Suggested out of network communication recipients

• US 9,497,156 B2
• Filed: 10/26/2015
• Issued: 11/15/2016
• Est. Priority Date: 01/07/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: LinkedIn Corporation (Microsoft Corporation)
• Inventors: Ahn, Junghoon (Andrew), Gupta, Abhishek, Posse, Christian, Bhasin, Anmol, Shi, Yurong, Li, Jian, Kessler, Jacob
• Primary Examiner(s): Casanova, Jorge A
• Application Number:
  US14/923,182
• Publication Number:
  US 20160043987A1
• Time in Patent Office: 386 Days
• US Class Current: 1/1
• 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 computer implemented method executed in conjunction with a social networking service, the method comprising:

determine a previous target member of the social networking service, the previous target member being a past communication target of a sending member of the social networking service, the sending member and the previous target member being further than a predetermined social network distance from each other on the social networking service;

determine first and second profile similarity scores for first and second members of the social networking service, the first and second members being further than the predetermined social network distance from the sending member on the social networking service, the first profile similarity score quantifying a determined similarity between a value of an attribute in a member profile of the first member and a value of an attribute in a member profile of the previous target member, the second profile similarity score quantifying a determined similarity between a value of an attribute in a member profile of the second member and a value of an attribute in the member profile of the previous target member;

determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores, the recommended out of network communication recipient being either the first or second member;

present the recommended out-of-network communication recipient to the sending member in a graphical user interface of the social networking service;

receive an input from the sending member indicating that the sending member would like to send a communication to the recommended out-of-network communication recipient; and

send an electronic communication to the recommended out-of-network communication recipient.

2. The computer implemented method of claim 1, wherein the predetermined social network distance is a first degree connection.

3. The computer implemented method of claim 1, wherein the computer processors are further configured to:

determine a first interest score for the first member that is determined based upon how closely a determined interest of the first member corresponds to a determined interest of the sending member;

determine a second interest score for the second member that is determined based upon how closely a determined interest of the second member corresponds to a determined interest of the sending member; and

wherein the one or more processors are configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second interest scores, the recommended out of network communication recipient being either the first or second member.

4. The computer implemented method of claim 3, wherein the computer processors are configured to determine the first interest score using a Bayesian classifier.

5. The computer implemented method of claim 1, wherein the computer processors are further configured to:

determine a first intent score for the first member that is determined based upon how closely a determined intent of the first member corresponds to a determined intent of the sending member;

determine a second intent score for the second member that is determined based upon how closely a determined intent of the second member corresponds to a determined intent of the sending member; and

wherein the one or more processors are configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second intent scores, the recommended out of network communication recipient being either the first or second member.

6. The computer implemented method of claim 5, wherein the computer processors are configured to determine the first intent score using a Bayesian classifier.

7. The computer implemented method of claim 1, wherein the computer processors are further configured to:

determine a first interest score for the first member that is determined based upon how closely a determined interest of the first member corresponds to a determined interest of the sending member;

determine a first intent score for the first member that is determined based upon how closely a determined intent of the first member corresponds to a determined intent of the sending member;

determine a second interest score for the second member that is determined based upon how closely a determined interest of the second member corresponds to a determined interest of the sending member;

determine a second intent score for the second member that is determined based upon how closely a determined intent of the second member corresponds to a determined intent of the sending member; and

wherein the one or more processors are configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second intent and interest scores, the recommended out of network communication recipient being either the first or second member.

8. A system comprising:

a memory;

one or more computer processors coupled to the memory and configured to;

determine a previous target member of a social networking service, the previous target member being a past communication target of a sending member of the social networking service, the sending member and the previous target member being further than a predetermined social network distance from each other on the social networking service;

determine first and second profile similarity scores for first and second members of the social networking service, the first and second members being further than the predetermined social network distance from the sending member on the social networking service, the first profile similarity score quantifying a determined similarity between a value of an attribute in a member profile of the first member and a value of an attribute in a member profile of the previous target member, the second profile similarity score quantifying a determined similarity between a value of an attribute in a member profile of the second member and a value of an attribute in the member profile of the previous target member;

determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores, the recommended out of network communication recipient being either the first or second member;

present the recommended out-of-network communication recipient to the sending member in a graphical user interface of the social networking service;

receive an input from the sending member indicating that the sending member would like to send a communication to the recommended out-of-network communication recipient; and

send an electronic communication to the recommended out-of-network communication recipient.

