Crowdsensus: deriving consensus information from statements made by a crowd of users

• US 8,781,990 B1
• Filed: 02/25/2011
• Issued: 07/15/2014
• Est. Priority Date: 02/25/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: de Alfaro, Luca, Jurca, Radu, Kulshreshtha, Ashutosh
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Wu, Fuming
• Application Number:
  US13/035,276
• Time in Patent Office: 1,236 Days
• Field of Search: 706/52
• US Class Current: 706/52
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A system and method for updating and correcting facts that receives proposed values for facts from users and determines a consensus value for the fact based on a distribution of the probabilities that the proposed values are the correct value for the fact wherein the probability that the proposed value is the correct value for the fact is based on a score indicative of the probability that the user proposing the value proposes accurate values.

Claims

1. A computer-implemented method for determining a consensus value for an attribute of a map feature, the method executed by a computer system, comprising:

receiving a plurality of proposed values for the attribute of the map feature, each proposed value provided by a user;

iteratively determining for each user proposing a value in the plurality of proposed values a first score indicative of an accuracy of the user until the difference between the determined first scores determined in two successive iterations is below a pre-defined threshold;

iteratively determining for each proposed value in the plurality of proposed values a second score indicative of a probability that the proposed value is a correct value for the attribute until the difference between the determined second scores determined in two successive iterations is below a pre-defined threshold and wherein the second score is based at least in part on the first score for each user proposing the proposed value;

determining from the plurality of proposed values a consensus value for the attribute, by;

determining a probability distribution of the proposed values based at least in part on the second score; and

determining the consensus value for the attribute based at least in part on the probability distribution; and

storing the consensus value of the attribute.

2. The method of claim 1 further comprising iteratively determining a third score indicative of a probability that the proposed value is an unreliable value until the difference between the determined third scores determined in two successive iterations is below a pre-defined threshold and wherein the second score is based at least in part on the third score.

3. The method of claim 1 further comprising iteratively determining a fourth score indicative of a probability that the user providing the proposed value provides unreliable values until the difference between the determined fourth scores determined in two successive iterations is below a pre-defined threshold and wherein the second score is based at least in part on the fourth score.

4. The method of claim 3 further comprising updating a user profile for the user providing the proposed value based upon the fourth score.

5. The method of claim 1 wherein determining the second score comprises Bayesian inference.

6. The method of claim 1 further comprising providing the consensus value of the attribute to a second user in response to a search query.

7. The method of claim 1 further comprising updating a user profile for the user providing the proposed value based upon the first score.

8. The method of claim 1 wherein the attribute was missing a value prior to determination of the consensus value.

9. A system for determining a consensus value for an attribute of a map feature comprising:

one or more processors for executing program code; and

a non-transitory computer-readable storage medium storing executable program code for;

receiving a plurality of proposed values for the attribute of the map feature, each proposed value provided by a user;

iteratively determining for each user proposing a value in the plurality of proposed values a first score indicative of an accuracy of the user until the difference between the determined first scores determined in two successive iterations is below a pre-defined threshold;

iteratively determining for each of the plurality of proposed values a second score indicative of a probability that the proposed value is a correct value for the attribute until the difference between the determined second scores determined in two successive iterations is below a pre-defined threshold and wherein the second score is based at least in part on the first score for each user proposing the proposed value;

determining a probability distribution of the proposed values in the plurality of proposed values based at least in part on the second score for each proposed value in the plurality of proposed values; and

determining a consensus value for the attribute based at least in part on the probability distribution.

10. The system of claim 9 further comprising executable program code for updating a user profile for the user based upon the first score.

11. The system of claim 9 further comprising executable program code for iteratively determining for each of the plurality of proposed values a third score indicative of a likelihood that the proposed value is unreliable until the difference between the determined third scores determined in two successive iterations is below a pre-defined threshold and determining the second score based at least in part on the third score.

12. The system of claim 9 further comprising executable program code for iteratively determining a fourth score indicative of a probability that the user providing the proposed value provides unreliable values until the difference between the determined fourth scores determined in two successive iterations is below a pre-defined threshold and determining the second score based at least in part on the fourth score.

13. The system of claim 12 further comprising executable program code for updating a user profile for the user providing the proposed value based upon the fourth score.

14. The system of claim 9 wherein the attribute was missing a value prior to determination of the consensus value.

15. A non-transitory computer-readable storage medium containing program code executable by a computer to determine a consensus value for an attribute of a map feature, comprising program code that instructs one or more computer processors to:

receive a plurality of proposed values for the attribute of the map feature, each proposed value provided by a user;

iteratively determine for each user proposing a value in the plurality of proposed values a first score indicative of an accuracy of the user until the difference between the determined first scores determined in two successive iterations is below a pre-defined threshold;

iteratively determine for each of the plurality of proposed values a second score indicative of a probability that the proposed value is a correct value for the attribute until the difference between the determined second scores determined in two successive iterations is below a pre-defined threshold and wherein the second score is based at least in part on the first score for each user proposing the proposed value;

determine from the plurality of proposed values a consensus value for the attribute, by;

determining a probability distribution of all of the proposed values in the plurality of proposed values based at least in part on the second score for each proposed value in the plurality of proposed values; and

determining the consensus value for the attribute based at least in part on the probability distribution; and

store the consensus value of the attribute.

16. The non-transitory computer-readable storage medium of claim 15 wherein determining the second score comprises Bayesian inference.

17. The non-transitory computer-readable storage medium of claim 15 further comprising iteratively determining a third score indicative of a probability that the proposed value is an unreliable value until the difference between the determined third scores determined in two successive iterations is below a pre-defined threshold and wherein the second score is based at least in part on the third score.

18. The non-transitory computer-readable storage medium of claim 15 further comprising iteratively determining a fourth score indicative of a probability that the user providing the proposed value provides unreliable values until the difference between the determined fourth scores determined in two successive iterations is below a pre-defined threshold and wherein the second score is based at least in part on the fourth score.

19. The non-transitory computer-readable storage medium of claim 15 further comprising program code that instructs one or more computer processors to provide the consensus value of the attribute to a second user in response to a search query.

20. The non-transitory computer-readable storage medium of claim 15 further comprising program code that instructs one or more computer processors to update a user profile for the user providing each proposed value based upon the first score.

21. The non-transitory computer-readable storage medium of claim 18 further comprising program code that instructs one or more computer processors to update a user profile for the user providing each proposed value based upon the fourth score.

22. The non-transitory computer-readable storage medium of claim 15 wherein the attribute was missing a value prior to determination of the consensus value.