Utilizing information about user-visited places to recommend novel spaces to explore

• US 8,782,034 B1
• Filed: 08/17/2011
• Issued: 07/15/2014
• Est. Priority Date: 08/17/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Moczydlowski, Wojciech
• Primary Examiner(s): PYO, MONICA M
• Application Number:
  US13/212,088
• Time in Patent Office: 1,063 Days
• Field of Search: 707/706, 707/713, 707/751, 707/736
• US Class Current: 707/713
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering

Abstract

A system and machine-implemented method for recommending a point of interest includes the steps of obtaining interest information indicating an interest of each of multiple users for a multiple points of interest, obtaining attributes for constraining a search of the multiple points of interest, identifying a point of interest that satisfies the attributes and has the least similarity to the interest information for a first user, and providing information about the identified point of interest for display to the first user.

Claims

1. A machine-implemented method for recommending a point of interest, the method comprising:

obtaining interest information for a plurality of users, including a first user, wherein the interest information for each of the plurality of users indicates that user'"'"'s interest in a plurality of points of interest;

obtaining a plurality of attributes for constraining a search of the plurality of points of interest;

identifying, from among the plurality of points of interest and based on the interest information for the plurality of users, a point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user; and

providing information about the identified point of interest for display to the first user,

wherein identifying the point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user is based on the equation;

2. The machine-implemented method of claim 1, wherein the interest information includes interest information obtained via an online map service and interest information obtained via an online search engine.

3. The machine-implemented method of claim 1, wherein the interest information further includes interest information for items other than the plurality of points of interest.

4. The machine-implemented method of claim 1, wherein the attributes include one or more of the following:

a geographical area to which recommended points of interest are to be limited,

a ceiling on an expected price of a meal,

a minimum quality of food, and

a minimum quality of service.

5. The machine-implemented method of claim 1, wherein identifying a point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user further comprises:

identifying a subset of the plurality of points of interest that satisfy the attributes and for which no interest information has been obtained from the first user;

determining a similarity between each point of interest in the subset and the interest information for the first user; and

identifying a point of interest in the subset having the least similarity as the point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user.

6. A machine-implemented method for recommending a point of interest, the method comprising:

obtaining interest information for a plurality of users, including a first user, wherein the interest information for each of the plurality of users indicates that user'"'"'s interest in a plurality of points of interest;

obtaining a plurality of attributes for constraining a search of the plurality of points of interest;

identifying, based on the interest information for the plurality of users, a subset of the plurality of users included in the plurality of users that have respective interest information with the least similarity to the interest information for the first user;

identifying, from among the plurality of points of interest that satisfy the attributes, a point of interest that is most popular with the subset of the plurality of users; and

providing information about the identified point of interest for display to the first user,

wherein identifying the point of interest that is most popular with the subset of the plurality of users is based on the equation;

7. The machine-implemented method of claim 6, wherein the interest information includes interest information obtained via an online map service and interest information obtained via an online search engine.

8. The machine-implemented method of claim 6, wherein the interest information further includes interest information for items other than the plurality of points of interest.

9. The machine-implemented method of claim 6, wherein the attributes include one or more of the following:

a geographical area to which recommended points of interest are to be limited,

a ceiling on an expected price of a meal,

a minimum quality of food, and

a minimum quality of service.

10. A system for recommending a location, the system comprising:

one or more processors; and

a machine-readable medium comprising instructions stored therein, which when executed by the processors, cause the processors to perform operations comprising;

obtaining interest information for a plurality of users, including a first user, wherein the interest information for each of the plurality of users indicates that user'"'"'s interest in a plurality of points of interest;

obtaining a plurality of attributes for constraining a search of the plurality of points of interest;

identifying, from among the plurality of points of interest and based on the interest information for the plurality of users, a point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user; and

providing information about the identified point of interest for display to the first user,

wherein identifying the point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user is based on the equation;

11. The system of claim 10, wherein the interest information includes interest information obtained via an online map service and interest information obtained via an online search engine.

12. The system of claim 10, wherein the interest information further includes interest information for items other than the plurality of points of interest.

13. The system of claim 10, wherein the attributes include one or more of the following:

a geographical area to which recommended points of interest are to be limited,

a ceiling on an expected price of a meal,

a minimum quality of food, and

a minimum quality of service.

