SUGGESTED OUT OF NETWORK COMMUNICATION RECIPIENTS

• US 20140195549A1
• Filed: 02/21/2013
• Published: 07/10/2014
• Est. Priority Date: 01/07/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Junghoon Ahn
• Inventors: Gupta, Abhishek, Posse, Christian, Bhasin, Anmol, Ahn, Junghoon, Shi, Yurong, Li, Jian, Kessler, Jacob
• Granted Patent: US 8,972,417 B2
• Time in Patent Office: Days
• US Class Current: 707/749
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Disclosed in some examples are methods, systems and machine readable medium for recommending an out-of-network communication by determining a set of potential recommended members of a social networking service based upon one or more recommendation criteria. In some examples the recommendation criteria may include: a profile similarity to a previous target of an out-of-network communication, a degree of correspondence between an interest and intent of the sending member, and a likelihood of response.

Claims

1. A method for recommending an out-of-network communication recipient, the method comprising:

determining a set of potential recommended members of a social networking service;

determining for each particular member in the set of potential recommended members;

a profile similarity score, the profile similarity score indicating a measure of how similar the particular member is to a previous target member of an out-of-network communication of a sending member; and

a recommendation criteria score, the recommendation criteria score being a measure of how closely the particular member matches a recommendation criteria;

determining a set of recommended members from the set of potential recommended members based upon the profile similarity scores and the recommendation criteria scores of the members in the set of potential recommended members;

presenting the set of recommended members to the sending member; and

sending an out-of-network communication to a selected member of the set of recommended member from the sending member.

2. The method of claim 1, wherein the set of potential recommended members is all the members of the social networking service.

3. The method of claim 1, wherein the profile similarity score is determined based upon the member profile attributes that the particular member has in common with the previous target member.

4. The method of claim 1, wherein the recommendation criteria is an interest, and the recommendation criteria score is determined based upon how closely a determined interest of the particular member corresponds to a determined interest of the sending member.

5. The method of claim 1, wherein the recommendation criteria is an intent, and the recommendation criteria score is determined based upon how closely a determined intent of the particular member corresponds to a determined intent of the sending member.

6. The method of claim 5, further comprising a second recommendation criteria, the second recommendation criteria is an interest, and the recommendation criteria score is determined based upon how closely a determined interest of the particular member corresponds to a determined interest of the sending member, and the set of recommended members is determined also based upon the second recommendation criteria.

7. The method of claim 1, wherein the members in the set of recommended members are determined from the set of potential recommended members based upon their profile similarities scores being above a first predetermined threshold and their recommendation criteria scores being above a second predetermined threshold.

8. The method of claim 1, further comprising:

for each recommended member calculating a recommendation score based upon the profile similarities score and the recommendation criteria scores, and determining a set of recommended members comprises selecting the members in the potential recommended member set whose recommendation score exceeds a predetermined threshold.

9. The method of claim 1, wherein the recommendation criteria is a response likelihood to an out-of-network message, and the recommendation criteria score is determined based upon how likely the particular member is to respond to the out-of-network communication.

10. A system for recommending an out-of-network communication recipient, the system comprising:

a recommendation module, operating on one or more computer processors, and configured to;

determine a set of potential recommended members of a social networking service;

determine for each particular member in the set of potential recommended members;

a profile similarity score, the profile similarity score indicating a measure of how similar the particular member is to a previous target member of an out-of-network communication of a sending member; and

a recommendation criteria score, the recommendation criteria score being a measure of how closely the particular member matches a recommendation criteria;

determine a set of recommended members from the set of potential recommended members based upon the profile similarity scores and the recommendation criteria scores of the members in the set of potential recommended members; and

a presentation module, configured to;

present the set of recommended members to the sending member; and

send an out-of-network communication to a selected member of the set of recommended member from the sending member.

11. The system of claim 10, wherein the set of potential recommended members is all the members of the social networking service.

12. The system of claim 10, wherein the recommendation module is configured to determine the profile similarity score based upon the member profile attributes that the particular member has in common with the previous target member.

13. The system of claim 10, wherein the recommendation criteria is an interest, and the recommendation module is configured to determine the recommendation criteria score based upon how closely a determined interest of the particular member corresponds to a determined interest of the sending member.

