METHOD AND APPARATUS FOR PROCESSING MESSAGES IN A SOCIAL NETWORK

• US 20150156145A1
• Filed: 12/22/2014
• Published: 06/04/2015
• Est. Priority Date: 02/14/2006
• Status: Active Grant

• Current Assignee: Calabrio
• Original Assignee: SRI International, Inc.
• Inventors: Davitz, Jeffrey, Basu, Sugato, Yu, Jiye, Gutelius, David
• Granted Patent: US 9,614,792 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/2471 Distributed queries
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/104 Peer-to-peer [P2P] networks
• CPC Class Codes: H04L 67/1072 Discovery involving ranked list compilation of candidate peers
• CPC Class Codes: H04L 67/303 Terminal profiles

Abstract

In one embodiment, the present invention is a method and apparatus for knowledge generation and deployment in a distributed network. In one embodiment, a method for processing messages in a social network includes receiving a new message from a first node in the network, the new message including a query, providing the first node with an answer to the query, if the answer is located in a repository, and initiating generation of the answer, if the answer is not located in the repository.

Claims

1-19. -19. (canceled)

20. A method for routing messages to nodes of a computerized social network, the method performed by a computing device, the method comprising:

computing an expertise measure for a node by comparing a local topic model of the node to a global topic set of the network, wherein the local topic model is derived from local content related to the node, and the global topic set is inferred from local topic models of a plurality of nodes of the network;

creating a profile for the node, the profile comprising a set of parameters including the expertise measure; and

determining to route a message to the node based on the profile.

21. The method of claim 20, comprising creating the local topic model by generating a topic distribution for the node using a clustering algorithm.

22. The method of claim 21, comprising generating the topic distribution based on a sent box of the node'"'"'s email program.

23. The method of claim 20, comprising creating the local topic model by generating a set of local topics for the node, wherein each local topic comprises a distribution over a set of local keywords.

24. The method of claim 23, comprising creating the local topic model by generating a probability distribution over the set of local topics.

25. The method of claim 20, comprising computing the expertise measure by generating a conditional probability distribution over the global topic set based on the local topic model of the node.

26. The method of claim 20, comprising generating a referral rank for the node by, for at least one other node, estimating a likelihood that the other node refers messages to the node;

and including the referral rank in the set of parameters of the profile for the node.

27. The method of claim 20, comprising calculating a response score for the node, wherein the response score is indicative of the accuracy of the node'"'"'s responses to messages, and including the response score in the set of parameters of the profile for the node.

28. The method of claim 20, comprising updating the expertise measure after the node participates in routing or answering a message.

29. A router for routing messages to nodes in a computerized social network, the router configured to:

compute an expertise measure for a node based on a local topic model derived from local content related to the node and a global topic set inferred from local topic models of a plurality of nodes of the network;

generate a referral rank for the node by, for at least one other node, estimating a likelihood that the other node refers messages to the node;

calculate a response score for the node, wherein the response score is based on an accuracy of the node'"'"'s responses to messages;

creating a profile for the node, the profile comprising a set of parameters including the expertise measure, the referral rank, and the response score; and

route a message to the node based on the profile.

30. The router of claim 29, configured to learn an initial profile distribution for the node based on a set of social groups associated with the node.

31. The router of claim 29, configured to infer an initial profile distribution for the node based on a plurality of different data sources including one or more of:

World Wide Web pages and email.

32. The router of claim 29, configured to update the profile for the node in response to a new node entering the network.

33. The router of claim 29, configured to select a plurality of nodes based on their respective profiles, and route the message to each of the selected nodes.

34. The router of claim 29, configured to receive a response to the message from the node, determine a validation ranking for the response and the node, and update the profile for the node based on the validation ranking.

35. A message routing module for routing messages to nodes in a computerized social network, the message routing module embodied in one or more non-transitory computer readable storage media and configured to cause a computing device to:

compute an expertise measure for a node based on a probabilistic analysis of local content related to the node and content related to a plurality of nodes of the network; and

route a message to the node based on the expertise measure.

36. The message routing module of claim 35, configured to cause the computing device to generate a referral rank for the node by, for at least one other node, estimating a likelihood that the other node refers a messages to the node;

and route the message to the node based on the referral rank.

37. The message routing module of claim 35, configured to cause the computing device to calculate a response score for the node, wherein the response score is based on the accuracy of the node'"'"'s responses to messages;

and route the message to the node based on the response score.

38. The message routing module of claim 35, configured to generate a database of frequently asked questions based on messages routed to the nodes of the social network and responses received from the nodes of the social network.

39. The message routing module of claim 35, configured to generate anchor text for a World Wide Web page based on messages routed to the nodes of the social network and responses received from the nodes of the social network.