine, the expert profile data comprising data that defines a displayable representation of a corresponding expert profile, the expert profile data further comprising data that facilitates a client-initiated, real-time communication session over the network with a person associated with the corresponding expert profile.

Abstract: A method, a computer program product, and a data processing system for determining a database signature of a database includes determining a set of characteristics of the database; identifying at least one unique characteristic of the database that is unique among characteristics of other databases, which characteristics of other databases are stored in a signature data store; generating the database signature from the at least one unique characteristic; and storing the database signature and the unique characteristic in the signature data store.

Abstract: Disclosed are systems, apparatus, methods, and computer readable media for discontinuing the following of records in an on-demand database service environment. In one embodiment, one or more records are identified according to one or more designated criteria. The records are stored in a database. The records are being followed by one or more users in an on-demand database service environment such that updates to the records are capable of being stored as feed items in one or more feed tables in the database. The feed items are capable of being published in an information feed displayed on one or more devices associated with the one or more users. The following of the identified one or more records by the one or more users is discontinued.

Abstract: To maintain user interest, the social networking system determines whether a particular user is interested in posting original broadcast feed stories to the social networking system during a session. Specifically, the social networking system determines a likelihood of a user posting an original broadcast feed story during the session. If the likelihood of the user posting an original broadcast feed story is above a threshold, the social networking system may encourage the user to post an original broadcast feed story by displaying original broadcast feed stories posted by other users to the user in a feed provided to the user. Specifically, the feed may contain more original broadcast feed stories posted by other users or the original broadcast feed stories posted by other users may be ranked higher in the feed than a feed provided to the user if the likelihood was below the threshold.

Abstract: Various embodiments of the invention provide methods, systems, and computer program products for conducting analytics on a communication so that search terms and corresponding synonyms can be considered in a context. A user identifies search terms and synonyms for the terms are provided. The user selects one or more of the synonyms and a topic model is applied to the search terms and selected synonyms to identify topics. The user selects a topic and communications associated with the topic are identified. The words articulated during the communications are then analyzed to identify occurrences where the search terms and synonyms were articulated during the communications. A GUI is displayed representing one of the communications with a plurality of icons, each icon representing one of the occurrences. Accordingly, the user may select a particular icon and a portion of the communication containing the corresponding occurrence is played and/or displayed for the user.

Abstract: Embodiments for extraction and summarization of decision discussions of a communication by a processor. The decision elements may be grouped together according to similar characteristics. The decision elements may be linked, and sentiments of the discussion participants towards each of the decision elements may be analyzed. A summary of the plurality of the decision elements may be provided via an interactive graphical user interface (GUI) on one or more Internet of Things (IoT) devices. The summary of the decision elements may be linked to domain knowledge. The summary may be enhanced using a domain knowledge.

Abstract: Systems, apparatus, and methods for providing promotions based on consumer interaction data are discussed herein. Some embodiments may include a system and/or apparatus including circuitry configured to provide electronic user interfaces (or impressions) of promotions to consumer devices and receive consumer interaction data indicating consumer interaction with the impressions. The system may be further configured to determine a selected promotion for providing in a subsequent impression based on the consumer interaction data. For example, the system may be configured to determine a promotion score of available promotion based on consumer interaction data indicating consumer responses to the available impressions. The promotion score may provide a rating by which available promotions may be selected and may be determined based on various criteria discussed herein to provide selected promotions to consumer devices.

Abstract: Methods, systems, apparatus, including computer programs encoded on computer storage medium, to facilitate identification of additional trigger-terms for a structured information card. In one aspect, the method includes actions of accessing data associated with a template for presenting structured information, wherein the accessed data references (i) a label term and (ii) a value. Other actions may include obtaining a candidate label term, identifying one or more entities that are associated with the label term, identifying one or more of the entities that are associated with the candidate label term, and for each particular entity of the one or more entities that are associated with the candidate label term, associating, with the candidate label term, (i) a label term that is associated with the particular entity, and (ii) the value associated with the label term.

