Search result ranking based on trust

• US 8,818,995 B1
• Filed: 09/13/2012
• Issued: 08/26/2014
• Est. Priority Date: 05/09/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Guha, Ramanathan V.
• Primary Examiner(s): Shmatov, Alexey
• Application Number:
  US13/614,339
• Time in Patent Office: 712 Days
• Field of Search: 707/722, 707/999.003
• US Class Current: 707/722
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A search engine system provides search results that are ranked according to a measure of the trust associated with entities that have provided labels for the documents in the search results. A search engine receives a query and selects documents relevant to the query. The search engine also determines labels associated with selected documents, and the trust ranks of the entities that provided the labels. The trust ranks are used to determine trust factors for the respective documents. The trust factors are used to adjust information retrieval scores of the documents. The search results are then ranked based on the adjusted information retrieval scores.

Claims

1. A method performed by data processing apparatus, the method comprising:

determining, based on web visitation patterns of a user, one or more trust relationships indicating that the user trusts one or more entities;

updating a set of trust relationships for the user such that;

a strength of a trust relationship with a first entity decreases based on passage of a period of time, and

based on the user visiting a web page associated with a second entity, a strength of a trust relationship with the second entity does not decrease after the passage of the period of time;

identifying one or more resources responsive to a search query, wherein each of the one or more resources is associated with one or more annotation label terms;

determining that one or more of the annotation label terms each matches a term of the search query;

identifying, for each of the annotation label terms that matches the term of the search query, a trust rank indicating a strength of a trust relationship between the user and the entity that associated the annotation label term with the resource, wherein one or more of the trust ranks are based on the one or more trust relationships determined based on web visitation patterns of the user;

determining, for each resource of the one or more resources that is associated with an annotation label term that matches the term of the search query, a relevance score based on the respective trust rank;

ranking the one or more resources based on the respective relevance scores; and

providing the ranking.

2. The method of claim 1, further comprising determining a trust relationship between the user and a first entity based on data indicating that the user trusts a second entity and data indicating that the second entity trusts the first entity.

3. The method of claim 1, further comprising:

determining that a web page associated with the user includes a link to a web page associated with a particular entity; and

determining a trust relationship between the user and the particular entity based on determining that the web page associated with the user includes the link to the web page associated with the particular entity.

4. The method of claim 1, further comprising determining a trust relationship between the user and a particular entity based on a vanity list in a web page associated with the particular entity, the vanity list indicating users who trust the particular entity.

5. The method of claim 1, further comprising maintaining a strength of a trust relationship between the user and a particular entity based on the user providing user input at a web page associated with the particular entity.

6. The method of claim 1, wherein determining that one or more of the annotation label terms each matches a term of the search query comprises determining that a particular annotation label term was associated with a particular resource of the one or more resources by two or more different entities;

wherein determining, for each resource of the one or more resources that is associated with an annotation label term that matches the term of the search query, the relevance score based on the respective trust rank comprises;

determining a weight based on a number of instances of the particular annotation label associated with the particular resource;

applying the weight to the trust ranks of the two or more different entities that associated the particular annotation label term with the particular resource to generate weighted trust ranks;

aggregating the weighted trust rank to generate an aggregated trust rank; and

determining the relevance score for the particular resource based on the aggregated trust rank.

7. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

determining, based on web visitation patterns of a user, one or more trust relationships indicating that the user trusts one or more entities;

updating a set of trust relationships for the user such that;

a strength of a trust relationship with a first entity decreases based on passage of a period of time, and

based on the user visiting a web page associated with a second entity, a strength of a trust relationship with the second entity does not decrease after the passage of the period of time;

identifying one or more resources responsive to a search query, wherein each of the one or more resources is associated with one or more annotation label terms;

determining that one or more of the annotation label terms each matches a term of the search query;

identifying, for each of the annotation label terms that matches the term of the search query, a trust rank indicating a strength of a trust relationship between the user and the entity that associated the annotation label term with the resource, wherein one or more of the trust ranks are based on the one or more trust relationships determined based on web visitation patterns of the user;

determining, for each resource of the one or more resources that is associated with an annotation label term that matches the term of the search query, a relevance score based on the respective trust rank;

ranking the one or more resources based on the respective relevance scores; and

providing the ranking.

8. The system of claim 7, wherein the operations further comprise determining a trust relationship between the user and a first entity based on data indicating that the user trusts a second entity and data indicating that the second entity trusts the first entity.

9. The system of claim 7, wherein the operations further comprise:

determining that a web page associated with the user includes a link to a web page associated with a particular entity; and

determining a trust relationship between the user and the particular entity based on determining that the web page associated with the user includes the link to the web page associated with the particular entity.

