Abstract: An aspect provides a method, including: obtaining, at an information handling device, user input search data; accessing contextual data; refining, using one or more processors, the user input search data based on the contextual data; searching, using one or more processors, a repository of stored tag data with refined user input search data to identify one or more stored tags matching one or more stored objects; and returning, using one or more processors, one or more results of the searching, the one or more results indicating one or more stored objects associated with stored tag data. Other aspects are described and claimed.

Abstract: The invention includes an algorithmic method for dynamically computing complex relationships among objects of an underlying functional system. The invention includes a method to algorithmically determine a set of functional locations in n-dimensional functional space of a set of elements of a functional system by electronically representing a set of data entities in a database system, the database system comprising a logical data model for structuring data sets from which functional information can be derived, using the logical data model to associate a set of characteristics with a reference point in the functional information system, selecting a functional positioning algorithm, and wherein the functional positioning algorithm executes a set of steps that takes as input a set of characteristics and returns as output a set of locations in n-dimensional functional space.

Abstract: System and method for creating enabling the user to select fields from a database, semi structured or unstructured documents that produces an automated process of joining the database tables, semi structured or unstructured documents into a feature vector that can be further processed by machine learning algorithms or preprocessing routines and filters. The full join performed starts by producing a graph representation of the links between data tables/documents and then restructuring the information into the most efficient join tree. The join tree then extracts the data in the form of a feature vector.

Abstract: A method and system are provided for performing a legal document search. The method includes finding, by a processor, for each of a plurality of documents, a respective law clause related thereto, to obtain a plurality of related law clauses. The method further includes constructing, by the processor, a graph having nodes defined by the plurality of documents and the plurality of related law clauses and having edges defined by (1) relations between the plurality of documents and the plurality of related law clauses and (2) relations between the plurality of documents. The method further includes identifying, by the processor, from the plurality of documents, one or more candidate documents that are similar to an input query document by mining the graph using similarity criteria.

Abstract: Disclosed herein are systems and methods for an analytics server to efficiently generate a control group dataset, including receiving, by the analytics server, a request to generate a control group dataset based on a test dataset and potential control dataset; generating, by the analytics server, an instruction to receive a first dataset based on the request; identifying, by the analytics server, data points within the first dataset corresponding to a number of users and user attributes; generating, by the analytics server, a second dataset by normalizing the user attributes; generating, by the analytics server, a third dataset comprising a space-filling curve, where each space-filling curve data point corresponds to the normalized user attributes and the number of users; determining, by the analytics server, control users by matching the space-filling curve data points with the user attribute; and generating, by the analytics server, an instruction for display on a client device.

Abstract: Provided herein are systems, methods and computer readable media for classification and tagging of textual data. An example method may include accessing a corpus comprising a plurality of documents, each document having one or more labels indicative of services offered by a merchant, generating a query based on extracted features and the documents, generating a precision score for at least a portion of the generated query and selecting a subset of the generated queries based on an assigned precision score satisfying a precision score threshold, the selected subset of the generated queries configured to provide an indication of one or more labels to be applied to machine readable text. A second example method, utilized for tagging machine readable text with unknown labels, may include assigning a label to textual portions of the machine readable text based on results of the application of the queries.

Abstract: Systems and techniques are disclosed to rank documents by analyzing a query log generated by a search engine. The query log includes data relating to user behavior, queries and documents. The systems and techniques distill query log information into surrogate documents and extract features from these surrogate documents to rank the documents.

Abstract: An online system receives posts that include links to various external pages and presents those posts to users of the online system. When the online system determines an opportunity to present a post to a particular viewing user of the online system, the online system determines a quality metric and an associated value score for the post. The quality metric is determined as a likelihood that the viewing user will view the external page for less than a threshold time period, and is used to adjust the associated value score. The online system compares the value score of the post to the value scores of other posts and selects one or more of the compared posts for presentation to the viewing user of the online system.

