Abstract: In some examples, systems and techniques can determine a respective visit likelihood for each respective destination of a plurality of destinations based at least in part on a respective distance between the respective destination and a geographic location from a location history associated with a user and a comparison between a time associated with the geographic location and a visit likelihood distribution across time. The systems and techniques can then sort at least some of the plurality of destinations. In other examples, systems and techniques can determine whether a user is likely to visit a place during a future instance of a timeslot based at least in part on a location history associated with the user. The systems and techniques can then output information relating to the place prior to the beginning of the future instance of the timeslot.

Abstract: In some examples, systems and techniques can determine a respective visit likelihood for each respective destination of a plurality of destinations based at least in part on a respective distance between the respective destination and a geographic location from a location history associated with a user and a comparison between a time associated with the geographic location and a visit likelihood distribution across time. The systems and techniques can then sort at least some of the plurality of destinations. In other examples, systems and techniques can determine whether a user is likely to visit a place during a future instance of a timeslot based at least in part on a location history associated with the user. The systems and techniques can then output information relating to the place prior to the beginning of the future instance of the timeslot.

Abstract: The systems and techniques disclosed herein provide the ability to determine locations visited by a user and associate relevant location labels with the locations visited based on contact information. In some examples, a location label can be applied based on a match between a location visited and information stored in a user's contact list. In other examples, a user can efficiently designate a contact and location label to be associated with a location visited. In still other examples, if a location visited by a user is not listed in the user's contact list, but is otherwise known to the system, the location visited can be appropriately labeled and the corresponding contact in the user's contact list can be updated to include the location visited.

Abstract: In one implementation, a computer-implemented method includes obtaining travel information that indicates travel patterns for a mobile computing device that is associated with a user; identifying a current context for the mobile computing device and the user; identifying one or more destination locations that the user has at least a threshold likelihood of travelling to with the mobile computing device based on the current context and the obtained travel information; generating a prediction that one or more events have at least a threshold probability of occurring along one or more of a plurality of routes for travelling to the identified one or more destination locations; selecting a particular route from the plurality of routes to recommend to the user based on the current context and the prediction of the one or more events; and providing route information that identifies the selected particular route.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting context-relevant information based on large-scale aggregations of data. One of the methods includes receiving a user context of a user, wherein the user context specifies a location of a user device being used by the user. Data that represents counts of websites visited by users matching the user context is obtained. Data that represents counts of websites visited by users in general is obtained. Using the obtained counts, one or more likely websites visited by users matching the user context more frequently than by users in general is determined. Information identifying the one or more likely websites in response to receiving the user context is provided.

Abstract: The systems and techniques disclosed herein provide the ability to determine locations visited by a user and associate relevant location labels with the locations visited based on contact information. In some examples, a location label can be applied based on a match between a location visited and information stored in a user's contact list. In other examples, a user can efficiently designate a contact and location label to be associated with a location visited. In still other examples, if a location visited by a user is not listed in the user's contact list, but is otherwise known to the system, the location visited can be appropriately labeled and the corresponding contact in the user's contact list can be updated to include the location visited.

Abstract: Embodiments relate to determining commute routes and clustering commute routes from a user's location history. Points in the user's location history may be clustered to find the user's home and work locations. Additionally, points along the user's commute may be identified to determine the user's typical commute. Similar commutes can be clustered together, and used to suggest various services to the user.

Abstract: Aspects of the technology pertain to geographical image processing of time-dependent imagery. Various assets acquired at different times are stored and processing according to acquisition date in order to generate one or more image tiles for a geographical region of interest. The different image tiles are sorted based on asset acquisition date. Multiple image tiles for the same region of interest may be available. In response to a user request for imagery as of a certain date, one or more image tiles associated with assets from prior to that date are used to generate a time-based geographical image for the user.

Abstract: A computer-implemented method includes: detecting whether a user is watching media content; after detecting that the user is watching media, presenting on a user device a first affordance providing a first user-selectable election to receive information on entities relevant to the media content; in response to user selection of the election: sampling at the user device program information from the media content including one or more of audio signals and subtitles, and sending the program information to a server, which identifies the media content and generates one or more second user-selectable user elections for the identified media content and sends to the user device one or more second affordances providing the second user-selectable elections; displaying the second affordances on the user device; and in response to user selection of one of the second affordances, displaying on the user device information on a respective entity relevant to the media content.