10. The system of claim 7, wherein the operations further comprise determining a trust relationship between the user and a particular entity based on a vanity list in a web page associated with the particular entity, the vanity list indicating users who trust the particular entity.

11. The system of claim 7, wherein the operations further comprise maintaining a strength of a trust relationship between the user and a particular entity based on the user providing user input at a web page associated with the particular entity.

12. The system of claim 7, wherein determining that one or more of the annotation label terms each matches a term of the search query comprises determining that a particular annotation label term was associated with a particular resource of the one or more resources by two or more different entities;

and

wherein determining, for each resource of the one or more resources that is associated with an annotation label term that matches the term of the search query, the relevance score based on the respective trust rank comprises;

determining a weight based on a number of instances of the particular annotation label associated with the particular resource;

applying the weight to the trust ranks of the two or more different entities that associated the particular annotation label term with the particular resource to generate weighted trust ranks;

aggregating the weighted trust rank to generate an aggregated trust rank; and

determining the relevance score for the particular resource based on the aggregated trust rank.

13. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:

determining, based on web visitation patterns of a user, one or more trust relationships indicating that the user trusts one or more entities;

updating a set of trust relationships for the user such that;

a strength of a trust relationship with a first entity decreases based on passage of a period of time, and

based on the user visiting a web page associated with a second entity, a strength of a trust relationship with the second entity does not decrease after the passage of the period of time;

identifying one or more resources responsive to a search query, wherein each of the one or more resources is associated with one or more annotation label terms;

determining that one or more of the annotation label terms each matches a term of the search query;

identifying, for each of the annotation label terms that matches the term of the search query, a trust rank indicating a strength of a trust relationship between the user and the entity that associated the annotation label term with the resource, wherein one or more of the trust ranks are based on the one or more trust relationships determined based on web visitation patterns of the user;

determining, for each resource of the one or more resources that is associated with an annotation label term that matches the term of the search query, a relevance score based on the respective trust rank;

ranking the one or more resources based on the respective relevance scores; and

providing the ranking.

14. The non-transitory computer storage medium of claim 13, wherein the operations further comprise determining a trust relationship between the user and a first entity based on data indicating that the user trusts a second entity and data indicating that the second entity trusts the first entity.

15. The non-transitory computer storage medium of claim 13, wherein the operations further comprise:

determining that a web page associated with the user includes a link to a web page associated with a particular entity; and

determining a trust relationship between the user and the particular entity based on determining that the web page associated with the user includes the link to the web page associated with the particular entity.

16. The non-transitory computer storage medium of claim 13, wherein the operations further comprise determining a trust relationship between the user and a particular entity based on a vanity list in a web page associated with the particular entity, the vanity list indicating users who trust the particular entity.

17. The non-transitory computer storage medium of claim 13, wherein the operations further comprise maintaining a strength of a trust relationship between the user and a particular entity based on the user providing user input at a web page associated with the particular entity.

18. The non-transitory computer storage medium of claim 13, wherein determining that one or more of the annotation label terms each matches a term of the search query comprises determining that a particular annotation label term was associated with a particular resource of the one or more resources by two or more different entities;

and

wherein determining, for each resource of the one or more resources that is associated with an annotation label term that matches the term of the search query, the relevance score based on the respective trust rank comprises;

determining a weight based on a number of instances of the particular annotation label associated with the particular resource;

applying the weight to the trust ranks of the two or more different entities that associated the particular annotation label term with the particular resource to generate weighted trust ranks;

aggregating the weighted trust rank to generate an aggregated trust rank; and

determining the relevance score for the particular resource based on the aggregated trust rank.

19. A method performed by data processing apparatus, the method comprising:

determining that a web page associated with the user includes a link to a web page associated with a particular entity;

determining a trust relationship between the user and the particular entity based on determining that the web page associated with the user includes the link to the web page associated with the particular entity;

updating a set of trust relationships for the user such that;

a strength of a trust relationship with a first entity decreases based on passage of a period of time, and

based on the user visiting a web page associated with a second entity, a strength of a trust relationship with the second entity does not decrease after the passage of the period of time;

identifying one or more resources responsive to a search query, wherein each of the one or more resources is associated with one or more annotation label terms;

determining that one or more of the annotation label terms each matches a term of the search query;

identifying, for each of the annotation label terms that matches the term of the search query, a trust rank indicating a strength of a trust relationship between the user and the entity that associated the annotation label term with the resource, wherein one or more of the trust ranks are based on the trust relationship between the user and the particular entity in response to determining that the web page associated with the user includes the link to the web page associated with the particular entity;

determining, for each resource of the one or more resources that is associated with an annotation label term that matches the term of the search query, a relevance score based on the respective trust rank;

ranking the one or more resources based on the respective relevance scores; and

providing the ranking.