Abstract: A computer-implemented technique can include detecting an initiation of composing an electronic message by a user, obtaining contextual information for the electronic message from a source external to a text of the electronic message, obtaining a first suggestion for the text of the electronic message based on the contextual information, detecting an operating condition indicative of a user activity during which the user is likely to experience difficulty in typing, in response to detecting the operating condition, obtaining a second suggestion for the electronic message based on the contextual information, the second suggestion being more detailed than the first suggestion, and outputting one of the first and second suggestions depending on one or more other conditions.

Abstract: Embodiments of the invention provide a computer-implemented method, computing system and computer program product for analyzing a message in a social network. The method comprises identifying an entity from the message; detecting historical popularity of the entity in a social network; identifying a topic from the message; detecting historical popularity of the topic in the social network; and generating an entity-topic correlation factor for the entity and the topic based on the historical popularity of the entity and the historical popularity of the topic. Results obtained with embodiments of the invention may be provided to popularity prediction tools for improving popularity prediction of messages in social networks.

Abstract: Provided herein are systems and methods for generating a set of recommended media works based on an identified seed media work. The seed media work is used to identify a set of co-occurring media works, which are defined as media works that have been intentionally interacted with within a predetermined time window as the seed media work by a single user. After the co-occurrence set is created, it is ranked and filtered. Media works identified in the co-occurrence set may then be selected based on their ranking.

Abstract: A system and a method are disclosed for predicting potential reach of an alert to a targeted audience, targeted personal delivery devices and targeted non-personal notification delivery devices in an emergency mass notification system. The system and method optimize alert deliveries based on the predicted reach.

Abstract: A trained search system can be configured to retrieve a candidate subset of results, where the trained search system uses data extracted from a machine learning scheme. The machine learning scheme can be trained to identify results that are ranked by a computationally expensive algorithm, such as a ranking algorithm. When a query is received, the trained search system can be used to retrieve results instead of applying the computationally expensive ranking algorithm.

Abstract: Systems and methods are described to address shortcomings in conventional conversation systems by determining an execution path for a natural language query using questions and answers and selecting the path in a knowledge graph based on the entities in the questions and answers and the user's feedback. In some aspects, the systems and methods described provide for determining an execution path for a natural language query presented to an interactive media guidance application. The interactive media guidance application receives, from a user, a query including an input entity and an unknown term. The interactive media guidance application retrieves, from a knowledge graph, a plurality of possible responses for the query. The interactive media guidance application determines a correct response of the plurality of possible responses based on feedback from the user. The interactive media guidance application selects an execution path for the query based on the correct response.

Abstract: A device may receive information that identifies an item to be categorized. The device may map the item to a first vector based on the information that identifies the item. The device may compare the first vector to a second vector based on mapping the item to the first vector. The device may determine a similarity value between the first vector and the second vector based on comparing the first vector and the second vector. The device may determine that the similarity value satisfies a threshold. The device may determine a category associated with the item based on the similarity value satisfying the threshold. The second vector may be associated with the category. The device may provide information that identifies the category associated with the item to cause an action to be performed.

Abstract: For calculating a social zone distance, a processor determines distances to one or more persons using the sensor array. In addition, the processor calculates the social zone distance based on the distances.

Abstract: A method for ranking comments includes receiving a request for a media item; obtaining a plurality of comments associated with the media item; and for each of the plurality of comments, identifying an entity that provided a respective comment; and identifying an attribution score for the entity, the attribution score based on a quantity of responses attributed to a sharing message pertaining to the media item, the responses representing consumption of the media item. The method further includes determining ranking scores for the plurality of comments based on corresponding attribution scores; and providing the media item and at least a portion of the plurality of comments to be displayed in an order defined by the ranking scores.

Abstract: A recommender engine is configured to access memory and surface transmedia content items; and/or linked transmedia content subsets; and/or one or more identifications of identified users; and/or content items of the plurality of transmedia content items associated with at least one identified user. The surfaced items are presented for selection by the given user via the transmedia content linking engine as one or more user-selected transmedia content items.

Abstract: A content server generates a media channel including a plurality of media items. A request for a media channel is received from a client device of a user, the request including a free-form media input seed identifying a plurality of ambiguous entities. A plurality of media playlists of media items is determined where each media playlist is associated with a corresponding one of the plurality of ambiguous entities identified by the free-form media input seed. The plurality of media playlists are combined into the media channel that includes media items selected from among the plurality of media playlists. The media channel is provided to the client device.

