Proactive user-based content correction and enrichment for geo data

• US 9,257,056 B2
• Filed: 10/31/2011
• Issued: 02/09/2016
• Est. Priority Date: 10/31/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sahuguet, Arnaud, Seefeld, Bernhard
• Primary Examiner(s): Rostami, Mohammad S
• Application Number:
  US13/286,144
• Publication Number:
  US 20130110847A1
• Time in Patent Office: 1,562 Days
• US Class Current: 1/1
• CPC Class Codes: G01C 21/3856 Data obtained from user input
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G09B 29/006 Representation of non-cartographic information on maps, e.g. population distribution, wind direction, radiation levels, air and sea routes
• CPC Class Codes: G09B 7/02 of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student

Abstract

A system and method determines ambiguous or missing information about map features, generates questions to address the ambiguity or the missing information and determines users from whom to request feedback to clarify the ambiguity or supply the missing information.

Claims

1. A computer-implemented method for soliciting feedback for an attribute of a map feature comprising:

identifying a map feature to be displayed on a map to a user wherein the map feature has a category describing a type of the map feature, a geographic region describing a location of the map feature and a map feature attribute with an associated confidence score indicating a low confidence that a value of the map feature attribute is accurate;

determining a question to solicit information about the value of the map feature attribute from the user responsive to the confidence score indicating the low confidence that the value of the map feature attribute is accurate;

retrieving a plurality of reliability scores for the user, the plurality of reliability scores based at least in part on how often feedback from the user in response to questions previously submitted to the user matched consensus values determined for map feature attribute values from a plurality of users and including one or more category-specific reliability scores based on feedback provided by the user in response to questions previously submitted to the user about specific categories of map features, one or more region-specific reliability scores based on feedback provided by the user in response to questions previously submitted to the user about map features located in specific geographic regions, and a global reliability score based on feedback provided by the user in response to all questions previously submitted to the user;

scoring the question based at least in part on a popularity score for the map feature, a priority score for the map feature attribute, the confidence score for the value of the map feature attribute, and at least one retrieved reliability score for the user; and

submitting the question to the user if the score for the question is greater than a threshold.

2. The method of claim 1 further comprising receiving, from the user, a response to the question indicating a user-specified value for the map feature attribute.

3. The method of claim 2, further comprising updating the reliability score of the user based at least in part on the response to the question.

4. The method of claim 2, further comprising updating the map feature attribute value in a map repository based at least in part on the received response.

5. The method of claim 2, further comprising determining a consensus value for the map feature attribute based on the response received from the user and a plurality of responses received from a respective plurality of other users.

6. The method of claim 5, wherein the consensus value is determined by weighting the responses received from the user and the plurality of other users by the respective reliability scores associated with the user and the plurality of other users.

7. The method of claim 5, further comprising determining a confidence score for the consensus value of the map feature attribute.

8. The method of claim 1, further comprising using the score for the question to rank the question among a plurality of questions relating to a respective plurality of map feature attributes;

and wherein submitting the question to a user further comprises determining that the question ranks higher than a threshold number of questions to be sent to the user.

14. The method of claim 1, wherein determining a question to solicit information about the value of the map feature attribute from a user comprises selecting the question from a predetermined list of questions.

15. The method of claim 1, wherein the map feature is an entity associated with a geographic location.

16. The method of claim 1, wherein the map feature attribute is one of a street address, a phone number, a fax number, a website address, or an email address.

9. A system including one or memories storing instructions and one or more processors, coupled to the memories and executing the instructions stored therein in order to perform steps comprising:

identifying a map feature to be displayed on a map to a user wherein the map feature has a category describing a type of the map feature, a geographic region describing a location of the map feature and a map feature attribute with an associated confidence score indicating a low confidence that a value of the map feature attribute is accurate;

determining a question to solicit information about the value of the map feature attribute from the user responsive to the confidence score indicating the low confidence that the value of the map feature is accurate;

retrieving a plurality of reliability scores for the user, the plurality of reliability scores based at least in part on how often feedback from the user in response to questions previously submitted to the user matched consensus values determined for map feature attribute values from a plurality of users and including one or more category-specific reliability scores based on feedback provided by the user in response to questions previously submitted to the user about specific categories of map features, one or more region-specific reliability scores based on feedback provided by the user in response to questions previously submitted to the user about map features located in specific geographic regions, and a global reliability score based on feedback provided by the user in response to all questions previously submitted to the user;

scoring the question based at least in part on a popularity score for the map feature, a priority score for the map feature attribute, the confidence score for the value of the map feature attribute, and at least one retrieved reliability score for the user; and

submitting the question to the user if the score for the question is greater than a threshold.

10. The system of claim 9 wherein the system further receives, from the user, a response to the question indicating a user-specified value for the map feature attribute.

11. The system of claim 10, wherein the system further updates the reliability score of the user based at least in part on the response to the question.

12. The system of claim 10, wherein the system further updates the map feature attribute value in a map repository based at least in part on the received response.

13. The system of claim 10, wherein the system further determines a consensus value for the map feature attribute based on the response received from the user and a plurality of responses received from a respective plurality of other users.