Search results based on user and result profiles

• US 9,529,915 B2
• Filed: 06/16/2011
• Issued: 12/27/2016
• Est. Priority Date: 06/16/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Lymberopoulos, Dimitrios, Wu, Qiang, Liu, Jie, Jiang, Li
• Primary Examiner(s): KUDDUS, DANIEL A
• Application Number:
  US13/161,527
• Publication Number:
  US 20120323876A1
• Time in Patent Office: 2,021 Days
• Field of Search: 707/732, 707/752, 707/784
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A method includes receiving a search query from a user at a search engine. The method also includes performing a search responsive to the search query to obtain a set of results. The set of results is ordered at least partially based on a distance between a profile of a user and a profile of each result in the ordered set of results. At least one profile of a result is based on an aggregate of a plurality of user profiles.

Claims

1. A computer-implemented method comprising:

receiving a search query from a particular user at a search engine, the particular user having a particular profile comprising a probability distribution function;

performing a search responsive to the search query to obtain a set of results, each result having an associated profile comprising a probability distribution function, wherein the probability distribution function of each result is generated by aggregating probability distribution functions generated for each of a plurality of users who clicked on or otherwise indicated an interest in the result, and wherein the set of results includes a business listing having a profile comprising a probability distribution function, said probability distribution function for the business listing being computed by identifying a plurality of clicks associated with a website of the business, identifying a plurality of users based on the identified plurality of clicks, and determining the probability distribution function of the business listing by aggregating the probability distribution functions generated for the identified plurality of users;

determining, for each result, a distance between the probability distribution function of the particular user profile and the probability distribution function of the result profile; and

ordering the set of results based on the determined distances.

2. The method of claim 1, further comprising determining the profile of the particular user based on one or more actions associated with the particular user.

3. The method of claim 2, wherein the one or more actions include a click action detected by the search engine.

4. A computer system, comprising:

a processor; and

a memory storing instructions executable by the processor to;

store information received at a search engine from a plurality of users, the stored information including user specific click log data corresponding to each user of the plurality of users;

determine a probability distribution function for each user of the plurality of users based on the stored information including the user specific click log data corresponding to each user;

store the probability distribution function for each of the plurality of users in a user store;

determine a probability distribution function associated with each business of a plurality of businesses, wherein each probability distribution function associated with a corresponding business is generated by aggregating probability distribution functions generated for each of a plurality of users whose probability distribution functions are stored in the user store and who clicked on or otherwise indicated an interest in the business;

store the probability distribution function for each particular business in a search index;

receive a search query from a particular user; and

perform a search responsive to the search query from the particular user based on the search index to obtain a set of results, the set of results identifying at least two of the plurality of businesses; and

ordering the set of results at least partially based on a distance between the probability distribution function of the particular user and the probability distribution function of each business identified in the set of results.

5. The computer system of claim 4, further comprising a click log to store the information, the click log including at least one of a location-segmented click log, a time-segmented click log, or a day-segmented click log.

6. The computer system of claim 4, further comprising the search index.

7. The computer system of claim 4, further comprising the search engine.

8. The computer system of claim 5, wherein the instructions are further executable by the processor to segment the click log based on location.

9. The computer system of claim 5, wherein the instructions are further executable by the processor to segment the click log based on time.

10. The computer system of claim 5, wherein the instructions are further executable by the processor to segment the click log based on day.

11. A computer system, comprising:

a processor; and

a memory storing instructions executable by the processor to;

receive a search query from a particular user at a search engine, wherein the search query includes one or more search terms, a user identifier of the particular user, and a user location of the particular user;

determine a business category based on the one or more search terms;

perform a search responsive to the query to obtain a set of results, wherein the set of results identifies a plurality of businesses associated with the business category and relevant to the user location;

retrieve a probability distribution function associated with the particular user based on the user identifier and the location, wherein the probability distribution function associated with the particular user is based on user specific click log data;

retrieve, for each business of the plurality of businesses, a business probability distribution function, wherein each business probability distribution function is generated by aggregating probability distribution functions generated for each of a plurality of users who clicked on or otherwise indicated an interest in the business;

determine a distance associated with each business, the distance being based on the distance between the probability distribution function associated with the particular user and the business probability distribution function associated with the business;

order the set of results at least partially based on the distance associated with each business; and

display the ordered set of results to the particular user.

12. The system of claim 11, wherein the search query further includes a timestamp.

13. The system of claim 12, wherein the probability distribution function associated with the particular user is weighted based on the timestamp, the user location, or any combination thereof.

14. The system of claim 11, wherein the probability distribution function associated with the business represents an average user who clicked on or otherwise indicated an interest in the business.

15. The system of claim 11, wherein the search query is received at a particular time of day, wherein user clicks made at a similar time of day are weighted more heavily than user clicks at other times of day, and wherein the search engine has access to age information regarding the users.