Abstract: Systems, apparatuses, services, platforms, and methods are discussed herein that provide user search services to a communication platform. An example user search service receives a user query to find users of the communication platform associated with one or more search terms, performs a graph search process based at least on the one or more search terms to identify a first set of users related to the user through at least one common user, and performs an indexed search process to identify a second set of users associated with the one or more search terms. The user search service then presents to the user a result view comprising the first set of users prioritized over the second set of users.

Abstract: One example is a system including a plurality of combinations of summarization engines and/or meta-algorithmic patterns used to combine a plurality of summarizers, an extractor, an evaluator, and a selector. Each of the plurality of combinations of summarization engines and/or meta-algorithmic patterns receives content to provide a meta-summary of the content. The extractor generates a collection of search queries based on the content. The evaluator determines a similarity value of each combination of summarization engines and/or meta-algorithmic patterns for the collection of search queries. The selector selects an optimal combination of summarization engines and/or meta-algorithmic patterns based on the similarity value.

Abstract: Methods, systems, and computer program products for ranking data items are described. A ranking configuration is defined for an object type, the ranking configuration comprising an assignment of one or more ranking dimensions to the object type and, for each of the one or more assigned ranking dimensions, one or more corresponding values and a significance weight assigned to each value, with at least one of the values being a dynamic value. Each ranking dimension comprises one or more object attributes and a ranking-impact weight, with at least one of the object attributes being a context-based object attribute. A ranking condition is generated for each ranking dimension assigned to the object type. The generation of the ranking condition is based at least in part on one or more object attributes, a specified ranking-impact weight, a context value, and the one or more values and associated significance weights.

Abstract: Data is received that include values that correspond to a plurality of variables. A score is then generated based on the received data and using a boosted ensemble of segmented scorecard models. The boosted ensemble of segmented scorecard models includes two or more segmented scorecard models. Subsequently, data including the score can be provided (e.g., displayed, transmitted, loaded, stored, etc.). Related apparatus, systems, techniques and articles are also described.

Abstract: In one embodiment, a method includes accessing user-concept scores for a first set of users, wherein each user-concept score is associated with a user-concept pair; calculating recommended user-concept scores for a subset of user-concept pairs in a second set of users. The first set of users may be discrete from the second set of users. A recommendation-algorithm may compute the recommended user-concept scores for a user-concept pair by optimizing an objective function comprising a plurality of predicted rating functions. Each predicted rating function may be determined using a user score, a concept score, a user-bias value associated with the user, as well as a concept-bias value associated with the concept. Finally, the method may include sending recommendations for one or more concepts based on the recommended user-concept scores for the second set of users.

Abstract: A method and system for providing adjusted content in a webpage are described. The system monitors traffic to a website and tracks users that are visiting the website to identify one or more parameters relating to relating to the user, including parameters associated with an identity of the user, navigation behavior for the user within the website, and usage of content by the user within the website. The system analyzes the parameters and selects at least one statistical algorithm for a type of the parameter, and based on the analysis, identifies an organization to which the user belongs. The system selects and presents content for the website to be presented to the user based on the analysis.

Abstract: Methods and systems for calculating a current response rate to an offer are disclosed. Examples of offers include but are not limited to design options for a web page and scripts used by operators in a call center. An offer may be served multiple times to one or more users and the current response rate may be determined for a point in time. The method may comprise obtaining estimates of response rate in successive iterations of response rate estimation. Each estimate may be determined over a period of time ending at the point in time, and each estimate may be determined over a larger period of time than the previous estimate. A range of uncertainty may be defined by upper and lower bounds for the estimates of response rate, with at least the first estimate being within the range of uncertainty. Each estimate may be compared to one or both of the upper and lower bounds and the result of the comparison may be used in the selection of one of the estimates as the calculated current response rate.