14. A system for recommending a location, the system comprising:

one or more processors; and

a machine-readable medium comprising instructions stored therein, which when executed by the processors, cause the processors to perform operations comprising;

obtaining interest information for a plurality of users, including a first user, wherein the interest information for each of the plurality of users indicates that user'"'"'s interest in a plurality of points of interest;

obtaining a plurality of attributes for constraining a search of the plurality of points of interest;

identifying, based on the interest information for the plurality of users, a subset of the plurality of users that have respective interest information with the least similarity to the interest information for the first user;

identifying, from among the plurality of points of interest that satisfy the attributes, a point of interest that is most popular with the subset of the plurality of users; and

providing information about the identified point of interest for display to the first user,

wherein identifying the point of interest that is most popular with the subset of the plurality of users is based on the equation;

15. The system of claim 14, wherein the interest information includes interest information obtained via an online map service and interest information obtained via an online search engine.

16. The system of claim 14, wherein the interest information further includes interest information for items other than the plurality of points of interest.

17. The system of claim 14, wherein the attributes include one or more of the following:

a geographical area to which recommended points of interest are to be limited,

a ceiling on an expected price of a meal,

a minimum quality of food, and

a minimum quality of service.

18. A non-transitory machine-readable medium comprising instructions stored therein, which when executed by a machine, cause the machine to perform operations comprising:

obtaining interest information for a plurality of users, including a first user, wherein the interest information for each of the plurality of users indicates that user'"'"'s interest in a plurality of points of interest;

obtaining a plurality of attributes for constraining a search of the plurality of points of interest;

identifying, from among the plurality of points of interest and based on the interest information for the plurality of users, a point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user; and

providing information about the identified point of interest for display to the first user,

wherein identifying the point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user is based on the equation;

19. The non-transitory machine-readable medium of claim 18, wherein the interest information includes interest information obtained via an online map service and interest information obtained via an online search engine.

20. The non-transitory machine-readable medium of claim 18, wherein the interest information further includes interest information for items other than the plurality of points of interest.

21. The non-transitory machine-readable medium of claim 18, wherein the attributes include one or more of the following:

a geographical area to which recommended points of interest are to be limited,

a ceiling on an expected price of a meal,

a minimum quality of food, and

a minimum quality of service.

22. A non-transitory machine-readable medium comprising instructions stored therein, which when executed by a machine, cause the machine to perform operations comprising:

obtaining interest information for a plurality of users, including a first user, wherein the interest information for each of the plurality of users indicates that user'"'"'s interest in a plurality of points of interest, and the plurality of users including a first user;

obtaining a plurality of attributes for constraining a search of the plurality of points of interest;

identifying, based on the interest information for the plurality of users, a subset of the plurality of users that have respective interest information with the least similarity to the interest information for the first user;

identifying, from among the plurality of points of interest that satisfy the attributes, a point of interest that is most popular with the subset of the plurality of users; and

providing information about the identified point of interest for display to the first user,

wherein identifying the point of interest that is most popular with the subset of the plurality of users is based on the equation;

23. The non-transitory machine-readable medium of claim 22, wherein the interest information includes interest information obtained via an online map service and interest information obtained via an online search engine.

24. The non-transitory machine-readable medium of claim 22, wherein the interest information further includes interest information for items other than the plurality of points of interest.

25. The non-transitory machine-readable medium of claim 22, wherein the attributes include one or more of the following:

a geographical area to which recommended points of interest are to be limited,

a ceiling on an expected price of a meal,

a minimum quality of food, and

a minimum quality of service.

26. A machine-implemented method for recommending a point of interest, the method comprising:

obtaining interest information for a plurality of users, including a first user, wherein the interest information for each of the plurality of users indicates that user'"'"'s interest in a plurality of points of interest;

obtaining a plurality of attributes for constraining a search of the plurality of points of interest;

identifying, from among the plurality of points of interest and based on the interest information for the plurality of users, a point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user;

providing information about the identified point of interest for display to the first user,

wherein identifying a point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user further comprises;

identifying a subset of the plurality of points of interest that satisfy the attributes and for which no interest information has been obtained from the first user;

determining a similarity between each point of interest in the subset and the interest information for the first user; and

identifying a point of interest in the subset having the least similarity as the point of interest that satisfies the attributes and that has the least similarity to the interest information for the first user, and

wherein determining a similarity between each point of interest in the subset and the interest information for the first user further comprises;

determining, for a first point of interest in the subset, similarity scores between the first point of interest and points of interest for which interest information has been obtained for the first user; and

computing a weighted average of the similarity scores, wherein the weights are determined from the interest information for the points of interest for which interest information has been obtained for the first user.