9. The system of claim 8, wherein the predetermined social network distance is a first degree connection.

10. The system of claim 8, wherein the one or more computer processors are further configured to:

determine a first interest score for the first member that is determined based upon how closely a determined interest of the first member corresponds to a determined interest of the sending member;

determine a second interest score for the second member that is determined based upon how closely a determined interest of the second member corresponds to a determined interest of the sending member; and

wherein the one or more processors are configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second interest scores, the recommended out of network communication recipient being either the first or second member.

11. The system of claim 10, wherein the one or more computer processors are configured to determine the first interest score using a Bayesian classifier.

12. The system of claim 8, wherein the one or more computer processors are further configured to:

determine a first intent score for the first member that is determined based upon how closely a determined intent of the first member corresponds to a determined intent of the sending member;

determine a second intent score for the second member that is determined based upon how closely a determined intent of the second member corresponds to a determined intent of the sending member; and

wherein the one or more processors are configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second intent scores, the recommended out of network communication recipient being either the first or second member.

13. The system of claim 12, wherein the one or more computer processors are configured to determine the first intent score using a Bayesian classifier.

14. The system of claim 8, wherein the computer processors are further configured to:

determine a first interest score for the first member that is determined based upon how closely a determined interest of the first member corresponds to a determined interest of the sending member;

determine a first intent score for the first member that is determined based upon how closely a determined intent of the first member corresponds to a determined intent of the sending member;

determine a second interest score for the second member that is determined based upon how closely a determined interest of the second member corresponds to a determined interest of the sending member;

determine a second intent score for the second member that is determined based upon how closely a determined intent of the second member corresponds to a determined intent of the sending member; and

wherein the one or more processors are configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second intent and interest scores, the recommended out of network communication recipient being either the first or second member.

15. A machine-readable storage medium that stores instructions which configure a machine to:

determine a previous target member of a social networking service, the previous target member being a past communication target of a sending member of the social networking service, the sending member and the previous target member being further than a predetermined social network distance from each other on the social networking service;

determine first and second profile similarity scores for first and second members of the social networking service, the first and second members being further than the predetermined social network distance from the sending member on the social networking service, the first profile similarity score quantifying a determined similarity between a value of an attribute in a member profile of the first member and a value of an attribute in a member profile of the previous target member, the second profile similarity score quantifying a determined similarity between a value of an attribute in a member profile of the second member and a value of an attribute in the member profile of the previous target member;

determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores, the recommended out of network communication recipient being either the first or second member;

present the recommended out-of-network communication recipient to the sending member in a graphical user interface of the social networking service;

receive an input from the sending member indicating that the sending member would like to send a communication to the recommended out-of-network communication recipient; and

send an electronic communication to the recommended out-of-network communication recipient.

16. The machine-readable storage medium of claim 15, wherein the predetermined social network distance is a first degree connection.

17. The machine-readable storage medium of claim 15, wherein the instructions configure the machine to:

determine a first interest score for the first member that is determined based upon how closely a determined interest of the first member corresponds to a determined interest of the sending member;

determine a second interest score for the second member that is determined based upon how closely a determined interest of the second member corresponds to a determined interest of the sending member; and

wherein the machine is configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second interest scores, the recommended out of network communication recipient being either the first or second member.

18. The machine-readable storage medium of claim 17, wherein the instructions configure the machine to determine the first interest score using a Bayesian classifier.

19. The machine-readable storage medium of claim 15, wherein the instructions configure the machine to:

determine a first intent score for the first member that is determined based upon how closely a determined intent of the first member corresponds to a determined intent of the sending member;

determine a second intent score for the second member that is determined based upon how closely a determined intent of the second member corresponds to a determined intent of the sending member; and

wherein the machine is configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second intent scores, the recommended out of network communication recipient being either the first or second member.

20. The machine-readable storage medium of claim 19, wherein the instructions configure the machine to determine the first intent score using a Bayesian classifier.

21. The machine-readable storage medium of claim 15, wherein the instructions configure the machine to:

determine a first interest score for the first member that is determined based upon how closely a determined interest of the first member corresponds to a determined interest of the sending member;

determine a first intent score for the first member that is determined based upon how closely a determined intent of the first member corresponds to a determined intent of the sending member;

determine a second interest score for the second member that is determined based upon how closely a determined interest of the second member corresponds to a determined interest of the sending member;

determine a second intent score for the second member that is determined based upon how closely a determined intent of the second member corresponds to a determined intent of the sending member; and

wherein the machine is configured to determine a recommended out of network communication recipient based upon a comparison of the first and second profile similarity scores and based upon the first and second intent and interest scores, the recommended out of network communication recipient being either the first or second member.