Abstract: In one embodiment, a method includes receiving, from a client system of a first user of the communication system, an input from the first user to access a card-stack interface, generating a card cluster comprising a plurality of cards, each card comprising a suggested query referencing a query-domain and one or more query-filters, wherein each query-filter references one or more objects associated with the communication system, and wherein each card in the card cluster is ranked within the card cluster based on a predicted click-thru rate (CTR) for the card based on one or more user-engagement factors, and sending, to the client system in response to the input from the first user, the card-stack interface for display to the first user, wherein the card-stack interface comprises the card cluster, the cards of the card cluster being ordered based on the rankings associated with the cards.

Abstract: A system and method for concealing searches for information stored on public networks, includes intercepting a sensitive query to a search engine prior to transmission of the sensitive query over a public network, transforming the sensitive query into one or more related queries, submitting the related queries over the public network to the search engine, aggregating search results from the search engine, and performing a search on the original query with a search engine privately against said search results.

Abstract: A method for facilitating the evaluation of candidates in an evaluation process is provided. The method includes operations of selecting a first data set including ratings of recorded responses of a set of evaluated persons and of selecting a second data set including additional recorded responses of a person under evaluation. The recorded responses are responsive to multiple prompts presented to each of the set evaluated persons in a recording sequence. The first data set further includes an evaluation result of each evaluated person in the evaluation. The additional recorded responses are responsive to the plurality of prompts and ordered in a first order corresponding to a recording sequence. The method includes analyzing the first data set to calculate a reviewing sequence and presenting the additional recorded responses in a second order corresponding to the reviewing sequence. Associated systems and other methods are also provided.

Abstract: An electronic device is provided. The electronic device includes a sensor circuit configured to obtain workout associated data using at least one or more sensors, a processor electrically connected with the at least one or more sensors, and a memory electrically connected with the processor. The processor is configured to classify the obtained data for each kind, divide the data, which is classified for each kind, into a plurality of sections, compare the sections with each other and select at least one or more sections, and provide description information about the selected section.

Abstract: A method, system, and medium related to data retrieval using tags and routing rules to optimize the data retrieved and the response time for the data retrieval by decreasing the latency of the response and by increasing the efficacy of the dynamic content delivery is provided. A message request is received from a client server. A local server determines if the digital content resides on a local server by comparing a tagged rule for the message request with a tagged rule associated with the local server. If the local server determines, by comparing the tagged rules, that the digital content does not reside on the local server, the local server sends the message request for the digital content to a service server. The service server then parses the tagged rule associated with the message request into a set of tree-based hierarchical tagged rules.

Abstract: An SSO provider—i.e., a provider of user accounts that a number of other online services accept as a sign-on technique—identifies the online services to which its users sign on, as well as the digital content items that those users access. The SSO provider uses this information to associate particular content items with particular online services, or combinations of online services. The SSO provider can then use the associations to make recommendations of content items to users based on the services to which the users have signed on.

Abstract: A computer-implemented method and system are provided for reducing garbage collection overhead. The method includes specifying, by a hardware processor from a set of nodes of a Directed Acyclic Graph representing an application program, wherein each of the nodes represents a respective one of a plurality of computation tasks, any of the nodes which store a respective computation result for at least a threshold period of time as cache nodes. The method further includes allocating, by the hardware processor, the respective computation result of each of the cache nodes into a tenure area of a memory.

Abstract: An anomaly detection system is provided and includes a processor, a memory and a security application stored in the memory and including instructions. The instructions are for collecting behavior data corresponding to users of an organization accessing cloud applications. The behavior data includes parameters tracked over time for the users. The instructions are for: creating a first model based on the behavior data tracked for the users; creating a second model corresponding to a first user based on the parameters tracked for the users except the first user, where the second model excludes behavior data pertaining to the first user; scoring the second model based on the first model to generate a first score; determining whether the first user is an outlier based on the first score; and removing the behavior data corresponding to the first user from the first model if the first user is an outlier.

Abstract: A system may include an access engine to access an input vector as well as a projection matrix. The projection matrix may include a number of rows equal to a number of hash values to generate from the input vector multiplied by the square root of an inverted sparsity parameter specifying a ratio of the hash universe size from which the hash values are generated to the number of hash values to generate. The projection matrix may include a number of columns equal to the dimensionality of the input vector. The system may also include a hash computation engine to determine a projection vector from the projection matrix and the input vector, split the projection vector into a number of sub-vectors equal to the number of hash values to generate, and generate a hash value from each of the sub-vectors.

