System and method for routing tasks to a user in a workforce

• US 20080209431A1
• Filed: 02/25/2008
• Published: 08/28/2008
• Est. Priority Date: 02/23/2007
• Status: Active Grant

• Current Assignee: MC2ES Pte., Ltd.
• Original Assignee: Crowdengineering Inc. (Crowd SRL)
• Inventors: Piccioni, Massimo, La Vecchia, Gioacchino, Colombo, Alberto
• Granted Patent: US 8,099,311 B2
• Time in Patent Office: Days
• US Class Current: 718/104
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task

Abstract

A routing system and method efficiently routes tasks to users who are members of a large and geographically diverse workforce. Generally, limited information is known about each user'"'"'s skills and behavioral factors. Based on a profile containing the known information about a user, task is efficiently allocated and routed to a user by matching attributes of the task to the profile using a neural network and a stochastic model. Feedback is collected by the routing system based on the user'"'"'s handling of the task and on whether a solution provided by the user was accepted. Over time, as more feedback is collected, the profile and/or the neural network are refined which allows for more efficient routing of future tasks.

Claims

1. A method comprising:

receiving a task including at least one normalized task attribute;

accessing a plurality of profiles, each profile associated with a user and including a plurality of skill metrics and a plurality of performance indicators of the user;

calculating an initial value for each profile based on the at least one normalized task attribute and the plurality of skill metrics;

calculating a fitness metric for each profile based on the initial value using a neural network having weights based on the plurality of performance indicators;

selecting a profile based on a stochastic model using the fitness metric; and

routing the task to the user associated with the selected profile.

2. The method of claim 1, further comprising updating at least one of the plurality of skill metrics of the selected profile based on whether a solution to the task provided by the user was accepted.

3. The method of claim 1, wherein at least one of the plurality of the skill metrics is based on a certification.

4. The method of claim 1, further comprising updating at least one of the plurality of performance indicators based on whether the user accepts the task.

5. The method of claim 1, further comprising updating at least one of the plurality of performance indicators based on an elapsed amount of time for the selected user to accept the task.

6. The method of claim 1, further comprising updating at least one of the plurality of performance indicators based on whether the user provided a solution to the task.

7. The method of claim 1, further comprising updating at least one of the plurality of performance indicators based on an elapsed amount of time for the selected user to provide a solution to the task.

8. The method of claim 1, further comprising pre-selecting a portion of the plurality of profiles based on the fitness metric.

9. The method of claim 1, wherein the stochastic model is based on a lottery.

10. The method of claim 1, wherein the stochastic model is based on a Gaussian distribution.

11. A system comprising:

an input module configured to receive a task including at least one normalized task attribute;

a profile module configured to access a plurality of profiles, each profile associated with a user and including a plurality of skill metrics and a plurality of performance indicators of the user;

a supervised learning module configured to calculate an initial value for each profile based on the at least one normalized task attribute and the plurality of skill metrics;

an unsupervised learning module configured to calculate a fitness metric for each individual profile based on the initial value using a neural network having weights based on the plurality of performance indicators;

a stochastic module configured to select a profile based on a stochastic model using the fitness metric; and

an output module configured to route the task to the user associated with the selected profile.

12. The system of claim 11, wherein at least one of the plurality of the skill metrics is based on a certification.

13. The system of claim 11, further comprising a feedback module configured to update the selected individual profile based on whether a solution to the task provided by the user was accepted.

14. The system of claim 13, wherein the feedback module is further configured to update at least one of the plurality of performance indicators based on whether the user accepts the task.

15. The system of claim 13, wherein the feedback module is further configured to update at least one of the plurality of performance indicators based on an elapsed amount of time for the selected user to accept the task.

16. The system of claim 13, wherein the feedback module is further configured to update at least one of the plurality of performance indicators based on whether the user provided a solution to the task.

17. The system of claim 13, wherein the feedback module is further configured to update at least one of the plurality of performance indicators based on an elapsed amount of time for the selected user to provide a solution to the task.

18. The system of claim 11, wherein the stochastic module is further configured to pre-select a portion of the plurality of profiles based on the fitness metric.

19. The system of claim 11, wherein the stochastic model is based on a lottery.

20. The system of claim 11, wherein the stochastic model is based on a Gaussian distribution.

21. A computer readable medium having embodied thereon a program executable by a processor for executing a method for allocating a task, the method comprising:

receiving a task including at least one normalized task attribute;

accessing a plurality of profiles, each profile associated with a user and including a plurality of skill metrics and a plurality of performance indicators of the user;

calculating an initial value for each profile based on the at least one normalized task attribute and the plurality of skill metrics;

calculating a fitness metric for each profile based on-the initial value using a neural network having weights based on the plurality of performance indicators;

selecting a profile based on a stochastic model using the fitness metric; and

routing the task to the user associated with the selected profile.

22. The computer readable medium of claim 21, wherein at least one of the plurality of the skill metrics is based on a certification.

23. The computer readable medium of claim 21, wherein the method further comprises pre-selecting a portion of the plurality of profiles based on the fitness metric.