Abstract: In some implementations, a device may receive historical content data indicating historical characteristics associated with one or more groups of content. The device may determine, based on the historical content data, one or more characteristics associated with a time period. The device may determine, based on the one or more characteristics, a new group of content associated with the time period. The device may generate a display element for accessing content included in the new group of content during the time period.

Abstract: A method, a device, and a non-transitory storage medium are described in which a rehearsal network service is provided that enables generalized learning for all types of input patterns ranging from one-shot inputs to a large set of inputs. The rehearsal network service includes using biological memory indicator data relating to a user and the input data. The rehearsal network service includes calculating a normalized effective salience for each input data, and generating a new set of input data in which the inclusion of input data is proportional to its normalization effective salience. The rehearsal network service provides the new set of input data to a learning network, such as a neural network or a deep learning network that can learn the user's taste or preference.

Abstract: In some implementations, a device may receive historical content data indicating historical characteristics associated with one or more groups of content. The device may determine, based on the historical content data, one or more characteristics associated with a time period. The device may determine, based on the one or more characteristics, a new group of content associated with the time period. The device may generate a display element for accessing content included in the new group of content during the time period.

Abstract: Disclosed is a system for generating personalized recommendations based on dynamic and customized content selections and modeling of the content selections. The system may receive a request with an identifier and a query, and may obtain a particular recommendation configuration based the identifier and the query. The system may retrieve a set of content that satisfies the query and that is identified with at least one content prioritization parameter specified in the particular recommendation configuration, may generate a set of models of one or more model types that model relevance between the set of content and a different event specified in the particular recommendation configuration, and may compute a score for each content in each model based on the modeled relevance. The system may present recommended content in a different order than the set of content based on aggregate scores compiled for each content from the set of models.

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: A device may receive content data, a first model, and a second model. The first model may be trained on different types of metadata than the second model. The content data may include a first identifier of a first content item and a first set of metadata associated with the first content item. The device may process the first set of metadata to generate first recommendations from the first model and second recommendations from the second model. The device may provide the first identifier and a combination of the first recommendations and the second recommendations to client devices. The device may receive, from the client devices, user-generated target recommendations based on the combination. The device may process the user-generated target recommendations, the first recommendations, and the second recommendations, to provide feedback to update the first model and the second model.

Abstract: A method, a device, and a non-transitory storage medium are described, which provide a natural language-based content system with corrective feedback and training service. The natural language-based content system with corrective feedback and training service may collect data based on interaction with search results from users. The natural language understanding model may generate feedback data based on the collected data, and use the feedback data to further train the natural language understanding model and update search and discovery logic for searching and discovering contents. The feedback data may categorize errors based on the interaction, and identify differences between search queries received during a search session with a user.

Abstract: A method, a device, and a non-transitory storage medium are described, which provide for calculating a first relevance score for each content item of a set of content items, wherein the first relevance scores correspond to a relevance of each content item with respect to a query term according to a term-weighting scheme; calculating, for each content item, a program title relevance score; a media personality relevance score; a media network relevance score; and a live programming event relevance score; ranking each content item based on the program title relevance scores, the media personality relevance scores, the media network relevance scores, and the live event relevance scores; receiving a user input search term; generating, based on the search term, a user interface including multiple graphic icons corresponding to a number of the ranked content items; and presenting, via the user interface, the multiple graphic icons for selection by a user.

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: Disclosed are systems and methods for art 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: Disclosed is a system for generating personalized recommendations based on dynamic and customized content selections and modeling of the content selections. The system may receive a request with an identifier and a query, and may obtain a particular recommendation configuration based the identifier and the query. The system may retrieve a set of content that satisfies the query and that is identified with at least one content prioritization parameter specified in the particular recommendation configuration, may generate a set of models of one or more model types that model relevance between the set of content and a different event specified in the particular recommendation configuration, and may compute a score for each content in each model based on the modeled relevance. The system may present recommended content in a different order than the set of content based on aggregate scores compiled for each content from the set of models.

Abstract: A method, a device, and a non-transitory storage medium are described, which provide a natural language-based content search and discovery service. The natural language-based content search and discovery service may use query object types as a basis for interpreting a vocalized search query from a user. The natural language-based content search and discovery service may use a multi-interpretative procedure that includes use of a probabilistic grammar parser, parts of speech, and query object type identification that are configured for a media domain. The natural language-based content search and discovery service may merge different interpretations of the search query based on probability values associated with each interpretation.