Abstract: One or more techniques and/or systems are provided for metadata tag evaluation. For example, a metadata tag, associated with content, may be identified (e.g., a hashtag #ML may be used to tag a social network post). A set of characters, within the content, may be evaluated utilizing a probability matrix and the content to identify an expanded metadata tag (e.g., an expanded hashtag “machine learning”). Descriptive content, such as websites, articles, social network posts, and/or other content associated with the expanded metadata tag, may be retrieved. A description for the metadata tag may be generated based upon the descriptive content (e.g., a definition for machine learning). In this way, the description, related metadata tags, and/or supplemental content may be provided to users having an interest in learning about the metadata tag.

Abstract: Implementations disclose livestream conversation notifications. A method includes receiving, via a first user device over a network, a livestream video; presenting, via the first user device to a first user, the livestream video; selecting a second user with whom the livestream video is to be shared, the selecting being based on relevance of content of the livestream video to the second user; and causing a transmission, to a second user device of the second user, of a notification that at least the first user is watching the livestream video.

Abstract: A method includes executing, via a processor, a document-oriented search based on a query in an index of documents to generate a set of document results, each document associated with at least one potential expert. The method includes analyzing the document results to produce a list of potential experts. The method includes calculating an expertise score for each potential expert based on a calculated content score and metadata score for each potential expert. The method includes calculating an evidence diversity score for each potential expert. The method includes calculating a confidence score for each potential expert based on a diversity-constrained content score and a diversity-constrained metadata score for each potential expert. The method includes displaying a list of potential experts with associated confidence scores.

Abstract: Systems, methods and computer-readable media for obtaining and enhancing metadata for content items are provided. In an aspect, a system can include an identification component configured to identify a resource, accessible to the system via a network, that includes a reference to a content item, and an extraction component configured to extract metadata associated with the resource and the reference to the content item. The system can further include an index component configured to associate at least a portion of the metadata with the content item in a data store, and a matching component configured to identify one or more reference content items based on correspondence between the metadata and reference metadata respectively associated with the one or more reference content items.

Abstract: As a user navigates a web site, a system can formulate or allow the user to formulate a query. The system can automatically expand the query to include additional keywords that were not present in the original query. The system can search a database using the expanded query to identify a set of information objects, each having at least one keyword that is present in the expanded query. The database may include a plurality of database tables, each describing a keyword hierarchy. A hierarchy may correspond to a subject matter category addressed by the information object. Another hierarchy may correspond to a project phase addressed by the information object. Still another hierarchy may correspond to the role or intended audience of the information object. The set of information objects thus identified can be displayed on a client computer where the user can see the results.

Abstract: Mention suggestion, and information processing methods and systems are provided, e.g., for social networking. A mention suggestion method comprises: in response to a mention symbol input by a user in a first social network, acquiring a first correspondence between a first user name set and a second user name set, and historical mention information of the user; and suggesting at least one first user name in the first user name set to the user according to the first correspondence and the historical mention information. The information processing method comprises: collecting historical mention information, of a user, on a first social network and another social network, or on another social network; and storing the historical mention information. User names can be suggested more accurately when a user needs to mention a user name, so as to improve an input speed of the user.

Abstract: Methods, systems, and computer program products for ranking data items are described. A ranking configuration is defined for an object type, the ranking configuration comprising an assignment of one or more ranking dimensions to the object type and, for each of the one or more assigned ranking dimensions, one or more corresponding values and a significance weight assigned to each value. Each ranking dimension comprises one or more object attributes and a ranking-impact weight, at least one of the object attributes being a continuous-scales object attribute. A ranking condition is generated for each ranking dimension assigned to the object type. The generation of the ranking condition is based at least in part on the one or more object attributes, a specified ranking-impact weight, the one or more values and associated significance weights, and a distance function corresponding to the continuous-scales object attribute.

