Preferred sites

• US 8,595,228 B1
• Filed: 01/09/2009
• Issued: 11/26/2013
• Est. Priority Date: 01/09/2009
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Horling, Bryan, Otto, Owen, Goel, Kavi J., Haahr, Paul G., Brukman, Michael Y., McDonnell, Philip
• Primary Examiner(s): Pham, Hung Q
• Assistant Examiner(s): CHEUNG, HUBERT G
• Application Number:
  US12/351,751
• Time in Patent Office: 1,782 Days
• Field of Search: 707/733
• US Class Current: 707/733
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results

Abstract

Methods, systems, and apparatus, including computer program products, for establishing preferences for sites that are explicitly identified by a user by either a textual input or an acceptance in response to a recommendation, and adjusting the presentation of search results based on these preferences.

Claims

1. A computer-implemented method, comprising:

accessing user site data associated with a user identifier, the user site data including resource locators of resources that were selected at least once for a user session associated with the user identifier;

identifying from the resource locators candidate sites for recommendation as preferred sites, each candidate site being specified by at least one of the resource locators included in the accessed user site data;

generating a recommendation score for each of the identified candidate sites based on per-site user metrics determined from the accessed user site data associated with the user identifier;

providing, in a subsequent user session associated with the user identifier, a recommendation of a recommended site as a preferred site for the user identifier, where the recommended site is a candidate site that has a corresponding generated recommendation score that exceeds a first recommendation threshold;

generating site preference data identifying the recommended site as the preferred site for the user identifier in response to receiving an explicit acceptance of the recommendation, the preferred site being a site having a corresponding resource locator referencing the site, where each search result that includes the corresponding resource locator is eligible for a presentation adjustment when the search result is presented to a user device associated with the user identifier;

receiving, from a search engine, a set of search results in response to a search query received during the subsequent user session associated with the user identifier, where each search result in the set of search results includes a resource locator that references a corresponding resource, and where each search result is ranked according to an associated score;

determining at least one search result in the set of search results includes the corresponding resource locator referencing the preferred site in the generated site preference data and adjusting presentation of the at least one search result in the set of search results to generate an adjusted set of search results; and

providing the generated adjusted set of search results to the user device.

2. The computer-implemented method of claim 1, wherein the providing, in the subsequent user session associated with the user identifier, the recommendation of the recommended site as the preferred site comprises providing for the subsequent user session associated with the user identifier a search preference page that includes the recommendation of the recommended site as the preferred site for the user identifier.

3. The computer-implemented method of claim 1, wherein the providing, in the subsequent user session associated with the user identifier, the recommendation of the recommended site as the preferred site comprises providing, in the subsequent user session associated with the user identifier, a search results page that includes the search results, each search result including a resource locator, and including in the search results page the recommendation of the recommended site as the preferred site if the recommended site is referenced by the corresponding resource locator included in one of the search results.

4. The computer-implemented method of claim 3, wherein the providing the search results page further comprises including the recommendation in the search results page only if the generated recommendation score of the recommended site exceeds a second recommendation threshold that is greater than the first recommendation threshold.

5. The computer-implemented method of claim 1, wherein the generating the recommendation score for each of the identified candidate sites comprises:

determining the per-site user metrics for each identified candidate site, the per-site user metrics measuring events associated with the user identifier for each identified candidate site;

determining per-site population metrics for each identified candidate site, the per-site population metrics measuring events associated with a population of user identifiers for each identified candidate site; and

generating the recommendation score for each of the identified candidate sites based on the determined per-site user metrics and the determined per-site population metrics.