Abstract: The present disclosure provides a method and an apparatus for broadcasting a search result based on artificial intelligence. The method includes: receiving a query sentence inputted by a user, and acquiring a plurality of candidate search results according to the query sentence; analyzing each candidate search result to determine a category of each candidate search result, in which the category includes a structured result and a rich-text result; acquiring intention information of the query sentence, and screening the plurality of candidate search results according to the intention information and the category of each candidate search result to obtain a screened search result; and generating text information corresponding to the screened search result, and broadcasting the text information.

Abstract: A method for operating an electronic device according to an embodiment of the present invention may comprise: if an occurrence of a notification is detected, determining an application related to the notification or a keyword extractable from the notification; determining whether feedback of a user for the notification occurs; and storing preference information of the user for the application or the keyword based on the feedback. Also, other embodiments are possible.

Abstract: Business Data Lake searching techniques are provided.

Abstract: A method and associated systems for identifying inputs to be used by a decision-support application. The decision-support application requests from the input-selection system a set of topics of interest that have experienced similar trends in public interest over a specified period of time, subject to certain constraints and confidence factors. In response, the system uses content retrieved from online news and social-media sources to identify common topics and past trends of public interest in each of those topics. The system then retrieves, from a more robust set of sources that include online references and encyclopedias, content related to the most popular topics and their related qualities. The system builds a Trie data structure for each topic and its related qualities and uses properties of Trie structures to efficiently identify the most similar Tries. The system then returns to the decision-support application the topics that correspond to the most similar Tries.

Abstract: A gaze initiated interaction technique for facilitating interaction between wearers of head-mountable devices. Methods are shown which allow users to interact with each other following an event of interlocking gaze. Methods are also shown which allows the operator of a personal point-of-interest beacon to control and limit interaction from the public thus ensuring a greater degree of privacy. Methods are also introduced which allow a mode of interaction to be determined by a remote service after mutual authorization of each interacting user. This disclosure also introduces a system of a head-mountable device which comprises a directional beacon transceiver system using beams in the infrared light spectrum enabling the detection of a gaze interlock event.

Abstract: Systems, apparatus, methods, and articles of manufacture for cooperatively-overlapped and Artificial Intelligence (AI)-managed interfaces. For example, multiple cooperatively and/or partially overlapped interfaces may be provided (e.g., via an electronic and/or touch-screen device), with such interfaces being dynamically managed by various AI components, such as natural language processing, machine learning techniques, and/or neural network data processing.

Abstract: Source objects according to a source data model are converted to target objects according to a target data model. A plurality of target data collections are generated, each including uniquely identifiable target objects. A first generated target data collection is merged with a subsequently generated target data collection.

Abstract: A method, computer program product, and system are disclosed. The method, when implemented in a computer system, includes receiving digital information at a production node. The digital information includes product information and production information, and the product information includes information identifying a product. The production information is configured to facilitate production of the product by the production node. The production node is identified by location information and one or more production criteria. The method further includes producing the product, identified by the product information, according to the production information, where the production node is configured to produce the product using the production information.

Abstract: Embodiments of the invention include methods and systems for question identification. Aspects of the invention include receiving, by a processor, an investigation profile, wherein the investigation profile associated with an investigation comprises a plurality of questions. Observation data associated with the investigation is received and one or more concepts are extracted from the observational data. The one or more concepts are mapped to the plurality of questions to generate one or more answers to the plurality of questions. The one or more answers to the plurality of questions are analyzed to identify unanswered questions from the plurality of questions.

Abstract: A method of generating search suggestions includes receiving an indication of a current location of the user device. After a user accesses a search function on the user device and before the user submits a search request, the method includes determining search results associated with locations in proximity to the current location of the user device, using query log data indicating selections of past search results by users after presentation of the past search results in response to respective past queries. The method also includes determining relative positioning of the search results based on the number of users that selected each search result, determining categories associated with the search results, grouping the search results by the determined categories; and sending the grouped search results and the one or more categories associated with the search results to the user device for display according to the determined relative positioning.

Abstract: Methods and systems for developing and distributing applications and data for building security applications can be provided. A plurality of data policies can be set for access and/or filtering security data based on selected parameters. One or more modules can be generated for processing the security data, with each of the modules governed by one or more module policies. Upon receipt of a request to initiate execution of the one or more modules to access and process a selected portion or filtered set of the security data, it can be determined if the request violates the data policies and/or the module policies applicable for processing the selected portion or filtered set of the security data, and if the data policies and/or the module policies are not violated, the one or more modules can be executed to process the selected portion or filtered set of the security data.

