Abstract: In implementations, a divergence from a pattern of detected instances of an event is identified, where the event is of a routine of a user. The identified divergence corresponds to an out of routine event. Contextual information is generated corresponding to the identified out of routine event. Furthermore, one or more recommended actions for presenting content to the user are selected based on the contextual information. An indication of the identified out of routine event, the contextual information, and the one or more recommended actions are provided to a service, which may be an application on a user device. The service can present content to the user based on the identified out of routine event, the generated contextual information corresponding to the identified out of routine event, and the selected one or more recommended actions. The service may follow or disregard any of the selected one or more recommended actions.

Abstract: A playlist generator that utilizes multiple data sources to rank each track within a set of candidate tracks to enable selection of candidate tracks according to the ranking. Candidate tracks are each scored according to one or more features, such as acoustic similarity and/or similar usage patterns of the candidate track or artist of the candidate track to a current or previously played track or artist. Each feature is weighted according to historical listening patterns surrounding a user-selected playlist seed artist. The weighting may also be further corrected according to historical listening patterns of the particular user. When historical usage data related to a particular seed artist is limited, more generalized historical usage data related to a higher level in a genre hierarchy may be used.

Abstract: A playlist generator that utilizes multiple data sources to rank each track within a set of candidate tracks to enable selection of candidate tracks according to the ranking. Candidate tracks are each scored according to one or more features, such as acoustic similarity and/or similar usage patterns of the candidate track or artist of the candidate track to a current or previously played track or artist. Each feature is weighted according to historical listening patterns surrounding a user-selected playlist seed artist. The weighting may also be further corrected according to historical listening patterns of the particular user. When historical usage data related to a particular seed artist is limited, more generalized historical usage data related to a higher level in a genre hierarchy may be used.

Abstract: Embodiments of the disclosure relate to apparatus for recommending items from a catalog of items to users in a population of users, configured to determine values for a measure of association between transactions of users with items in a first catalog and transactions of users with items in a second catalog and provide recommendations to users for transacting with items in the catalogs based on the determined values of association.

Abstract: Event information is provided to a user in response to receiving a request to retrieve event information associated with the event. At least one event occurring at a particular time on a computing device associated with a user is detected and stored as an event record. The event record can include event characteristics, as well as references to files and/or data associated therewith. A request is received, preferably through a personal assistant-type application, to retrieve information associated with the event. The request may include one or more search parameters corresponding to the event characteristics. Based on the request, the event can be located and communicated to the user.

Abstract: Systems, methods, and media for proposing similar applications to a candidate application are provided. A similar results server may surface similar applications to a user of an application store. The applications can be selected based on similarity between features of the application. The features may be extracted from graphical user interface information rendered by a device that executes the applications. The applications that are identified as similar (e.g., based on the features) are displayed to the user.

Abstract: Aspects of the technology described herein can analyze signal data from multiple computing devices to ascertain a user's exercise pattern. Understanding a user's exercise pattern can help reduce power usage by automatically turning physiological sensors on and off to coincide with the start and end of an exercise event. Exemplary computing devices that can provide signal data related to a user's exercise routine can include a mobile computing device (e.g., smart phone) that captures location signals and other contextual data and a wearable computing device (e.g., fitness tracker) that captures physiological characteristics of the user, such as heart rate, temperature, and movement. The signals captured by the multiple computing devices can be analyzed together to determine when an individual exercise event has occurred. The plurality of exercise events associated with a user or group of users can be analyzed to ascertain an exercise pattern.

Abstract: Aspects of the technology described herein provide a mechanism to authenticate a task request received by a personal digital assistant. The authentication mechanism improves security for transactions facilitated by the personal digital assistant. The authentication mechanism can also improve machine and user efficiency by streamlining a transaction process. In one aspect, the request is a verbal request made by a person and received by the personal digital assistant through a microphone. The personal assistant can generate an authentication questions using data from a semantic knowledge base accessible to the personal digital assistant.

Abstract: In implementations, a divergence from a pattern of detected instances of an event is identified, where the event is of a routine of a user. The identified divergence corresponds to an out of routine event. Contextual information is generated corresponding to the identified out of routine event. Furthermore, one or more recommended actions for presenting content to the user are selected based on the contextual information. An indication of the identified out of routine event, the contextual information, and the one or more recommended actions are provided to a service, which may be an application on a user device. The service can present content to the user based on the identified out of routine event, the generated contextual information corresponding to the identified out of routine event, and the selected one or more recommended actions. The service may follow or disregard any of the selected one or more recommended actions.

Abstract: One or more web-behavior-augmented recommendation servers augment catalog interaction data between consumers and a catalog of products with collected online web behavior data associated with individual users. The online web behavior data represents online web behavior of the each consumer outside of the catalog of products and can improve the accuracy of product recommendations, which then be presented to an individual consumer via a computer user interface.

Abstract: Systems, methods, and media for proposing similar applications to a candidate application are provided. A similar results server may surface similar applications to a user of an application store. The applications can be selected based on similarity between features of the application. The features may be extracted from graphical user interface information rendered by a device that executes the applications. The applications that are identified as similar (e.g., based on the features) are displayed to the user.

Abstract: Topical affinity badges in information retrieval is described, for example, where graphical elements are presented together with ranked search results from a search engine, to indicate a degree of association between an author of a document and a topic. In various embodiments, a measure of an author's affinity to a topic is predicted using a machine learning system that takes as input author features derived from documents of the author. In various examples topical affinity scores or labels are used to generate badges and/or to index documents at an index of a search engine. For example, badges may be presented with ranked search results, in pop up displays or in other ways. In examples author features relating to any of recency, frequency and presentation of an author's documents are generated, where presentation features may relate to biographical information such as experience, qualifications, and previous documents.

Abstract: Topical affinity badges in information retrieval is described, for example, where graphical elements are presented together with ranked search results from a search engine, to indicate a degree of association between an author of a document and a topic. In various embodiments, a measure of an author's affinity to a topic is predicted using a machine learning system that takes as input author features derived from documents of the author. In various examples topical affinity scores or labels are used to generate badges and/or to index documents at an index of a search engine. For example, badges may be presented with ranked search results, in pop up displays or in other ways. In examples author features relating to any of recency, frequency and presentation of an author's documents are generated, where presentation features may relate to biographical information such as experience, qualifications, and previous documents.