6. The computer-implemented method of claim 5, wherein:

the per-site user metrics associated with the user identifier include one or more of;

a click-through rate measuring a rate at which search results that include the corresponding resource locator referencing the identified candidate site were selected in user sessions associated with the user identifier;

a long click-through rate measuring the rate at which the search results that include the corresponding resource locator referencing the identified candidate site received a long click-through in the user sessions associated with the user identifier;

an impression rate measuring how often the search results that include the corresponding resource locator referencing the identified candidate site appear in the search results that are provided for the user sessions associated with the user identifier; and

a last-time selection value that measures a time period from a current time to a last time a resource from the identified candidate site was provided for a session associated with the user identifier; and

the per-site population metrics associated with the population of user identifiers include one or more of;

a click-through rate measuring the rate at which the search results that include the corresponding resource locator referencing the identified candidate site were selected in user sessions associated with the population of user identifiers;

a long click-through rate measuring the rate at which the search results that include the corresponding resource locator referencing the identified candidate site received a long click-through in the user sessions associated with the population of user identifiers;

an impression rate measuring how often the search results that include the corresponding resource locator referencing the identified candidate site appear in the search results that are provided to the user; and

a query count measuring how many distinct queries result in the identified candidate site being identified in the search results.

7. The computer-implemented method of claim 6, wherein the candidate sites include resource locations from which resources have never been requested for the user session associated with the user identifier.

8. The computer-implemented method of claim 6, further comprising:

training a predictive model on the per-site user metrics and the per-site population metrics to predict a likelihood that the search result referencing the recommended site will be selected in the subsequent user session associated with the user identifier; and

wherein the first recommendation threshold is a minimum probability of selection.

9. The computer-implemented method of claim 1, further comprising:

receiving a preferred site textual input for the subsequent user session associated with the user identifier;

resolving the received preferred site textual input to a host name; and

generating the site preference data identifying the host name as the preferred site for the user identifier.

10. The computer-implemented method of claim 9, wherein the resolving the received preferred site textual input to the host name comprises:

determining that the received preferred site textual input specifies only a domain name and then;

identifying a geographic location associated with the user identifier;

identifying from the domain name only host names that are locally relevant to the identified geographical location; and

resolving the received preferred site textual input to one or more of the identified host names.

11. The computer-implemented method of claim 1, wherein:

the receiving from the search engine the set of search results in response to the search query comprises receiving the search results ranked according to a first order; and

adjusting the presentation of the at least one search result to generate the adjusted set of search results comprises adjusting the rank of the search result that includes the corresponding resource locator referencing the preferred site to rank the set of search results according to a second order.

12. The computer-implemented method of claim 11, wherein:

each associated score is a relevance score that measures a relevance of the search query to the corresponding resource specified by the corresponding resource locator; and

adjusting the rank of the search result comprises adjusting the rank of the search result only if the relevance score associated with the search result exceeds a relevance score threshold.

13. The computer-implemented method of claim 11, wherein the adjusting the rank of the search result comprises adjusting the rank of the search result so that the search result is positioned a predetermined number of positions below a top ranked search result.

14. The computer-implemented method of claim 11, wherein the adjusting the rank of the search result further comprises generating display data for the search result that causes the user device to display a visual indication that the search result is an adjusted search result.

15. The computer-implemented method of claim 11, wherein the generated site preference data further identifies sites explicitly disfavored by the user, and further comprising determining that the search result includes the corresponding resource locator referencing a site explicitly disfavored and in response demoting the search result in the first order.

16. The computer-implemented method of claim 11, wherein:

the generated site preference data identifies sites by a host name or a domain name; and

adjusting the rank of the search result comprises adjusting the rank of the search result only if the generated site preference data identifying the site referenced by the resource locator of the search result is not the domain name.

17. A system for processing search results, comprising:

a data store storing user site data associated with a user identifier, the user site data including resource locators of resources that were selected at least once for a user session associated with the user identifier; and

instructions stored on a non-transitory computer readable medium and executable by a data processing apparatus to cause the data processing apparatus to perform operations comprising;

identifying from the resource locators candidate sites for recommendation as preferred sites, each candidate site being specified by at least one of the resource locators included in the stored user site data;

generating a recommendation score for each of the identified candidate sites based on per-site user metrics determined from the stored user site data associated with the user identifier;