Abstract: A system, apparatus, and method are provided for implementing secondary profiles for members of an online application or service. Each member has a corresponding primary profile populated by the member, and a secondary profile populated with information from data sources other than the member. Each fact or entry in the secondary (or inferred) profile is accompanied by a confidence score reflecting confidence in the source of the fact, confidence that the fact is correctly associated with this member, and/or other factors. A given fact may be obtained or extracted from multiple sources, with each copy or version assigned a separate confidence score. In response to a request to identify members having a particular attribute, in addition to identifying members that have the attribute in their primary profiles, members having the attribute in their secondary profiles may be identified if the corresponding confidence scores are greater than a threshold.

Abstract: A data analysis system allows users to interact with distributed data structures stored in-memory using natural language queries. The data analysis system receives a prefix of a natural language query from the user. The data analysis system provides suggestions of terms to the user for adding to the prefix. Accordingly, the data analysis system iteratively receives longer and longer prefixes of the natural language queries until a complete natural language query is received. The data analysis system stores natural language query templates that represent natural language queries associated a particular intent. For example, a natural language query template may represent queries that compare two columns of a dataset. The data analysis system compares an input prefix of natural language with the natural language query templates to determine the suggestions. The data analysis system receives user defined metrics or attributes that can be used in the natural language queries.

Abstract: A method for a frame certainty metric for automatic content recognition. The method includes determining a frame match between media device frames of a media device stream relative to broadcast frames of a broadcast media stream and determining whether to shift the frame match by determining the following: a first frame certainty metric based on a first media device fingerprint and a target broadcast fingerprint; a second frame certainty metric based on a second media device fingerprint sequentially adjacent the first media device fingerprint and the target broadcast fingerprint; a third frame certainty metric based on a third media device fingerprint sequentially adjacent the first media device fingerprint and the target broadcast fingerprint; and a greatest frame certainty metric. The method further includes identifying the media device fingerprint corresponding to the greatest frame certainty metric as a target media device fingerprint matching the target broadcast fingerprint.

Abstract: A collaborative prediction system for altering predictive outcomes of dynamic processes may include a processor configured to store initial information about a specific dynamic process having a plurality of potentially differing outcomes, assign to the specific dynamic process a first likelihood of occurrence of at least one of the potentially differing outcomes, and receive, from a first system user, notification data, the notification data being associated with the specific dynamic process.

Abstract: Technical solutions are described for representing health of a cognitive system. An example computer-implemented method includes displaying an animated set of icons, each icon representing a question input to the cognitive system. Each icon has a respective movement pattern. The computer-implemented method also includes receiving a selection of a first icon from the animated set of icons. The computer-implemented method also includes in response, identifying a category of a first question corresponding to the first icon, determining a subset of the icons corresponding to question from the category, and displaying connectors between the subset of the icons.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a system configured to select actions to be performed by an agent that interacts with an environment. The system comprises a manager neural network subsystem and a worker neural network subsystem. The manager subsystem is configured to, at each of the multiple time steps, generate a final goal vector for the time step. The worker subsystem is configured to, at each of multiple time steps, use the final goal vector generated by the manager subsystem to generate a respective action score for each action in a predetermined set of actions.

Abstract: Technical solutions are described for selecting and retrieving, by a media retrieval system, media items for displaying. An example method for selecting and retrieving the media items includes monitoring a conversation of a user via a user device, and extracting a conversation topic from the conversation. The method further includes determining that a metadata database of a media storage associated with the user includes the conversation topic. The method further includes adding, in response, to a topic match database, from the media storage, an identity of a media item matching with the conversation topic, and adding, to a list of media items to be played back by a media display device, the topic match database. Further yet, the method includes playing back, by the media display device, the media item.