Abstract: A computing system is described that obtains, based at least in part on information included in at least one previous communication associated with a user of a computing device, an indication of a future location and a future time and event information associated with the future location and the future time. The computing system obtains a duration of time for the user to travel from a current location of the computing device to the future location, and, based at least in part on the duration of time, obtains a departure time at which the user is predicted to need to depart from the current location in order to arrive at the future location by an arrival time based on the event. The computing system outputs, for transmission to the computing device, an indication associated with the event and including information indicative of the departure time.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting context-relevant information based on large-scale aggregations of data. One of the methods includes receiving a user context of a user, wherein the user context specifies a location of a user device being used by the user. Data that represents counts of websites visited by users matching the user context is obtained. Data that represents counts of websites visited by users in general is obtained. Using the obtained counts, one or more likely websites visited by users matching the user context more frequently than by users in general is determined. Information identifying the one or more likely websites in response to receiving the user context is provided.

Abstract: Computer-implemented methods for generating and executing user-based standing queries are provided. In one aspect, a method includes determining whether to generate a notification based on a user-based query and geographical context. The method also includes filtering the notification through explicit or inferred filter criteria. Systems and machine-readable media are also provided.

Abstract: A computing system is described that obtains, based at least in part on information included in at least one previous communication associated with a user of a computing device, an indication of a future location and a future time and event information associated with the future location and the future time. The computing system obtains a duration of time for the user to travel from a current location of the computing device to the future location, and, based at least in part on the duration of time, obtains a departure time at which the user is predicted to need to depart from the current location in order to arrive at the future location by an arrival time based on the event. The computing system outputs, for transmission to the computing device, an indication associated with the event and including information indicative of the departure time.

Abstract: The present invention pertains to geographical image processing of time-dependent imagery. Various assets acquired at different times are stored and processing according to acquisition date in order to generate one or more image tiles for a geographical region of interest. The different image tiles are sorted based on asset acquisition date. Multiple image tiles for the same region of interest may be available. In response to a user request for imagery as of a certain date, one or more image tiles associated with assets from prior to that date are used to generate a time-based geographical image for the user.

Abstract: A computing system is described that determines, based on a location history, a content-viewing location associated with a user of a mobile computing device and identifies a media output device located at the content-viewing location. Responsive to determining that the mobile computing device is located at the content-viewing location and in proximity to the media output device at a current time, the computing system determines, based on a plurality of features of the media output device, various media recommendations for the user at the current time. The plurality of features include an indication of whether the media output device is operating in an on state at the current time. The computing system outputs, for transmission to the mobile computing device, an indication of the various media recommendations.

Abstract: Methods, systems, and computer program products are provided for providing aggregated starting point information. One example method includes identifying a location associated with an entity, identifying, from navigation information query logs, starting points for navigation information that includes an ending point in a predefined vicinity of the location associated with the entity, aggregating information associated with the starting points, and providing aggregated starting point information to the entity.

Abstract: In some examples, systems and techniques can determine a respective visit likelihood for each respective destination of a plurality of destinations based at least in part on a respective distance between the respective destination and a geographic location from a location history associated with a user and a comparison between a time associated with the geographic location and a visit likelihood distribution across time. The systems and techniques can then sort at least some of the plurality of destinations. In other examples, systems and techniques can determine whether a user is likely to visit a place during a future instance of a timeslot based at least in part on a location history associated with the user. The systems and techniques can then output information relating to the place prior to the beginning of the future instance of the timeslot.

Abstract: In one example, a method includes determining, based on first motion data, that a change in an angle of a mobile computing device relative to gravity satisfies a threshold amount of change, and, responsive to determining that the change in the angle satisfies the threshold amount of change, initiating, at a first position of the mobile computing device, storage of second motion data, wherein the first position is a reference position. The method may also include determining, based on an external signal, a second position of the mobile computing device, wherein the second position is a current position of the mobile computing device that is different from the reference position, and, responsive to determining the second position of the mobile computing device, determining, based on the second motion data and the current position, the reference position of the mobile computing device.

Abstract: A computing system extracts, based on one or more electronic messages sent or received by a user of a mobile computing device, travel plan information associated with the user of the mobile computing device. The travel plan information may indicate a destination to which the user is planning to travel. In response to extracting the travel plan information, the computing system may send an instruction to the mobile computing device to cache, in advance of the user arriving at the destination, information associated with the destination. In this way, the mobile computing device may access the information associated with the destination while at the destination, even if the mobile computing device is unable to access the information via a wireless communication channel.

Abstract: In some examples, systems and techniques can determine a respective visit likelihood for each respective destination of a plurality of destinations based at least in part on a respective distance between the respective destination and a geographic location from a location history associated with a user and a comparison between a time associated with the geographic location and a visit likelihood distribution across time. The systems and techniques can then sort at least some of the plurality of destinations. In other examples, systems and techniques can determine whether a user is likely to visit a place during a future instance of a timeslot based at least in part on a location history associated with the user. The systems and techniques can then output information relating to the place prior to the beginning of the future instance of the timeslot.