Detecting social relationships from user activity logs

A computer-implemented process for detecting social relationships between a plurality of users, the process comprising:

• using one or more computing devices to perform the following process actions, the computing devices being in communication with each other via a computer network whenever a plurality of computing devices is used:
• inputting a set of user activity logs, the set of user activity logs originating from one or more network services, each of the user activity logs originating from a particular one of the network services and comprising a structured data stream that records each interaction that each of the plurality of users has with the particular one of the network services, said structured data stream comprising,
• a timestamp specifying when said interaction occurred, and
• a public network identifier specifying a network address from which said interaction by a respective user of the plurality of users occurred at the timestamp at a client end of a communications network with respect to the particular one of the network services at a service end of the communications network,
• analyzing the set of user activity logs to detect a prescribed kind of social relationship between the users by correlating a cluster of two or more of the users interacting with the one or more network services over a same period of time based on the public network identifier and the timestamp of respective interactions specified by the set of user activity logs,
• generating a data structure that identifies the users between whom the prescribed kind of social relationship is detected, and
• outputting the data structure.

A computer-readable storage medium having computer-executable instructions stored thereon that, responsive to execution by a computing device, cause the computing device to detect social relationships between a plurality of users, said detection comprising:

• inputting a set of user activity logs, the set of user activity logs originating from one or more network services, each of the user activity logs originating from a particular one of the network services and comprising a structured data stream that records each interaction that each of the plurality of users has with the particular one of the network services, said structured data stream comprising,
• a timestamp specifying when said interaction occurred, and
• a public network identifier specifying a network address from which said interaction by a respective user of the plurality of users occurred at the timestamp at a client end of a communications network with respect to the particular one of the network services at a service end of the communications network,
• analyzing the set of user activity logs to detect a prescribed kind of social relationship between the users by correlating a cluster of two or more of the users interacting with the one or more network services over a same period of time based on the public network identifier and the timestamp of respective interactions specified by the set of user activity logs,
• generating a data structure that identifies the users between whom the prescribed kind of social relationship is detected, and
• outputting the data structure.