Generating connection recommendations based on recent connections and connections of close connections
Abstract
The present disclosure is directed to methods, systems, and computer program products for rendering member profile suggestions based on data derived from a social graph and activity data derived from a social network service operation on the social graph. A social network service may store member or organization profiles as nodes on the social graph. In response to a recommendation event, the social network service may identify a source profile having direct connections to a first set of profiles. The social network service may then determine a second set of profiles that are directly connected to one or more profiles of the first set of profiles. The profiles may be further associated with connection activity information, and the social network service may select one or more of the profiles from the second set of profiles as recommended profiles for the source profile based on the connection activity information.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A method comprising:
receiving, with one or more processors, a recommendation event, the recommendation event identifying an activity having been performed by a first member of a social network service; identifying, from a plurality of member profiles stored in a non-transitory, computer-readable memory in communication with the one or more processors, a first member profile associated with the first member, the plurality of member profiles being represented as corresponding nodes in a social graph; selecting, with the one or more processors, from the plurality of member profiles, a second member profile indirectly connected to the first member profile by a first plurality of edges in the social graph; selecting, with the one or more processors, from the plurality of member profiles, a third member profile indirectly connected to the first member profile by a second plurality of edges in the social graph; selecting, with the one or more processors, first connection activity information associated with the second member profile; selecting, with the one or more processors, second connection activity information associated with the third member profile; determining, with the one or more processors, a recommended member profile from the second member profile and the third member profile based on a comparison of the first connection activity information and the second connection activity information; and providing, with the one or more processors, the recommended member profile in response to the received recommendation event.
2 . The method of claim 1 , wherein the second member profile is directly connected to a fourth member profile, the fourth member profile being directly connected to the first member profile.
3 . The method of claim 2 , wherein:
the third member profile is directly connected to a fifth member profile; the fifth member profile is directly connected to the first member profile; and the fourth member profile and the fifth member profile are different member profiles.
4 . The method of claim 1 , wherein the second member profile and the third member profile are each directly connected to a fourth member profile, the fourth member profile being directly connected to the first member profile.
5 . The method of claim 1 , wherein:
the first connection activity information comprises connection time data associated with a first edge selected from the first plurality of edges; the second connection activity information comprises connection time data associated with a second edge selected from the second plurality of edges; and the comparison of the first connection activity and the second connection activity comprises a comparison of the first connection time data with the second connection time data.
6 . The method of claim 5 , wherein the recommended member profile is determined based on the first connection time data indicating that the first connection activity occurred more recent than the second connection activity.
7 . The method of claim 1 , wherein;
the first connection activity information comprises a first number of connections shared between the first member profile and the second member profile; the second connection activity information comprises a second number of connections shared between the first member profile and the third member profile; and the comparison of the first connection activity and the second connection activity comprises a comparison of the first number of shared connections with the second number of shared connections.
8 . A system comprising:
a non-transitory, computer-readable memory storing computer-executable instructions; and one or more processors in communication with the non-transitory, computer-readable memory that, having executed the computer-executable instructions, are configured to:
receive a recommendation event, the recommendation event identifying an activity having been performed by a first member of a social network service;
identify, from a plurality of member profiles, a first member profile associated with the first member, the plurality of member profiles being represented as corresponding nodes in a social graph;
select, from the plurality of member profiles, a second member profile indirectly connected to the first member profile by a first plurality of edges in the social graph;
select, from the plurality of member profiles, a third member profile indirectly connected to the first member profile by a second plurality of edges in the social graph;
select first connection activity information associated with the second member profile;
select second connection activity information associated with the third member profile; and
determine a recommended member profile from the second member profile and the third member profile based on a comparison of the first connection activity information and the second connection activity information;
provide the recommended member profile in response to the received recommendation event.
9 . The system of claim 8 , wherein the second member profile is directly connected to a fourth member profile, the fourth member profile being directly connected to the first member profile.
10 . The system of claim 9 , wherein:
the third member profile is directly connected to a fifth member profile; the fifth member profile is directly connected to the first member profile; and the fourth member profile and the fifth member profile are different member profiles.
11 . The system of claim 8 , wherein the second member profile and the third member profile are each directly connected to a fourth member profile, the fourth member profile being directly connected to the first member profile.
12 . The system of claim 8 , wherein:
the first connection activity information comprises connection time data associated with a first edge selected from the first plurality of edges; the second connection activity information comprises connection time data associated with a second edge selected from the second plurality of edges; and the comparison of the first connection activity and the second connection activity comprises a comparison of the first connection time data with the second connection time data.
13 . The system of claim 8 , wherein the recommended member profile is determined based on the first connection time data indicating that the first connection activity occurred more recent than the second connection activity.
14 . The system of claim 8 , wherein;
the first connection activity information comprises a first number of connections shared between the first member profile and the second member profile; the second connection activity information comprises a second number of connections shared between the first member profile and the third member profile; and the comparison of the first connection activity and the second connection activity comprises a comparison of the first number of shared connections with the second number of shared connections.
15 . A non-transitory, computer-readable medium storing computer-executable instructions thereon that, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:
receiving, with the one or more processors, a recommendation event, the recommendation event identifying an activity having been performed by a first member of a social network service; identifying, from a plurality of member profiles stored in a non-transitory, computer-readable memory in communication with the one or more processors, a first member profile associated with the first member, the plurality of member profiles being represented as corresponding nodes in a social graph; selecting, with the one or more processors, from the plurality of member profiles, a second member profile indirectly connected to the first member profile by a first plurality of edges in the social graph; selecting, with the one or more processors, from the plurality of member profiles, a third member profile indirectly connected to the first member profile by a second plurality of edges in the social graph; selecting, with the one or more processors, first connection activity information associated with the second member profile; selecting, with the one or more processors, second connection activity information associated with the third member profile; determining, with the one or more processors, a recommended member profile from the second member profile and the third member profile based on a comparison of the first connection activity information and the second connection activity information; and providing, with the one or more processors, the recommended member profile in response to the received recommendation event.
16 . The non-transitory, computer-readable medium of claim 15 , wherein the second member profile is directly connected to a fourth member profile, the fourth member profile being directly connected to the first member profile.
17 . The non-transitory, computer-readable medium of claim 15 , wherein the second member profile and the third member profile are each directly connected to a fourth member profile, the fourth member profile being directly connected to the first member profile.
18 . The non-transitory, computer-readable medium of claim 15 , wherein:
the first connection activity information comprises connection time data associated with a first edge selected from the first plurality of edges; the second connection activity information comprises connection time data associated with a second edge selected from the second plurality of edges; and the comparison of the first connection activity and the second connection activity comprises a comparison of the first connection time data with the second connection time data.
19 . The non-transitory, computer-readable medium of claim 18 , wherein the recommended member profile is determined based on the first connection time data indicating that the first connection activity occurred more recent than the second connection activity.
20 . The non-transitory, computer-readable medium of claim 15 , wherein;
the first connection activity information comprises a first number of connections shared between the first member profile and the second member profile; the second connection activity information comprises a second number of connections shared between the first member profile and the third member profile; and the comparison of the first connection activity and the second connection activity comprises a comparison of the first number of shared connections with the second number of shared connections.Join the waitlist — get patent alerts
Track US2015106371A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.