ACCELERATING COLLABORATION IN TASK ASSIGNMENT BY USING SOCIALLY ENHANCED MODEL

• US 20150067043A1
• Filed: 08/29/2013
• Published: 03/05/2015
• Est. Priority Date: 08/29/2013
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Agarwal, Shivali, Lee, Juhnyoung, Liu, Rong, Sindhgatta, Renuka R.
• Application Number:
  US14/013,595
• Publication Number:
  US 20150067043A1
• Time in Patent Office: Days
• US Class Current: 709/204
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/306 User profiles

Abstract

Communication logs may be analyzed to detect interactions between members, and a social network of members built based on the analysis. A plurality of communities of members is determined in the social network, and social positions of at least some of the members in each of the community are detected. The communities and their member social positions are utilized in dynamically forming a team of members to handle a task assignment.

Claims

1. A method of accelerating executing tasks for global service delivery, comprising:

building, by a computer processor, member social network from one or more collaboration logs describing social interactions between a plurality of workers processing tasks, the member social network comprising nodes and edges, wherein a node represents a member and an edge connecting two nodes represents an interaction between two members represented by the two nodes;

formulating, by the computer processor, a plurality of communities in the member social network, each of the plurality of communities comprising one or more members of the member social network;

determining, by the computer processor, one or more topics processed by one or more of the plurality of communities;

detecting one or more social positions for at least one member in each of at least some of the plurality of communities based on the built member social network; and

updating at least one social profile associated with the at least one member with the detected one or more social positions, wherein the social profile is used to dynamically configure a team of members for executing a task as the task is received for execution.

2. The method of claim 1, wherein the building is performed continually based on periodic analysis of the one or more collaboration logs.

3. The method of claim 1, wherein the formulating the plurality of communities is performed by employing a community detection algorithm.

4. The method of claim 1, wherein the determining the one or more topics is performed by employing a topic modeling technique.

5. The method of claim 1, wherein the social profile is associated with one member, and the social profile describes at least a member community the one member belongs to, a community topic that the member community processes, and one or more member social positions of the one member.

6. The method of claim 1, wherein the one or more social positions are detected from at least one of influencer, key contributor, coordinator, representative, gatekeeper, and liaison.

7. The method of claim 6, wherein the coordinator detected as a node with highest betweennes centrality in a community of the member social network.

8. The method of claim 6, wherein the influencer is detected as a node with highest eigenvector centrality score in a community of the member social network.

9. The method of claim 6, wherein the key contributor is detected as one with highest degree centrality in a community of the member social network.

10. The method of claim 6, wherein the representative is detected as one with highest outdegree score between sub-networks representing the plurality of communities.

11. The method of claim 6, wherein the gatekeeper is detected as one with highest indegree score between sub-networks representing the plurality of communities.

12. The method of claim 1, further comprising:

receiving the task for execution;

finding one or more matching communities from the plurality of communities by matching the topics associated with the plurality of communities and one or more keywords present in task description of the task for execution;

selecting an influencer, coordinator, and key contributor within each of the matching communities based on social profiles associated with members in the matching communities, the social profiles updated based on the built member social network; and

dynamically configuring the team of members for executing the task.

13. The method of claim 12, further comprising selecting a gatekeeper and representative within each of the matching communities, in response to finding more than one matching community.

14. The method of claim 12, further comprising finding a task owner associated with the task for execution and notifying the task owner of the dynamically configured team of members.

20. The method of claim 1, further comprising:

receiving the task for execution;

finding one or more matching communities from the plurality of communities by matching the topics associated with the plurality of communities and one or more keywords present in task description of the task for execution;

selecting an influencer, coordinator, and key contributor within each of the matching communities based on social profiles associated with members in the matching communities, the social profiles updated based on the built member social network; and

dynamically configuring the team of members for executing the task.

15-19. -19. (canceled)