Abstract: Described are computer-based methods and apparatuses, including computer program products, comprising the steps of, or structure for, storing a plurality of expert profiles in a database, each of the plurality of expert profiles comprising information associated with a person having knowledge in a particular category, subject or topic; receiving search criteria over a network from a query source; selecting at least one of the plurality of expert profiles comprising information that satisfy the search criteria; and transmitting expert profile data for each of the selected expert profiles to the remote search engine, the expert profile data comprising data that defines a displayable representation of a corresponding expert profile, the expert profile data further comprising data that facilitates a client-initiated, real-time communication session over the network with a person associated with the corresponding expert profile.

Abstract: Systems and methods are described herein for updating search results based on a user's comment or a conversation among users using a media guidance application. A set of search results may be presented to a user or users. Comments or a conversation about the search results may be analyzed by the media guidance application. Selected comments by a user determined to have a greater weight may be used to update the search results.

Abstract: A system and method for a method for processing sound beams associated with visual elements, including: analyzing at least one received multimedia data element (MMDE) to identify audio features and visual elements within the MMDE; extracting at least one audio feature and at least one visual element from the MMDE; generating at least one sound signal from the MMDE based on the audio features; associating the at least one sound signal with at least one of the visual elements; and tagging each associated sound signals and visual element as an event.

Abstract: A mechanism is provided in a data processing system for using paraphrase metrics for answering questions. The mechanism receives an input question and generating a candidate answer from a corpus of information. The candidate answer has a supporting passage from the corpus of information. The mechanism divides the input question into a first sequence of tokens and divides the supporting passage into a second sequence of tokens. The mechanism identifies a plurality of subsequences of tokens within the second sequence of tokens and applies a paraphrase metric to compare the first sequence of tokens to each of the plurality of subsequences of tokens to generate a plurality of paraphrase metric scores. The mechanism then determines a confidence score for the candidate answer based on a highest paraphrase metric score within the plurality of paraphrase metric scores.

Abstract: The present invention extends to methods, systems, and computer program products for forming data responsive to a query. Responding to a query can include selecting data views on top of data sources. A data catalog stores data elements from different data sources and stores links between data elements from the different data sources. A view can be selected for a query based on one or more of: classification of data included in the data catalog or prior usage of data included in the data catalog. A selected data view is populated with data elements from the data catalog using the links to determine that data elements spanning multiple data sources satisfy the query. The data catalog can be used to identify relationships between data elements from different data sources that would not otherwise be identified.

Abstract: Embodiments are directed to a computer implemented method of improving queries. The method includes performing a query on a document set, wherein documents that satisfy the query comprise a first subset of the document set and documents that do not satisfy the query comprise a complement subset. Thereafter, calculating a correlation for all terms in the complement subset, with respect to the complement subset. Thereafter determining a set of top correlated terms. A set of bottom correlated terms is determined. The set of top correlated terms and bottom correlated terms are presented to generate an improved query.

Abstract: In one embodiment, a method includes receiving, from a client system, a query inputted by a first user at a search client, the search client being associated with context data from a page associated with the search client. The context data identifies: a type of the page associated with the search client, a social context of the page associated with the search client, and a threshold number of search results for display. The method includes identifying one or more entities matching the query and ranking each of the identified entities based at least in part on the social context and the type of the page associated with the search client. The method includes sending, to the client system, instructions for presenting a search-results interface including the threshold number of search results corresponding to the threshold number of top ranking identified entities.

Abstract: In one embodiment, a method includes receiving a query inputted by a user; identifying one or more objects matching the query; generating a reconstructed embedding of the query based on one or more term embeddings associated with one or more of the n-grams of the query, respectively; calculating, for each identified object, a relevance-score based on a similarity metric of the reconstructed embedding of the query and an object embedding associated with the identified object; generating one or more search results based on the calculated relevance-scores, each search result corresponding to one of the identified objects; and sending a search-results interface for display, the search-results interface comprising one or more of the search results, each search result comprising a reference to its corresponding identified object.

Abstract: A mechanism is provided for automated management of a set of media data using a set of social networking data. The set of social networking data related to a media event is collected. The set of social networking data related to the media event is correlated with the set of media data of the media event. Based on the set of social networking data, a determination is made of an inflection point of the media event. An inflection marker for the inflection point of the media event is then established with respect to the set of media data of the media event.