DETECTING SOCIAL RELATIONSHIPS FROM USER ACTIVITY LOGS

• US 20170323002A1
• Filed: 05/03/2016
• Published: 11/09/2017
• Est. Priority Date: 05/03/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Singh, Shiv Nandan, Saura, Jose D., Oren, Gilad
• Granted Patent: US 10,540,374 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/24568 Data stream processing; Continuous queries
• CPC Class Codes: G06F 16/2477 Temporal data queries
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Social relationships are detected between a plurality of users. A set of user activity logs is input, where these logs originate from one or more network services and cover a prescribed period of time. Each of the logs originates from a particular one of the services and includes a structured data stream that records each interaction that each of one or more of the users has with the particular one of the services. This structured data stream includes a timestamp specifying when this interaction occurred, and a public network identifier specifying a network address from which this interaction occurred. The set of user activity logs is then analyzed to detect a prescribed kind of social relationship between the users. A data structure is then generated that identifies the users between whom the prescribed kind of social relationship is detected, and the data structure is output.

Claims

1. A system for detecting social relationships between a plurality of users, comprising:

a social relationship detector comprising one or more computing devices, said computing devices being in communication with each other via a computer network whenever there is a plurality of computing devices, and a computer program having a plurality of sub-programs executable by said computing devices, wherein the sub-programs configure said computing devices to,

input a set of user activity logs, the set of user activity logs originating from one or more network services and covering a prescribed period of time, 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 one or more of the 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 occurred,

analyze the set of user activity logs to detect a prescribed kind of social relationship between the users,

generate a data structure that identifies the users between whom the prescribed kind of social relationship is detected, and

output the data structure.

2. The system of claim 1, wherein the set of user activity logs originates from a single prevalent network service that is routinely utilized by a large number of users.

3. The system of claim 1, wherein the set of user activity logs originates from a plurality of network services, and said structured data stream further comprises a universal user identifier that uniquely and anonymously identifies a particular one of the users who initiated said interaction, said universal user identifier being used to uniquely and anonymously identify said particular one of the users across each of the network services that said particular one of the users interacts with.

4. The system of claim 1, wherein whenever a particular one of the users utilizes a plurality of end-user computing devices to interact with the particular one of the network services, said structured data stream further comprises a universal user identifier that uniquely and anonymously identifies the particular one of the users across each of the end-user computing devices.

5. The system of claim 1, wherein the network address comprises an Internet Protocol (IP) address.

6. The system of claim 5, wherein the public network identifier comprises a Service Set Identifier (SSID) that identifies a Wi-Fi local area network from which said interaction occurred, and the sub-programs of the computer program further configure said computing devices to utilize the SSID to correlate a cluster of users between whom the prescribed kind of social relationship is detected across different IP addresses that are associated with said cluster.

7. The system of claim 1, wherein the sub-programs of the computer program further configure said computing devices to perform one or more of the actions of:

employing the data structure to build a social network that includes the users between whom the prescribed kind of social relationship is detected;

or

employing the data structure to allow one of the users between whom the prescribed kind of social relationship is detected to play a multiplayer game with one or more others of said users;

or

employing the data structure to recommend media to one of the users between whom the prescribed kind of social relationship is detected based on the media preferences of one or more others of said users;

or

employing the data structure to associate the purchasing habits of one of the users between whom the prescribed kind of social relationship is detected with one or more others of said users.

8. The system of claim 1, wherein the prescribed kind of social relationship comprises a family relationship, the prescribed period of time comprises a prescribed number N1 of consecutive days, and the sub-program for analyzing the set of user activity logs to detect a prescribed kind of social relationship between the users comprises a sub-program for using a variety of clustering factors to recursively cluster the users represented in the set of user activity logs, said clustering factors comprising a prescribed evening time frame TF1, a prescribed maximum number N2 of different users whose interactions with the network services originated from the same public network identifier, and a prescribed social relationship strength threshold T1.

9. The system of claim 8, wherein the prescribed number N1 is 90, the prescribed evening time frame TF1 is between 8:

00 PM and 6;

00 AM, the prescribed maximum number N2 is 20, and the prescribed social relationship strength threshold T1 is 30.

10. The system of claim 1, wherein the prescribed kind of social relationship comprises a friends relationship, the prescribed period of time comprises a prescribed number N3 of consecutive days, and the sub-program for analyzing the set of user activity logs to detect a prescribed kind of social relationship between the users comprises a sub-program for using a variety of clustering factors to recursively cluster the users represented in the set of user activity logs, said clustering factors comprising a prescribed holiday time frame TF2, a prescribed non-holiday time frame TF3, a prescribed maximum number N4 of different users whose interactions with the network services originated from the same public network identifier, and a prescribed social relationship strength threshold T2.

11. The system of claim 10, wherein the prescribed number N3 is 90, the prescribed holiday time frame TF2 is between 10:

00 AM and 8;

00 PM, the prescribed non-holiday time frame TF3 is between 5;

00 PM and 8;

00 PM, the prescribed maximum number N4 is 20, and the prescribed social relationship strength threshold T2 is 10.

12. The system of claim 1, wherein the prescribed kind of social relationship comprises a colleagues relationship, the prescribed period of time comprises a prescribed number N5 of consecutive days, and the sub-program for analyzing the set of user activity logs to detect a prescribed kind of social relationship between the users comprises a sub-program for using a variety of clustering factors to recursively cluster the users represented in the set of user activity logs, said clustering factors comprising a prescribed non-holiday time frame TF4, a prescribed maximum number N6 of different users whose interactions with the network services originated from the same public network identifier, and a prescribed social relationship strength threshold T3.

13. The system of claim 12, wherein the prescribed number N5 is 90, the prescribed non-holiday time frame TF4 is between 10:

00 AM and 4;

00 PM, the prescribed maximum number N6 is 50, and the prescribed social relationship strength threshold T3 is 20.

14. The system of claim 12, wherein the network address comprises a static Internet Protocol (IP) address, and the sub-programs of the computer program further configure said computing devices to utilize a static IP address registry to determine which organization owns one or more static IP addresses that are associated with the users between whom the colleagues relationship is detected.

15. The system of claim 1, wherein the sub-programs of the computer program further configure said computing devices to utilize demographic data about the users between whom the prescribed kind of social relationship is detected to determine a deeper relationship amongst said users.

16. The system of claim 15, wherein the prescribed kind of social relationship comprises a family relationship, the demographic data about the users comprises age and gender data, and the deeper relationship comprises one of said users being one of a head-of-household, or a husband, or a wife.

17. The system of claim 1, wherein said structured data stream further comprises geographic location data specifying a geographic location from which said interaction occurred, and the sub-programs of the computer program further configure said computing devices to utilize said geographic location data to determine a deeper relationship amongst the users between whom the prescribed kind of social relationship is detected.

18. The system of claim 17, wherein the prescribed kind of social relationship comprises a colleagues relationship, and the deeper relationship comprises which of said users works at a particular geographic location.

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

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 and covering a prescribed period of time, 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 one or more of the 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 occurred,

analyzing the set of user activity logs to detect a prescribed kind of social relationship between the users,

generating a data structure that identifies the users between whom the prescribed kind of social relationship is detected, and

outputting the data structure.

20. 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 and covering a prescribed period of time, 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 one or more of the 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 occurred,

analyzing the set of user activity logs to detect a prescribed kind of social relationship between the users,

generating a data structure that identifies the users between whom the prescribed kind of social relationship is detected, and

outputting the data structure.