Method, system, and graphical user interface for providing personalized recommendations of popular search queries

• US 9,443,022 B2
• Filed: 01/19/2012
• Issued: 09/13/2016
• Est. Priority Date: 06/05/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Jeh, Glen
• Primary Examiner(s): Saeed, Usmaan
• Assistant Examiner(s): Zhao, Yu
• Application Number:
  US13/354,280
• Publication Number:
  US 20150161256A1
• Time in Patent Office: 1,699 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• 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

A method, system, and graphical user interface for providing personalized recommendations of popular search queries are disclosed. One aspect of the invention involves a graphical user interface on a computer that includes a plurality of queries recommended by a search engine for a computer user. The plurality of queries are determined by the search engine based on Internet usage data for the computer user and submission popularity data for search queries submitted by a plurality of users.

Claims

1. A method, comprising:

at a system having one or more processors that execute one or more programs stored in memory of a search engine executing on a network apparatus;

obtaining a set of popular search queries;

receiving Internet usage data for an individual computer user, the Internet usage data including information regarding a plurality of queries previously submitted by the individual computer user, the plurality of queries including a first query submitted by the individual computer user, the plurality of queries being searches for search terms in at least one of an Internet and an Intranet;

receiving a second query submitted by the individual computer user later in time than the first query, the second query being a request for search results related to the first query, the second query being for a keyword search in at least one of the Internet and the Intranet;

performing the keyword search in at least one of the Internet and the Intranet based on the second query;

determining a time difference between when the first query and the second query was submitted by the individual computer user;

determining a subset of personalized recommendations of popular search queries based on the second query and the Internet usage data for the individual computer user from among the set of popular search queries, the subset of personalized recommendations;

(i) excluding the first query based on determining that the time difference is within a predefined time range between a point of time in the past and the time the second query was received, and

(ii) including the first query based on determining that the time difference is earlier than the predefined time range and the first query is in the subset of personalized recommendations;

sending search results based on the second query to a computer associated with the individual computer user for display, the search results being ordered based on the Internet usage data for the individual computer user; and

sending links corresponding to the subset of personalized recommendations to the computer associated with the individual computer user for display, the links being ordered based on the Internet usage data for the individual computer user.

2. The method of claim 1, wherein the predefined time range is at least one week.

3. The method of claim 1, where the Internet usage data include search results activated by the individual computer user.

4. The method of claim 1, where the Internet usage data include web pages selected by the individual computer user.

5. The method of claim 4, wherein the web pages selected by the individual computer user correspond to search results selected by the individual computer user.

6. The method of claim 4, wherein the subset of personalized recommendations includes a search query associated with a plurality of web sites containing web pages in the individual computer user'"'"'s Internet usage data.

7. A method, comprising:

at a system having one or more processors that execute one or more programs stored in memory of a search engine;

obtaining a set of popular search queries including one or more categories associated with a respective query;

receiving Internet usage data for an individual computer user, the Internet usage data including one or more categories of interest to the user;

receiving a submitted query as submitted by the individual computer user, the submitted query being a request for search results from at least one of an Internet and an Intranet and is related to one of the set of popular search queries;

performing a search in at least one of the Internet and the Intranet based on the submitted query;

determining, from the set of popular search queries, a set of personalized popular search queries based on the Internet usage data for the individual computer user and the submitted query, wherein

the determining of the set of personalized popular search queries includes selecting, from the set of popular search queries, a set of personalized popular search queries, based on the one or more categories of interest to the individual computer user,

the determining of the set of personalized popular search queries excludes respective queries of the set of popular search queries in the individual computer user'"'"'s Internet usage data if the respective queries of the set of popular search queries were selected by the individual computer user within a predefined time range between a point of time in the past and the time the submitted query was received;

sending search results based on the submitted query to a computer associated with the individual computer user for display, the search results being ordered based on the Internet usage data for the individual computer user, the search results being ordered based on the Internet usage data for the individual computer user; and

sending links corresponding to the personalized popular search queries to the computer associated with the individual computer user for display, the links being ordered based on the Internet usage data for the individual computer user.

8. The method of claim 7, wherein the categories of interest to the user are weighted.

9. The method of claim 8, wherein weights of categories are determined based on the individual computer user'"'"'s query events, result click events, or browsing events in the Internet usage data for the individual computer user.

10. The method of claim 8, wherein weights of categories are used to select the set of personalized popular search queries.

11. The method of claim 8, wherein weights of categories are used to order the set of personalized popular search queries.

12. The method of claim 7, wherein the set of personalized popular search queries includes at least one query associated with a plurality of categories of interest to the user.

13. The method of claim 7, further comprising, for each respective distinct query in the set of popular search queries, associating the respective distinct query with one or more categories.

14. The method of claim 13, wherein the one or more categories for the respective distinct query are associated with web pages that are selected by one or more of a plurality of users from among search results produced in response the distinct query.

15. A method, comprising:

at a system having one or more processors that execute one or more programs stored in memory of a search engine;

receiving a plurality of search queries collectively submitted by a plurality of users, for each respective distinct query in the plurality of search queries;

determining submission popularity data for the respective distinct query, and

associating the respective distinct query with one or more web sites containing web pages that are selected by one or more of the plurality of users in response to the respective distinct query, and

receiving Internet usage data for an individual computer user, wherein the Internet usage data for the individual computer user includes web pages selected by the individual computer user;

receiving a submitted query as submitted by the individual computer user later in time than a time at which the web pages were selected by the individual computer user, the submitted query being a request for search results from at least one of an Internet and an Intranet and is related to one of the plurality of search queries;

performing a search in at least one of the Internet and the Intranet based on the submitted query;

determining one or more personalized recommendations of popular search queries from among the plurality of search queries based on the submitted query, wherein

(a) a respective determined personalized popular search query excludes queries associated with a plurality of web sites containing web pages in the individual computer user'"'"'s Internet usage data if the web pages in the individual computer user'"'"'s Internet usage data were selected by the individual computer user within a predefined time range between a point of time in the past and the time the submitted query was received, and

(b) a respective determined personalized popular search query excludes respective queries of the plurality of search queries associated with the individual computer user'"'"'s Internet usage data that include a change in a number of times the respective query is received within a predefined time period between a point of time in the past and the time the submitted query was received exceeds a predefined value; and

sending search results based on the submitted query to a computer associated with the individual computer user for display, the search results being ordered based on the Internet usage data for the individual computer user; and

sending links corresponding to the determined personalized recommendations of popular search queries to the computer associated with the individual computer user for display, the links being ordered based on the Internet usage data for the individual computer user.

16. The method of claim 15, wherein the submission popularity data include a number of times the respective distinct query was received in a predefined time period.

17. The method of claim 15, wherein the submission popularity data include a change in a number of times the respective distinct query was received within the predefined time period.

18. The method of claim 15, wherein the submission popularity data include a percentage change in a number of times the distinct query was received within the predefined time period.