providing, in a subsequent user session associated with the user identifier, a recommendation of a recommended site as a preferred site for the user identifier, where the recommended site is a candidate site that has a corresponding generated recommendation score that exceeds a first recommendation threshold;

generating site preference data identifying the recommended site as the preferred site for the user identifier in response to receiving an explicit acceptance of the recommendation, the preferred site being a site having a corresponding resource locator referencing the site, where each search result that includes the corresponding resource locator is eligible for a presentation adjustment when the search result is presented to a user device associated with the user identifier;

receiving, from a search engine, a set of search results in response to a search query received from the subsequent user session associated with the user identifier, where each search result in the set of search results includes a resource locator that references a corresponding resource, and where each search result is ranked according to an associated score;

determining at least one search result in the set of search results includes the corresponding resource locator referencing the preferred site in the generated site preference data and adjusting presentation of the at least one search result in the set of search results to generate an adjusted set of search results; and

providing the generated adjusted set of search results to the user device.

18. The system of claim 17, wherein the providing, in the subsequent user session associated with the user identifier, the recommendation of the recommended site as the preferred site comprises providing for the subsequent user session associated with the user identifier a search preference page that includes the recommendation of the recommended site as the preferred site for the user identifier.

19. The system of claim 17, wherein the providing, in the subsequent user session associated with the user identifier, the recommendation of the recommended site as the preferred site comprises providing for the subsequent user session associated with the user identifier a search results page that includes the search results, each search result including a resource locator, and including in the search results page the recommendation of the recommended site as the preferred site if the recommended site is referenced by the corresponding resource locator included in one of the search results and if the generated recommendation score of the recommended site exceeds a second recommendation threshold that is greater than the first recommendation threshold.

20. The system of claim 17, wherein the generating the recommendation score for each of the identified candidate sites based on the per-site user metrics determined from the stored user site data associated with the user identifier comprises:

determining the per-site user metrics for each identified candidate site, the per-site user metrics measuring events associated with the user identifier for each identified candidate site;

determining per-site population metrics for each identified candidate site, the per-site population metrics measuring events associated with a population of user identifiers for each identified candidate site; and

generating the recommendation score for each of the identified candidate sites based on the determined per-site user metrics and the determined per-site population metrics.

21. The system of claim 20, wherein:

the per-site user metrics associated with the user identifier include one or more of;

a click-through rate measuring a rate at which the search results that include the corresponding resource locator referencing the identified candidate site were selected in user sessions associated with the user identifier;

a long click-through rate measuring the rate at which search results that include the corresponding resource locator referencing the identified candidate site received a long click-through in user sessions associated with the user identifier;

an impression rate measuring how often the search results that include the corresponding resource locator referencing the identified candidate site appear in the search results that are provided for the user sessions associated with the user identifier; and

a last-time selection value that measures a time period from a current time to a last time a resource from the identified candidate site was provided for a session associated with the user identifier; and

the per-site population metrics associated with the population of user identifiers include one or more of;

a click-through rate measuring the rate at which the search results that include the corresponding resource locator referencing the identified candidate site were selected in the user sessions associated with the population of user identifiers;

a long click-through rate measuring the rate at which the search results that include the corresponding resource locator referencing the identified candidate site received a long click-through in the user sessions associated with the population of user identifiers;

an impression rate measuring how often the search results that include the corresponding resource locator referencing the identified candidate site appear in the search results that are provided to the user; and

a query count measuring how many distinct queries result in the identified candidate site being identified in the search results.

22. The system of claim 17, wherein:

the receiving from the search engine the set of search results in response to the search query comprises receiving the search results ranked according to a first order; and

adjusting the presentation of the at least one search result to generate the adjusted set of search results comprises adjusting the rank of the search result that includes the corresponding resource locator referencing the preferred site to rank the set of search results according to a second order.

23. The system of claim 22, wherein:

each associated score is a relevance score that measures a relevance of the search query to the corresponding resource specified by the corresponding resource locator; and

adjusting the rank of the search result comprises adjusting the rank of the search result only if the relevance score associated with the search result exceeds a relevance score threshold.