Abstract: A device may receive content data, a first model, and a second model. The first model may be trained on different types of metadata than the second model. The content data may include a first identifier of a first content item and a first set of metadata associated with the first content item. The device may process the first set of metadata to generate first recommendations from the first model and second recommendations from the second model. The device may provide the first identifier and a combination of the first recommendations and the second recommendations to client devices. The device may receive, from the client devices, user-generated target recommendations based on the combination. The device may process the user-generated target recommendations, the first recommendations, and the second recommendations, to provide feedback to update the first model and the second model.

Abstract: Systems and methods for scoring popularity of entities in a social network are disclosed herein. An exemplary system assigns popularity scores to a plurality of entities in a social network, the popularity scores including a first popularity score assigned to a first entity of the plurality of entities and a second popularity score assigned to a second entity of the plurality of entities, and adjusts, in response to an operation in the social network, the second popularity score based on the first popularity score. In certain examples, the system also adjusts, in response to the operation in the social network, the first popularity score based on the first popularity score at the time of the operation.

Abstract: A method, a device, and a non-transitory storage medium are described in which a rehearsal network service is provided that enables generalized learning for all types of input patterns ranging from one-shot inputs to a large set of inputs. The rehearsal network service includes using biological memory indicator data relating to a user and the input data. The rehearsal network service includes calculating a normalized effective salience for each input data, and generating a new set of input data in which the inclusion of input data is proportional to its normalization effective salience. The rehearsal network service provides the new set of input data to a learning network, such as a neural network or a deep learning network that can learn the user's taste or preference.

Abstract: A device may receive content data, a first model, and a second model. The first model may be trained on different types of metadata than the second model. The content data may include a first identifier of a first content item and a first set of metadata associated with the first content item. The device may process the first set of metadata to generate first recommendations from the first model and second recommendations from the second model. The device may provide the first identifier and a combination of the first recommendations and the second recommendations to client devices. The device may receive, from the client devices, user-generated target recommendations based on the combination. The device may process the user-generated target recommendations, the first recommendations, and the second recommendations, to provide feedback to update the first model and the second model.

Abstract: A method, a device, and a non-transitory storage medium are described in which a priming-based search and discovery service for contents uses a data structure that stores metadata pertaining to the contents, activation values, threshold values, and a distance parameter that limits the search space relative to primed nodes that are relevant to search terms.

Abstract: A computing device may include a memory configured to store instructions and a processor configured to execute the instructions to receive a selection of a content catalog item or a search query from a user; generate an input vector based on the selected content catalog item or the search query; and map the generated input vector onto one or more points on a self-organizing map associated with the user. The processor may be further configured to select a set of points within a particular distance of the one or more points; reverse map the selected set of points to a plurality of content catalog items using the self-organizing map associated with the user; and present one or more of the plurality of content catalog items to the user as recommended content catalog items for the user.

Abstract: A method, a device, and a non-transitory storage medium are described in which a rehearsal network service is provided that enables generalized learning for all types of input patterns ranging from one-shot inputs to a large set of inputs. The rehearsal network service includes using biological memory indicator data relating to a user and the input data. The rehearsal network service includes calculating a normalized effective salience for each input data, and generating a new set of input data in which the inclusion of input data is proportional to its normalization effective salience. The rehearsal network service further includes augmenting the new set of input data using perturbation values. The rehearsal network service provides the new set of input data to a learning network, such as a neural network or a deep learning network that can learn the user's taste or preference.

Abstract: A method, a device, and a non-transitory storage medium for determining, based on media content selection activity of a user for a media content inventory, the user's sensitivity to a cost and to a relevance of the media content; assigning a cost value to respective media content items based on user-specific content cost information from media content providers; assigning a relevance value to the respective media content items based on user-specific content relevancy information associated with the respective media content items; ranking the media content items based on: the user's sensitivity to the cost of the media content relative to the cost values for the respective media content items, and the user's sensitivity to the relevance of the media content relative to the relevance values for the respective media content items; and presenting, via a personalized media content recommendation interface, an ordering of the media content items based on the ranking.