Abstract: The present disclosure provides a system for intelligently sampling information, such as location, activities, etc. on device. Sampling and uploading of background context is optimized using machine learning, such that battery usage is reduced, and quality of metrics based on the reported information is maintained or improved. A policy is generated based on the machine learning, the policy dictating how scanning and upload rates should change in response to conditions on the device.

Abstract: The present disclosure provides a system for intelligently sampling information, such as location, activities, etc. on device. Sampling and uploading of background context is optimized using machine learning, such that battery usage is reduced, and quality of metrics based on the reported information is maintained or improved. A policy is generated based on the machine learning, the policy dictating how scanning and upload rates should change in response to conditions on the device.

Abstract: The present disclosure provides a system for intelligently sampling information, such as location, activities, etc. on device. Sampling and uploading of background context is optimized using machine learning, such that battery usage is reduced, and quality of metrics based on the reported information is maintained or improved. A policy is generated based on the machine learning, the policy dictating how scanning and upload rates should change in response to conditions on the device.

Abstract: The present disclosure provides a system for intelligently sampling information, such as location, activities, etc. on device. Sampling and uploading of background context is optimized using machine learning, such that battery usage is reduced, and quality of metrics based on the reported information is maintained or improved. A policy is generated based on the machine learning, the policy dictating how scanning and upload rates should change in response to conditions on the device.

Abstract: The technology relates to generating a wireless network access point model for determining locations within an area. In one example, a plurality of scan vectors, each scan vector representing a set of signal strengths for a set of wireless network access point identifiers and being associated with a location within the area at which a mobile device moving through the area measured the set of signal strengths are received. A set of clusters is generated by iterating through a split phase until the number of clusters in the set of clusters equals a maximum number of clusters or there are no bad scan vectors identified. A bad scan vector may include a vector having a vector difference from a center of a cluster to which that vector is assigned is less than a minimum similarity value. The set of cluster is then used to generate the model of the area.

Abstract: The technology relates to generating a wireless network access point model for determining locations within an area. In one example, a plurality of scan vectors, each scan vector representing a set of signal strengths for a set of wireless network access point identifiers and being associated with a location within the area at which a mobile device moving through the area measured the set of signal strengths are received. A set of clusters is generated by iterating through a split phase until the number of clusters in the set of clusters equals a maximum number of clusters or there are no bad scan vectors identified. A bad scan vector may include a vector having a vector difference from a center of a cluster to which that vector is assigned is less than a minimum similarity value. The set of cluster is then used to generate the model of the area.

Abstract: The present disclosure provides a system for intelligently sampling information, such as location, activities, etc. on device. Sampling and uploading of background context is optimized using machine learning, such that battery usage is reduced, and quality of metrics based on the reported information is maintained or improved. A policy is generated based on the machine learning, the policy dictating how scanning and upload rates should change in response to conditions on the device.

Abstract: Systems and methods for determining an improved user location using real world map data and/or sensor data are provided. In one embodiment, the method can include obtaining an initial estimate of a location of a user device and maps information corresponding to a geographic area at least partially surrounding the initial estimate of the location of the user device. The maps information can include one or more physical boundaries located at least in part within the geographic area at least partially surrounding the initial estimate. The method can further include determining a set of permissible areas that can potentially include the user device. The set of permissible areas can be determined based at least in part on the one or more physical boundaries. The method can further include revising the initial estimate to provide a revised estimate for the location of the user device based at least in part on the set of permissible areas.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for recommending content based on context such as location. In one aspect, a method includes receiving data that references a location of a mobile device, selecting, from among multiple, different applications that are available in an online application marketplace, one or more of the applications that are relevant to the location, and providing, by a recommendation server, a recommendation to the mobile device, where the recommendation identifies the one or more applications as applications that the user is likely to be interested in purchasing or downloading.

Abstract: Systems and methods for improving a stability of a displayed user location using location history are provided. In one embodiment, the method can include obtaining a location history of a user device corresponding to the user, and determining one or more predicted locations of the user device based at least in part on an application of a smoothing transformation to the location history. The method can further include determining a location of the user device based at least in part on the predicted locations of the user device, and providing the location of the user device to a display device for display.

Abstract: Systems and methods for improving a stability of a displayed user location using location history are provided. In one embodiment, the method can include obtaining a location history of a user device corresponding to the user, and determining one or more predicted locations of the user device based at least in part on an application of a smoothing transformation to the location history. The method can further include determining a location of the user device based at least in part on the predicted locations of the user device, and providing the location of the user device to a display device for display.

