METHODS AND SYSTEMS FOR RECOMMENDING CROWDSOURCING TASKS

• US 20160232474A1
• Filed: 02/05/2015
• Published: 08/11/2016
• Est. Priority Date: 02/05/2015
• Status: Abandoned Application

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: ZOU, GUANGYU, GIL, ALVARO E.
• Application Number:
  US14/614,480
• Publication Number:
  US 20160232474A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

The disclosed embodiments illustrate methods and systems for recommending crowdsourcing tasks. A first crowdsourcing task is received from a requestor. Based on the first crowdsourcing tasks a set of second crowdsourcing tasks, previously attempted by one or more crowdworkers is determined. The set of second crowdsourcing tasks is determined based on a degree of similarity between the first crowdsourcing task and each of the one or more sets of second crowdsourcing tasks. Further, the first crowdsourcing task is recommended to a set of crowdworkers from the one or more crowdworkers based on performance of the set of crowdworkers on the set of second crowdsourcing tasks.

Claims

1. A method for recommending crowdsourcing tasks to one or more crowdworkers, said method comprising:

receiving, by one or more processors, a first crowdsourcing task from a requestor;

determining, by said one or more processors, a set of second crowdsourcing tasks, from one or more sets of second crowdsourcing tasks previously attempted by one or more crowdworkers, based on a degree of similarity between said first crowdsourcing task and each of said one or more sets of second crowdsourcing tasks, wherein said degree of similarity is determined based on a comparison between one or more first attributes associated with said first crowdsourcing task and one or more second attributes associated with each of said one or more sets of second crowdsourcing tasks; and

recommending, by said one or more processors, said first crowdsourcing task to a set of crowdworkers from said one or more crowdworkers based on performance of said set of crowdworkers on said set of second crowdsourcing tasks.

2. The method of claim 1, wherein said one or more first attributes and said one or more second attributes correspond to at least one of a posting time of a crowdsourcing task, an expiry time of a crowdsourcing task, a task type associated with a crowdsourcing task, a unit price associated with a crowdsourcing task, and a task expertise associated with a crowdsourcing task.

3. The method of claim 1, wherein said one or more sets of second crowdsourcing tasks are obtained by clustering one or more crowdsourcing tasks based on at least said degree of similarity among said one or more crowdsourcing tasks, wherein said one or more crowdsourcing tasks are previously attempted by said one or more crowdworkers.

4. The method of claim 3 further comprising creating, by said one or more processors, a graph representative of one or more links between each of said one or more crowdworkers and said one or more crowdsourcing tasks, wherein each link between a crowdworker and a crowdsourcing task represents that said crowdsourcing task was processed by said crowdworker.

5. The method of claim 4 further comprising assigning, by said one or more processors, one or more weights to each of said one or more links based on one or more performance metrics of said one or more crowdworkers on said one or more crowdsourcing tasks.

6. The method of claim 5, wherein said one or more performance metrics comprises at least one of one or more of a completion time associated with a crowdsourcing task, a responding time associated with said crowdsourcing task, and an accuracy associated with said crowdsourcing task.

7. The method of claim 5 wherein said one or more weights are updated dynamically based on a performance of said crowdworker on said first crowdsourcing task and a frequency of said crowdworker performing said first crowdsourcing task.

8. The method of claim 5 further comprising ranking, by said one or more processors, each crowdworker of said one or more crowdworkers based on a weight associated with said one or more links corresponding to said one or more crowdworkers, wherein said first crowdsourcing task is recommended to said one or more crowdworkers based on said rank.

9. The method of claim 1 further comprising transmitting notifications, by said one or more processors to said set of crowdworkers about said first crowdsourcing task.

10. A system for recommending crowdsourcing tasks to one or more crowdworkers, said system comprising:

one or more processors configured to;

receive a first crowdsourcing task from a requestor;

determine a set of second crowdsourcing tasks, from one or more sets of second crowdsourcing tasks previously attempted by one or more crowdworkers, based on a degree of similarity between said first crowdsourcing task and each of said one or more sets of second crowdsourcing tasks, wherein said degree of similarity is determined based on a comparison between one or more first attributes associated with said first crowdsourcing task and one or more second attributes associated with each of said one or more sets of second crowdsourcing tasks; and

recommend said first crowdsourcing task to a set of crowdworkers from said one or more crowdworkers based on performance of said set of crowdworkers on said set of second crowdsourcing tasks.

11. The system of claim 10, wherein said one or more first attributes and said one or more second attributes correspond to at least one of a posting time of a crowdsourcing task, an expiry time of a crowdsourcing task, a task type associated with a crowdsourcing task, a unit price associated with a crowdsourcing task, and a task expertise associated with a crowdsourcing task.

12. The system of claim 10, wherein one or more sets of second crowdsourcing tasks are obtained by clustering one or more crowdsourcing tasks based on at least said degree of similarity among said one or more crowdsourcing tasks, wherein said one or more crowdsourcing tasks are previously attempted by said one or more crowdworkers.

13. The system of claim 12, wherein said one or more processors are configured to create a graph representative of one or more links between each of said one or more crowdworkers and said one or more crowdsourcing tasks, wherein each link between a crowdworker and a crowdsourcing task represents that said crowdsourcing task was processed by said crowdworker.

14. The system of claim 13, wherein said one or more processors are configured to assign one or more weights to each of said one or more links based on one or more performance metrics of said one or more crowdworkers on said one or more crowdsourcing tasks.

15. The system of claim 14, wherein said one or more performance metrics comprises at least one of one or more of a completion time associated with a crowdsourcing task, a responding time associated with said crowdsourcing task, and an accuracy associated with said crowdsourcing task.

16. The system of claim 14, wherein said one or more weights are updated dynamically based on a performance of said crowdworker on said first crowdsourcing task and a frequency of said crowdworker performing said first crowdsourcing task.

17. The system of claim 14, wherein said one or more processors are configured to rank each crowdworker of said one or more crowdworkers based on a weight associated with said one or more links corresponding to said one or more crowdworkers, wherein said first crowdsourcing task is recommended to said one or more crowdworkers based on said rank.

18. The system of claim 10, wherein said one or more processors are configured to transmit notifications to said set of crowdworkers about said first crowdsourcing task.

19. A computer program product for use with a computing device, the computer program product comprising a non-transitory computer readable medium, the non-transitory computer readable medium stores a computer program code for recommending crowdsourcing tasks, the computer program code is executable by one or more processors in the computing device to:

receive a first crowdsourcing task from a requestor;

determine a set of second crowdsourcing tasks, from one or more sets of second crowdsourcing tasks previously attempted by one or more crowdworkers, based on a degree of similarity between said first crowdsourcing task and each of said one or more sets of second crowdsourcing tasks, wherein said degree of similarity is determined based on a comparison between one or more first attributes associated with said first crowdsourcing task and one or more second attributes associated with each of said one or more sets of second crowdsourcing tasks; and

recommend said first crowdsourcing task to a set of crowdworkers from said one or more crowdworkers based on performance of said set of crowdworkers on said set of second crowdsourcing tasks.