Matching method based on a machine learning algorithm and a system thereof

• US 9,117,180 B1
• Filed: 03/15/2013
• Issued: 08/25/2015
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Elance Incorporation
• Original Assignee: Elance Incorporation
• Inventors: Chiu, Kwan-Min, Grad, Daniel-Augustin, Gupta, Nidhi
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Brown, Jr., Nathan
• Application Number:
  US13/837,826
• Time in Patent Office: 893 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/1053 Employment or hiring

Abstract

Embodiments of the present invention are directed to a matching method that implements a machine learning algorithm to serve one or more matches to an individual and to ensure that an outcome of each match is more likely than not to be successful. A recommendation engine uses the machine learning algorithm to perform predictive analysis to thereby select one or more members of an online community to match or pair with the individual, based on at least structured data, unstructured data or both of the individual and/or each selected member. The recommendation engine is configured to continuously learn from past user behavior, including the individual'"'"'s, to further improve future matches provided to the individual.

Claims

1. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers; and

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful, wherein each set of requirements include at least one structured datum, at least one unstructured datum or a combination thereof, wherein the at least one structured datum is explicit and the at least one unstructured datum is implicit.

2. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers; and

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful, wherein each set of requirements include at least one structured datum, at least one unstructured datum or a combination thereof, wherein the at least one unstructured datum includes positive user actions and negative user actions.

3. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers; and

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful, wherein each set of requirements include at least one structured datum, at least one unstructured datum or a combination thereof, wherein the at least one unstructured datum is behavior datum.

4. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers; and

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful, wherein each set of requirements include at least one structured datum, at least one unstructured datum or a combination thereof, wherein the at least one structured datum includes function/role/skills, geography, time zone, languages, availability, budget, or a combination thereof.

5. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers; and

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful, wherein each set of requirements include at least one structured datum, at least one unstructured datum or a combination thereof, wherein the at least one structured datum includes job details or job history.

6. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers; and

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful, wherein the predictive analysis is based on a machine learning algorithm configured to learn from past user behavior.

7. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers; and

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful, wherein success is defined as a hire and an eventual positive feedback.

8. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers;

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful; and

d. using requirements of a community in making the suggestion, wherein the buyer and the group of service providers belong to the community.

9. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers;

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful; and

d. tracking actions of each user participating in the community.

10. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers;

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful; and

d. providing at least one communication mechanism configured to allow a direct live communication between the buyer and the service provider belonging to the group of service providers.

11. A non-transitory computer-readable medium storing instructions that, when executed by a computing device, cause the computing device to perform a method comprising:

a. determining a first set of requirements for a buyer;

b. determining a second set of requirements for each service provider belonging to a group of service providers;

c. performing predictive analysis based on all sets of requirements, thereby intelligently suggesting at least one match between the buyer and a service provider belonging to the group of service providers such that the match is more likely than not to be successful; and

d. providing access to an online profile associated with the service provider belonging to the group of service providers.

12. A system comprising:

a. an online community for hiring and working on demand, wherein the online community includes members; and

b. a recommendation engine configured to perform predictive analysis to intellectually pair an individual with at least one member of the online community such that the pairing is based at least on behavior characteristics determined by a machine learning algorithm, wherein the at least one member is able to be timely committed to the individual during a specified period identified by the user.

13. A system comprising:

a. an online community for hiring and working on demand, wherein the online community includes members; and

b. a recommendation engine configured to perform predictive analysis to intellectually pair an individual with at least one member of the online community such that the pairing is based at least on behavior characteristics determined by a machine learning algorithm, wherein the members includes clients and contractors, wherein the clients have jobs to be filled and the contractors are looking to fill the jobs.

14. A system comprising:

a. an online community for hiring and working on demand, wherein the online community includes members; and

b. a recommendation engine configured to perform predictive analysis to intellectually pair an individual with at least one member of the online community such that the pairing is based at least on behavior characteristics determined by a machine learning algorithm, wherein the members includes clients and contractors, wherein the clients have jobs to be filled and the contractors are looking to fill the jobs, wherein each job is one of role based and deliverable based.

15. A system comprising:

a. an online community for hiring and working on demand, wherein the online community includes members; and

b. a recommendation engine configured to perform predictive analysis to intellectually pair an individual with at least one member of the online community such that the pairing is based at least on behavior characteristics determined by a machine learning algorithm, wherein the recommendation engine, the members, and the individual are communicatively coupled.

16. A system comprising:

a. an online community for hiring and working on demand, wherein the online community includes members; and

b. a recommendation engine configured to perform predictive analysis to intellectually pair an individual with at least one member of the online community such that the pairing is based at least on behavior characteristics determined by a machine learning algorithm, wherein the recommendation engine is also configured to determine a first success rate of an outcome of a match between the individual and a first member, to determine a second success rate of an outcome of a match between the individual and a second member, and to present one of the two matches with the higher success rate.

17. A system comprising:

a. an online community for hiring and working on demand, wherein the online community includes members; and

b. a recommendation engine configured to perform predictive analysis to intellectually pair an individual with at least one member of the online community such that the pairing is based at least on behavior characteristics determined by a machine learning algorithm, wherein the recommendation engine is also configured to;

i. obtain structured data of a user;

ii. determine unstructured data of the user based on past behavior of the user in the online community; and

iii. assign a weight to each datum of the structured data and unstructured data.

18. A system comprising:

a. an online community for hiring and working on demand, wherein the online community includes members; and

b. a recommendation engine configured to perform predictive analysis to intellectually pair an individual with at least one member of the online community such that the pairing is based at least on behavior characteristics determined by a machine learning algorithm, wherein the recommendation engine is also configured to communicatively couple with one or more social networks to access one or more social graphs associated with the one or more social networks, wherein the one or more social graphs are used by the machine learning algorithm during the performance.