Abstract: Systems and methods for determining semantic travel modes are provided. In one embodiment, a method can include obtaining, by one or more computing devices, a plurality of location reports from a user device. Each of the plurality of location reports can include at least a set of data indicative of an associated location and time. The method can further include obtaining, by the one or more computing devices, one or more geographic signals that comprise a set of data associated with one or more geographic locations. The method can include determining, by the one or more computing devices, a semantic travel mode associated with the user device based at least in part on the plurality of location reports and the one or more geographic signals.

Abstract: Systems and methods for determining semantic travel modes are provided. In one embodiment, a method can include obtaining a plurality of location reports from a user device. Each of the plurality of location reports can include at least a set of data indicative of an associated location and time. The method can further include determining a travel period associated with the user device based on the plurality of location reports. The method can include obtaining one or more personalization signals that include a set of data associated with a semantic travel mode. The method can include determining that the user device is associated with the semantic travel mode during the travel period based at least in part on the plurality of location reports and the one or more personalization signals.

Abstract: Systems and methods for determining semantic place names from one or more location reports received from a user device are provided. High quality visits for a candidate semantic place location from a plurality of previously obtained location reports can be aggregated and used to generate a point cloud for the semantic place location. A high quality visit can correspond to a visit by a device that is determined to be associated with a candidate semantic place location with greater likelihood relative to a plurality of other candidate semantic place locations. Data associated with one or more point clouds can be accessed and used to support determinations of semantic place name for one or more location reports. In example embodiments, the semantic place name can be stored as part of a location history and/or provided for display in a user interface presented on a display device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for recommending content based on context such as location. In one aspect, a method includes receiving data that references a location of a mobile device, selecting, from among multiple, different applications that are available in an online application marketplace, one or more of the applications that are relevant to the location, and providing, by a recommendation server, a recommendation to the mobile device, where the recommendation identifies the one or more applications as applications that the user is likely to be interested in purchasing or downloading.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for recommending content based on context such as location. In one aspect, a method includes receiving data that references a location of a mobile device, selecting, from among multiple, different applications that are available in an online application marketplace, one or more of the applications that are relevant to the location, and providing, by a recommendation server, a recommendation to the mobile device, where the recommendation identifies the one or more applications as applications that the user is likely to be interested in purchasing or downloading.

Abstract: Systems and methods for determining semantic place names from one or more location reports received from a user device are provided. High quality visits for a candidate semantic place location from a plurality of previously obtained location reports can be aggregated and used to generate a point cloud for the semantic place location. A high quality visit can correspond to a visit by a device that is determined to be associated with a candidate semantic place location with greater likelihood relative to a plurality of other candidate semantic place locations. Data associated with one or more point clouds can be accessed and used to support determinations of semantic place name for one or more location reports. In example embodiments, the semantic place name can be stored as part of a location history and/or provided for display in a user interface presented on a display device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for recommending content based on context such as location. In one aspect, a method includes receiving data that references a location of a mobile device, selecting, from among multiple, different applications that are available in an online application marketplace, one or more of the applications that are relevant to the location, and providing, by a recommendation server, a recommendation to the mobile device, where the recommendation identifies the one or more applications as applications that the user is likely to be interested in purchasing or downloading.

Abstract: Methods, systems and apparatus, including computer programs encoded on a computer storage medium, for receiving an application installation log, the application installation log including per-user installation data indicating when each of a plurality of applications available through an application marketplace was installed on a plurality of computing devices, determining an overall score corresponding to a first application and a second application, the score indicating a degree of overlap in installation periods of the first application and the second application on the plurality of computing devices, determining that the overall score is greater than or equal to a threshold score, generating an index, the index associating the second application as an application of interest in view of the first application, and storing the index in computer-readable memory.

Abstract: Methods, systems, apparatus, and computer storage mediums for receiving an initial index, the initial index associating each application of one or more applications with one or more applications of interest; for each application, receiving metadata associated with the application and receiving metadata associated with each of the one or more applications of interest; processing the metadata to selectively remove at least one of the one or more applications of interest from the initial index to provide a final index, the final index associating each application of the one or more applications with a remaining one or more applications of interest; storing the final index in memory; receiving a user selection of a particular application of the one or more applications; retrieving the one or more applications of interest based on the particular application using the final index; and providing the one or more applications of interest for display.