14. The system of claim 10, wherein the recommendation criteria is an intent, and the recommendation module is configured to determine the recommendation criteria score based upon how closely a determined intent of the particular member corresponds to a determined intent of the sending member.

15. The system of claim 14, further comprising a second recommendation criteria, the second recommendation criteria is an interest, and the recommendation module is configured to determine the recommendation criteria score based upon how closely a determined interest of the particular member corresponds to a determined interest of the sending member, and the set of recommended members is determined also based upon the second recommendation criteria.

16. The system of claim 10, wherein the recommendation module is configured to determine the members in the set of recommended members from the set of potential recommended members based upon their profile similarities scores being above a first predetermined threshold and their recommendation criteria scores being above a second predetermined threshold.

17. The system of claim 10, further comprising:

for each recommended member calculating a recommendation score based upon the profile similarities score and the recommendation criteria scores, and determining a set of recommended members comprises selecting the members in the potential recommended member set whose recommendation score exceeds a predetermined threshold.

18. The system of claim 10, wherein the recommendation criteria is a response likelihood to an out-of-network message, and the recommendation module is configured to determine the recommendation criteria score based upon how likely the particular member is to respond to the out-of-network communication.

19. A machine readable medium that stores instructions which when performed by a machine, cause the machine to perform operations comprising:

determining a set of potential recommended members of a social networking service;

determining for each particular member in the set of potential recommended members;

a profile similarity score, the profile similarity score indicating a measure of how similar the particular member is to a previous target member of an out-of-network communication of a sending member; and

a recommendation criteria score, the recommendation criteria score being a measure of how closely the particular member matches a recommendation criteria;

determining a set of recommended members from the set of potential recommended members based upon the profile similarity scores and the recommendation criteria scores of the members in the set of potential recommended members;

presenting the set of recommended members to the sending member; and

sending an out-of-network communication to a selected member of the set of recommended member from the sending member.

20. The machine-readable medium of claim 19, wherein the set of potential recommended members is all the members of the social networking service.

21. The machine-readable medium of claim 19, wherein the instructions for determining the profile similarity score include instructions, which when performed by the machine, cause the machine to perform the operations of determining the profile similarity score based upon the member profile attributes that the particular member has in common with the previous target member.

22. The machine-readable medium of claim 19, wherein the recommendation criteria is an interest, and the instructions for determining the recommendation criteria score include instructions, which when performed by the machine, cause the machine to perform the operations of determining the recommendation criteria score based upon how closely a determined interest of the particular member corresponds to a determined interest of the sending member.

23. The machine-readable medium of claim 19, wherein the recommendation criteria is an intent, and the instructions for determining the recommendation criteria score include instructions, which when performed by the machine, cause the machine to perform the operations of determining the recommendation criteria score based upon how closely a determined intent of the particular member corresponds to a determined intent of the sending member.

24. The machine-readable medium of claim 23, further comprising a second recommendation criteria, the second recommendation criteria is an interest, and the instructions for determining the recommendation criteria score include instructions, which when performed by the machine, cause the machine to perform the operations of determining the recommendation criteria score based upon how closely a determined interest of the particular member corresponds to a determined interest of the sending member, and the set of recommended members is determined also based upon the second recommendation criteria.

25. The machine-readable medium of claim 19, wherein the instructions for determining the set of recommended members include instructions, which when performed by the machine, cause the machine to perform the operations of determining the set of recommended members from the set of potential recommended members based upon their profile similarities scores being above a first predetermined threshold and their recommendation criteria scores being above a second predetermined threshold.

26. The machine-readable medium of claim 19, wherein the instructions further comprise instructions, which when performed by the machine, cause the machine to perform the operations of:

calculating a recommendation score for each recommended member based upon the profile similarities score and the recommendation criteria scores, and the instructions for determining the set of recommended members comprises instructions, which when performed by the machine, causes the machine to perform the operations of determining the set of recommended members by selecting the members in the potential recommended member set whose recommendation score exceeds a predetermined threshold.

27. The machine-readable medium of claim 19, wherein the recommendation criteria is a response likelihood to an out-of-network message, and the instructions for determining the recommendation criteria score include instructions, which when performed by the machine, cause the machine to perform the operations of determining the recommendation criteria score based upon how likely the particular member is to respond to the out-of-network communication