Interactive machine learning advice facility

• US 7,958,066 B2
• Filed: 10/31/2008
• Issued: 06/07/2011
• Est. Priority Date: 11/02/2007
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: Hunch Inc. (eBay Inc.)
• Inventors: Pinckney, Thomas, Dixon, Chris, Gattis, Matthew Ryan
• Primary Examiner(s): Rivas; Omar F Fernandez
• Application Number:
  US12/262,862
• Publication Number:
  US 20090119234A1
• Time in Patent Office: 949 Days
• Field of Search: None
• US Class Current: 706/12
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

In embodiments of the present invention improved capabilities are described for helping a user make a decision through the use of a machine learning facility. The process may begin with an initial question being received by the machine learning facility from the user. The user may then be provided with a dialog consisting of questions from the machine learning facility and answers provided by the user. The machine learning facility may then provide a decision to the user based on the dialog and pertaining to the initial question, such as a recommendation, a diagnosis, a conclusion, advice, and the like. In embodiments, future questions and decisions provided by the machine learning facility may be improved through feedback provided by the user.

Claims

1. A method of helping a user make a decision through the use of a machine learning facility, comprising:

creating a profile for the user through a sequence of questions presented from the machine learning facility to the user during a registration process;

receiving an initial question at the machine learning facility from the user;

providing the user with a dialog consisting of questions from the machine learning facility and answers provided by the user, wherein at least one of the questions from the machine learning facility is selected based upon the profile;

including at least one randomly selected question in the dialogue, wherein the at least one randomly selected question is used to train the machine learning facility upon reaching a decision; and

providing the decision to the user from the machine learning facility, wherein the decision is a single answer to the initial question from the user based on the dialog and the profile.

2. The method of claim 1, wherein the decision is a recommendation.

3. The method of claim 1, wherein the decision is a diagnosis.

4. The method of claim 1, wherein the initial question is associated by the user with one of a broad category of topics.

5. The method of claim 4, wherein the one of the broad category of topics is a product.

6. The method of claim 4, wherein the one of the broad category of topics is health.

7. The method of claim 4, wherein the one of the broad category of topics is business.

8. The method of claim 4, wherein the one of the broad category of topics is political.

9. The method of claim 4, wherein the one of the broad category of topics is educational.

10. The method of claim 4, wherein the one of the broad category of topics is entertainment.

11. The method of claim 4, wherein the one of the broad category of topics is environment.

12. The method of claim 1, wherein the initial question is about the user.

13. The method of claim 1, wherein the decision includes at least one image.

14. The method of claim 1, wherein the dialogue continues until the machine learning facility develops a predetermined level of confidence in the single answer.

15. The method of claim 1, wherein the decision includes one or more additional answers, each of the one or more additional answers ranked according to a level of confidence.

16. The method of claim 1, wherein the decision is a pseudo random decision presented to the user with a request for user feedback on whether the pseudo random decision is helpful.

17. The method of claim 1 wherein the at least one randomly selected question is randomly selected from a plurality of suggested questions provided by users after completion of previous instances of a user dialogue related to the initial question.

18. A computer program product embodied in a non-transitory computer readable medium that, when executing on one or more computing devices, performs the steps of:

creating a profile for the user through a sequence of questions presented from the machine learning facility to the user during a registration process;

receiving an initial question at the machine learning facility from the user;

providing the user with a dialog consisting of questions from the machine learning facility and answers provided by the user, wherein at least one of the questions from the machine learning facility is selected based upon the profile;

including at least one randomly selected question in the dialogue, wherein the at least one randomly selected question is used to train the machine learning facility upon reaching a decision; and

providing the decision to the user from the machine learning facility, wherein the decision is a single answer to the initial question from the user based on the dialog and the profile.

19. A server comprising a memory, a processor, and an interface to access devices through a network, wherein the processor is configured to perform the steps of:

creating a profile for the user through a sequence of questions presented from the machine learning facility to the user during a registration process;

receiving an initial question at the machine learning facility from the user;

providing the user with a dialog consisting of questions from the machine learning facility and answers provided by the user, wherein at least one of the questions from the machine learning facility is selected based upon the profile;

including at least one randomly selected question in the dialogue, wherein the at least one randomly selected question is used to train the machine learning facility upon reaching a decision; and

providing the decision to the user from the machine learning facility, wherein the decision is a single answer to the initial question from the user based on the dialog and the profile.