Abstract: The present disclosure relates to forming crowds of users taking into account known physical boundaries. In general, current locations of a number of users are obtained. A crowd of users is then formed based on the current locations of the users while taking into account one or more known physical boundaries such that the crowd does not include spatially proximate users on opposite sides of the one or more known physical boundaries. By utilizing known physical boundaries in a spatial crowd formation process, users that are spatially proximate to one another but are separated by a physical boundary are not included in the same crowd. In this manner, the spatial crowd formation process provides accurate and meaningful crowd formation in environments such as, but not limited to, buildings with multiple rooms, shopping malls, or the like.

Abstract: Systems and methods are disclosed for creating social connections. In general, a current crowd of a first user is monitored to detect if the current crowd matches an active interest of the first user. If the current crowd matches the active interest, a beacon is narrowcast to mobile devices of at least a subset of a number of other users in the current crowd of the first user. In one embodiment, the beacon is narrowcast to mobile devices of all of the other users in the current crowd. In another embodiment, the beacon is narrowcast to the mobile devices of only those other users having user profiles that include interests that match the active interest of the first user. Subsequently, a response to the beacon is received from a mobile device of a second user, and a new social connection is created between the first and second users.

Abstract: A system and method for predicting a future location of a user are provided. In general, a prediction basis including crowd data describing crowds in which a user was included during a number of reoccurring time windows is generated. Each reoccurring time window may be, for example, a day of the week (i.e., Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, or Sunday), a portion of a day of the week (e.g., Monday Morning, Monday Afternoon, Monday Evening, Tuesday Evening, etc.), a day of the month (e.g., 1st day of the month), a day of the year (e.g., March 25th), or the like. The prediction basis of the user is then used to predict one or more future locations of the user.

Abstract: Systems and methods are provided for preventing indirect user tracking in a mobile aggregate profiling system. In general, access to aggregate profile data for groups of users is controlled in a mobile aggregate profiling system based on rate of change values for one or more characteristics, such as population, of the groups of users.

Abstract: Systems and methods are disclosed for providing social crowd data for a number of social locations. In one embodiment, a social browsing system processes social crowd requests using social locations collected for users over time. In one embodiment, upon receiving a social crowd request, for each of one or more social locations identified for the social crowd request, the social browsing system identifies a social crowd for the social location. Optionally, the social crowds may be filtered. Social crowd data is generated for the social locations based on user profiles of the users in the corresponding social crowds. In one embodiment, the social crowd data is returned to a user device of a requesting user. In another embodiment, the social browsing system visualizes the social crowd data and returns the visualized social crowd data to the user device of the requesting user for presentation to the requesting user.

Abstract: Systems and methods for providing content recommendations to a user based on aggregate profile data of other users that the user is predicted to encounter in the future are disclosed. In general, an aggregate profile is obtained for a predicted encounter of a first user. The aggregate profile is based on user profiles of a number of second users identified for the predicted encounter. In one embodiment, the predicted encounter is a predicted physical encounter. In another embodiment, the predicted encounter is a predicted remote encounter. One or more content recommendations are then obtained for the first user based on the aggregate profile for the predicted encounter. The content recommendation may be, for example, a recommended movie, a recommended television program, a recommended news article, a recommended user-generated video (e.g., a recommended video on YouTube.com), or the like.

Abstract: Systems and methods are disclosed for creating a user profile for a subject user based on historical aggregate profile data for locations at which the subject user was previously located. In one embodiment, one or more location and time period pairs are determined for the subject user. Each location and time period pair defines a previous location of the subject user and a time period during which the subject user was at the previous location. Historical aggregate profile data is obtained for the location and time period pairs. For each location and time period pair, the historical aggregate profile data is generally an aggregation of user profiles of a number of users relevant to the location and time period pair. A user profile for the subject user is then created based on the historical aggregate profile data for the one or more location and time period pairs.

Abstract: Systems and methods are disclosed for tailoring user profiles of users in a mobile aggregate profiling system. In one embodiment, the user profiles of the users in the mobile aggregate profiling system are tailored based on aggregate profile data relevant to current locations of the users. More specifically, in order to tailor the user profile of a user, aggregate profile data is obtained for the current location of the user. The user profile of the user is then filtered based on the aggregate profile data for the current location of the user. In one embodiment, the user profile is filtered at a server of the mobile aggregate profiling system. In another embodiment, the user profile is filtered at a mobile device of the user prior to sending the user profile to a server of the mobile aggregate profiling system.

Abstract: A system and method are provided for automatically performing user actions at a device based on a context of the user device. In one embodiment, user actions taken by a user of a user device and corresponding contexts of the user device at times at which the user actions were taken are monitored to detect context-to-user-action correlations. Each context-to-user-action correlation defines a context of the user device and a user action historically taken by the user of the user device for when the device is in that context. Subsequently, a current context of the user device is obtained and compared to the stored context-to-user-action correlations to identify a matching context-to-user-action correlation. The user device then automatically performs the user action that is correlated to the current context as defined by the matching context-to-user-action correlation.

Abstract: Systems and methods are disclosed for anonymously comparing user groups, such as but not limited to crowds, to determine a degree of user overlap. In general, a hash value is obtained for a first user group, where the hash value includes a hash value component for a number of two-user permutations within the first user group. Similarly, a hash value is obtained for a second user group, where the hash value includes a hash value component for a number of two-user permutations within the second user group. Thereafter, a degree of user overlap between the first and second user groups is determined based on a comparison of the hash value for the first user group and the hash value for the second user group.

Abstract: Systems and methods are provided for augmenting a user profile of a subject user. In general, the user profile of the subject user is augmented based on aggregate profile data for a group of users relevant to a current location of the subject user. In one embodiment, the group of users is a crowd of users currently located at a location that is relevant to the current location of the subject user. In another embodiment, the group of users is a number of users historically, or previously, located at locations relevant to the current location of the subject user.

Abstract: Systems and methods are disclosed for providing private location tracking. In general, a location-aware mobile device includes a location broker. Over time, as a location of the mobile device changes, the location broker generates a number of route fragments each defining the location of the mobile device over a corresponding period of time. The location broker obfuscates the route fragments and sends the obfuscated route fragments to a remote server for storage. At some point, the location broker receives a location tracking request from a requestor. In response, the location broker processes the location tracking request such that one or more obfuscated route fragments that are relevant to the location tracking request are obtained from the remote server and de-obfuscated to recover the corresponding route fragments. The recovered route fragments may then be utilized by the requestor.

Abstract: Systems and methods are disclosed for providing automated social routing. In general, a starting point and a stopping point are obtained from a requesting user. A desired number of recommended routes from the starting point to the stopping point are then programmatically generated for the requesting user by dynamically selecting physical waypoints for the recommended routes based on one or more routing factors including one or more social routing factors.

Abstract: A system and method are provided for creating location-based user networks. In general, a proximity group including a number of users is identified. Each user in the proximity group is within a proximate area of at least one other user in the proximity group and has an area of interest. The areas of interest of the users in the proximity group are aggregated to provide an aggregate area of interest for the proximity group. Other users within the aggregate area of interest are identified as neighbors of each of the users in the proximity group. Once the neighbors are identified, each of the users in the proximity group may use the neighbors as members, or potential members, for a user network.