Systems and methods for content provisioning are disclosed herein. The system can include memory having a content database, a task database, and a user profile database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: receive a user identifier from the user device; retrieve user information from the user profile database, which user information identifies one or several attributes of the user; retrieve user task data from the task database, which user task data identifies a plurality of tasks for completion by the user; automatically generate prioritization data for the plurality of tasks identified by the user task data; select a task based on the prioritization data; and send content relating to the selected task to the user device.

A document creation apparatus includes a processor configured to: acquire information about a person; estimate a topic of interest to the person, based on the acquired information; acquire one or more articles related to the estimated topic; and create a document by using the acquired one or more articles.

A computer-based system for presenting interpersonal relationship recommendation that utilizes peer based opinions about a potential match to influence the recommendation, and that presents the peer based opinions along with the recommendation.

According to an aspect, a pair of related entities that includes a first entity and a second entity is received. Distributional relations are detected between the first entity and the second entity. The detecting includes identifying two sets of entities in a corpus, the first set including the first entity and at least one other entity that is semantically similar to the first entity, and the second set including the second entity and at least one other entity that is semantically similar to the second entity. Semantic relations are detected between entities in the first set and entities in the second set. A relation classifier is trained using the pair of related entities and detected semantic relations. The relation classifier model is applied to a new pair of entities to determine a likelihood of a semantic relation between the entities in the new pair of entities.

Identifying impressions relating to a target publisher that are related to or derived from a user interaction with a content recommendation source. User activity data for multiple users is collected during an activity window. Based on the collected user activity data, an initial interaction by a user with a source is identified and used to establish a source-related user session beginning at a time of the initial interaction and ending after a session period. A set of impressions (e.g., page views) by the user relating to the target publisher occurring during the user session is identified. The identified set of impressions is associated with the user session. A source-related user activity measurement is calculated based on the identified user sessions and associated impressions occurring during the activity window.

A system for data aggregation and analytical scoring is described that includes a gateway operable to aggregate data received from multiple remote devices, and a device history data model storing properties for each of the multiple remote devices and storing the data received from each remote device. A scoring engine in the system acts to aggregate and analyze the data stored in the device history data model and to produce a metric based on the data. The system also includes a notification policy to conditionally notify a user based on the metric produced by the scoring engine.

Systems and methods of identifying entities are disclosed. In particular, one or more images that depict an entity can be identified from a plurality of images. One or more candidate entity profiles can be determined from an entity directory based at least in part on the one or more images that depict the entity. The one or more images that depict the entity and the one or more candidate entity profiles can be provided as input to a machine learning model. One or more outputs of the machine learning model can be generated. Each output can include a match score associated with an image that depicts the entity and at least one candidate entity profile. The entity directory can be updated based at least in part on the one or more generated outputs of the machine learning model.

Architecture that enables the creation and utilization of a user location profile for a personalized search experience in recommendation systems. The user location profile does not necessitate login of the user to obtain user profile information such as a user ID. Rather, the identifying information associated with the user location can be a network address and/or a device identifier that identifies the particular device from which the user is performing a search or which auto-suggest is being initiated. The user location profile can then be used to identify items about which the user may want information. Once generated, a matching operation is performed between the user location profile and item profiles in a log. The matched item profiles related to the user's location information (the user physical location and/or or user interested location(s)) are identified and recommended to the user.

Techniques for designing an awareness engine that organizes and serves popularly discussed and viral online content in response to user search queries. In an aspect, quality online content is identified by analyzing posts by users of a social network over specific time periods. For each item of quality online content identified, a virality score is calculated, and a social signature is constructed. The social signature can be constructed from the content itself, as well as from posts referencing the content. Based on this processing, relevant quality online content having the highest virality scores may be retrieved and served in response to user queries. Further techniques are provided for designing a user interface for the awareness engine.

Systems and methods are disclosed that identify users of a media distribution system that tend to consume popular media items prior to such media items gaining popularity. For example, a set of early adopters may be identified that tend to listen to music associated with particular artists before such artists become popular. The systems and methods disclosed may also utilize identified early adopters to determine relatively obscure or unpopular media items (or creators thereof) that are likely to become popular in the future. Illustratively, an obscure artist whose content is commonly consumed by early adopters can be identified as potentially achieving widespread popularity in the future. These media items predicted to become popular or media item creators may then be recommended to other users of the media distribution system.