24. The system of claim 23, wherein the relevance score threshold is proportional to the relevance score of another search result that is displaced by the search result adjusted.

25. A system for processing search results, comprising:

a data store storing user site data associated with a user identifier, the user site data including resource locators that reference sites that were selected at least once for a user session associated with the user identifier; and

instructions stored on a non-transitory computer readable medium and executable by a data processing apparatus to cause the data processing apparatus to perform operations comprising;

identifying from the resource locators candidate sites for recommendation as preferred sites, each candidate site being specified by at least one of the resource locators included in the stored user site data;

generating a recommendation score for each of the identified candidate sites based on per-site user metrics determined from the stored user site data associated with the user identifier;

providing, in a subsequent user session associated with the user identifier, a recommendation of a recommended site as a preferred site for the user identifier, where the recommended site is a candidate site that has a corresponding generated recommendation score that exceeds a first recommendation threshold; and

generating site preference data identifying the recommended site as the preferred site for the user identifier in response to receiving an explicit acceptance of the recommendation, the generated site preference data is provided as input to a search engine that generates a score for a resource in response to a search query associated with the user identifier and based, in part, on the resource being located at a resource locator referencing the preferred site.

26. A computer program product, encoded on a non-transitory computer readable medium, operable to cause a data processing apparatus to perform operations comprising:

accessing user site data associated with a user identifier, the user site data including resource locators of resources that were selected at least once for a user session associated with the user identifier;

identifying from the resource locators candidate sites for recommendation as preferred sites, each candidate site being specified by at least one of the resource locators included in the accessed user site data;

generating a recommendation score for each of the identified candidate sites based on per-site user metrics determined from the accessed user site data associated with the user identifier;

providing, in a subsequent user session associated with the user identifier, a recommendation of a recommended site as a preferred site for the user identifier, where the recommended site is a candidate site that has a corresponding generated recommendation score that exceeds a first recommendation threshold;

generating site preference data identifying the recommended site as the preferred site for the user identifier in response to receiving an explicit acceptance of the recommendation, the preferred site being a site having a corresponding resource locator referencing the site, where each search result that includes the corresponding resource locator is eligible for a presentation adjustment when the search result is presented to a user device associated with the user identifier;

receiving, from a search engine, a set of search results in response to a search query received during the subsequent user session associated with the user identifier, where each search result in the set of search results includes a resource locator that specifies references a corresponding resource, and where each search result is ranked according to an associated score;

determining at least one search result in the set of search results includes the corresponding resource locator referencing the preferred site in the generated site preference data and adjusting presentation of the at least one search result in the set of search results to generate an adjusted set of search results; and

providing the generated adjusted set of search results to the user device.

27. The computer program product of claim 26, wherein the providing, in the subsequent user session associated with the user identifier, the recommendation of the recommended site as the preferred site comprises providing for the subsequent user session associated with the user identifier a search preference page that includes the recommendation of the recommended site as the preferred site for the user identifier.

28. The computer program product of claim 26, wherein the providing, in the subsequent user session associated with the user identifier, the recommendation of the recommended site as the preferred site comprises:

providing for the subsequent user session associated with the user identifier a search results page that includes the search results, each search result including a resource locator; and

including in the search results page the recommendation to identify the recommended site as the preferred site if the recommended site is referenced by the corresponding resource locator included in one of the search results only if the generated recommendation score of the recommended site exceeds a second recommendation threshold that is greater than the first recommendation threshold.

29. The computer program product of claim 26, wherein the generating the recommendation score for each of the identified candidate sites comprises:

determining the per-site user metrics for each identified candidate site, the per-site user metrics measuring events associated with the user identifier for each identified candidate site;

determining per-site population metrics for each identified candidate site, the per-site population metrics measuring events associated with a population of user identifiers for each identified candidate site; and

generating the recommendation score for each of the identified candidate sites based on the determined per-site user metrics and the determined per-site population metrics.