Abstract: Various technologies pertaining to exploratory suggestions are described herein. A computer-implemented graph is constructed, where the graph includes nodes that are representative of aspects and edges that are representative of associations between aspects. An aspect is representative of a sub-topic of a topic or a sub-task of a task. The computer-implemented graph is learned based upon content of search logs, and is used to output exploratory suggestions, where a user is exploring a topic or attempting to complete a multi-step task.

Abstract: A method includes receiving a search query from a user device and selecting entity type records from an entity type data store based on the query. Each of the entity type records includes an entity type name and entity type facets that each include terms descriptive of the entity type name. Selecting the entity type records includes identifying matches between the entity type facets and the query. The method includes selecting function records from a function data store based on the query and the entity type names from the selected entity type records. Each of the function records includes an entity type field with entity type names; an access URL template; instructions for completing the access URL template; and function facets with terms descriptive of an application state accessed using the completed access URL. The method includes returning search results including the completed access URLs to the user device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving data identifying contexts; selecting an initial set of questions based at least on the contexts; providing a respective representation of the questions of the initial set, for output; receiving data indicating a selection of a particular representation associated with a particular question of the initial set of questions; selecting a set of answers associated with the particular question; providing a respective representation of the answers of the set that are associated with the particular question, for output; receiving data indicating a selection of a particular representation associated with a particular answer of the set that are associated with the particular question; determining that an additional set of other questions is associated with the particular answer; and in response to the determining, providing a respective representation of the other questions of the additional set, for output.

Abstract: A data streaming environment provides a summary of streaming data from a sensor that is an Internet of things device. An input interface receives the streaming data. A processor is communicatively coupled to the input interface for processing the streaming data. The processed streaming data includes, but is not limited to, a plurality of records and variables that describe a characteristic of a physical object. A computer-readable medium has instructions stored thereon that, when executed by the processor, cause the processor to execute a correlation update application with the received streaming data to provide a correlation between two variables of the streaming data. The non-transitory computer-readable medium further stores sum and bin data for the correlation update application to compute the correlation. The output interface provides the processed streaming data to be visually presented in one or more data graphs on a display device.

Abstract: Technique to determine relative relevance of pairs of nodes in a linked data graph, such as an RDF graph, including calculation of raw relevance scores (which are based upon adjacency relations between nodes after edge filtering, the incoming and outgoing degrees of nodes in the graph after the edge filtering, and the distance (or weight) values of the edge(s)) and/or “refined relevance scores,” which take into account “complementary nodes.

Abstract: Methods, systems, and computer program products for ranking data items are described. In accordance with various example embodiments, a ranking configuration is defined for an object type, the ranking configuration comprising an assignment of one or more ranking dimensions each comprising one or more object attributes to the object type and, for each of the one or more assigned ranking dimensions, one or more corresponding values and a significance weight assigned to each value, at least one of values being a dynamic value corresponding to the context-based object attribute. A ranking condition is generated for each ranking dimension assigned to the object type. The generation of the ranking condition is based at least in part on one or more object attributes, a specified ranking-impact weight, a context value corresponding to the context-based object attribute, and the one or more values and associated significance weights.

Abstract: Methods, systems, program products are described to create a social network based on dynamic interests of users and using ad-hoc networking. A user of mobile device can identify another user who is close by and has similar interests. Dynamic interests of the users can be extracted or identified based on mobile usage, browsing history, places traveled, and other user actions. Users are notified if another user who is similar more than a threshold is present nearby. The system also facilitates communication between users by way of chatting, file sharing, image sharing etc.

Abstract: A system, method and computer program product for evaluating a user's database (db) design schema and definitions syntax and generating a database score according to applied decision tree logic. The database design syntax is automatically evaluated and decision tree logic is applied to determine a context of the database design object and associated syntax and definitions statements. As a result of the automated evaluation, users may then obtain, via a user interface device, a detailed context information associated with their design to assist them in understanding how their database score was derived. By using this detailed contextual information, users analyze the results and can understand what changes can be made to improve their definitions Database Score. The system and method increases the ability of the user to create better database definitions by learning and improving using the contextual data returned.