Method, system, and storage device for recommending products utilizing category attributes

• US 8,612,306 B1
• Filed: 07/29/2009
• Issued: 12/17/2013
• Est. Priority Date: 07/29/2009
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Mukherjee, Rajat, Das, Abhinandan S., Moisa, Dan, Low, Jennifer Liu
• Primary Examiner(s): ALLEN, WILLIAM J
• Application Number:
  US12/511,289
• Time in Patent Office: 1,602 Days
• Field of Search: 705 261- 272, 707705-788
• US Class Current: 705/26.5
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0253 During e-commerce, i.e. online transactions
• CPC Class Codes: G06Q 30/0627 using item specifications
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for related search suggestions for products. In one aspect, a method includes receiving a query for searching documents wherein the query specifies a first product. A number of occurrences of the first product in a plurality of prior queries of the documents submitted by users is determined. A product category for the first product is determined based on one or more attributes associated with the first product, the category having a predetermined plurality of category attributes. A suggested product is selected wherein the suggested product is associated with attributes that satisfy the category attributes.

Claims

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

receiving a query from a client device wherein the query specifies a first product by specifying a product brand and a product model;

determining, using the product brand and the product model, one or more specific product attributes associated with the first product;

determining a respective correspondence between the one or more specific product attributes associated with the first product and one or more category attributes associated with one or more product categories, each product category having a predetermined plurality of category attributes;

identifying, by data processing apparatus, a product category associated with the first product based on the determined respective correspondence;

identifying a first set of one or more second products, the first set of second products having one or more attributes corresponding to the one or more category attributes associated with the product category of the first product;

calculating, by data processing apparatus, respective distances between the one or more specific product attributes of the first product and corresponding attributes of products in the first set of second products;

determining that one or more of the calculated respective distances satisfy a threshold;

in response to the determining, identifying at least one product in the first set of second products as a suggested product based on the determination that the threshold is satisfied by one of the calculated respective distances; and

providing the at least one identified product as a suggestion in response to the query.

2. The method of claim 1 in which the query comprises one or more of a product brand and a product model.

3. The method of claim 2 in which the query comprises the product brand, and wherein the method further comprises identifying a popular product model associated with the product brand as the suggested product.

4. The method of claim 1 in which the category attributes comprise attributes that occur in one or more of the prior queries.

5. The method of claim 1 in which one of the category attributes is received from one or more of:

one of the client devices, a system administrator, a merchandiser, and a manufacturer of the product.

6. The method of claim 1 wherein identifying the suggested product is based on a count of a number of times documents containing the suggested product were selected by users from search results for one or more of the prior queries.

7. The method of claim 1 in which identifying the suggested product is based on a promotion associated with the suggested product.

8. The method of claim 1, further comprising providing a price for the suggested product.

9. The method of claim 8 in which receiving a user selection of the suggested product initiates a process in which a user can purchase the suggested product.

10. The method of claim 8 in which receiving a user selection of the suggested product'"'"'s price initiates a process in which a user can view one or more of product ratings, product reviews, product previews and product comparisons.

11. The method of claim 1, further comprising receiving input selecting the suggested product and causing the documents to be searched for the suggested product.

12. The method of claim 1 in which the query comprises a product brand and a product model, and wherein identifying the second product as a suggested product comprises selecting one or more other product models of the product brand where a distance between attributes of the other product models and the product model satisfies a criterion.

13. A computer program product, stored on a computer-readable storage device which, when executed, is operable to cause data processing apparatus to perform operations comprising:

receiving a query from a client device wherein the query specifies a first product by specifying a product brand and a product model;

determining, using the product brand and the product model, one or more specific product attributes associated with the first product;

determining a respective correspondence between the one or more specific product attributes associated with the first product and one or more category attributes associated with one or more product categories, each product category having a predetermined plurality of category attributes;

identifying, by data processing apparatus, a product category associated with the first product based on the determined respective correspondence;

identifying a first set of one or more second products, the first set of second products having one or more attributes corresponding to the one or more category attributes associated with the product category of the first product;

calculating, by data processing apparatus, respective distances between the one or more specific product attributes of the first product and corresponding attributes of products in the first set of second products;

determining that one or more of the calculated respective distances satisfy a threshold;

in response to the determining, identifying at least one product in the first set of second products as a suggested product based on the determination that the threshold is satisfied by one of the calculated respective distances; and

providing the at least one identified product as a suggestion in response to the query.

14. The program product of claim 13 in which the query comprises one or more of a product brand and a product model.

15. The program product of claim 14 in which the query comprises the product brand, and wherein the operations further comprise identifying a popular product model associated with the product brand as the suggested product.

16. The program product of claim 13 in which the category attributes comprise attributes that occur in one or more of the prior queries.

17. The program product of claim 13 in which one of the category attributes is received from one or more of:

one of the client devices, a system administrator, a merchandiser, and a manufacturer of the product.

18. The program product of claim 13 wherein identifying the suggested product is based on a count of a number of times documents containing the suggested product were selected by users from search results for one or more of the prior queries.

19. The program product of claim 13 in which identifying the suggested product is based on a promotion associated with the suggested product.

20. The program product of claim 13, further comprising providing a price for the suggested product.

21. The program product of claim 20 in which receiving a user selection of the suggested product initiates a process in which a user can purchase the suggested product.

22. The program product of claim 20 in which receiving a user selection of the suggested product'"'"'s price initiates a process in which a user can view one or more of product ratings, product reviews, product previews and product comparisons.

23. The program product of claim 13, further comprising receiving input selecting the suggested product and causing the documents to be searched for the suggested product.

24. The program product of claim 13 in which the query comprises a product brand and a product model, and wherein identifying the second product as a suggested product comprises selecting one or more other product models of the product brand where a distance between attributes of the other product models and the product model satisfies a criterion.

25. A system comprising:

a computer readable medium including a program product; and

one or more processors configured to execute the program product and perform operations comprising;

receiving a query from a client device wherein the query specifies a first product by specifying a product brand and a product model;

determining, using the product brand and the product model, one or more specific product attributes associated with the first product;

determining a respective correspondence between the one or more specific product attributes associated with the first product and one or more category attributes associated with one or more product categories, each product category having a predetermined plurality of category attributes;

identifying, by data processing apparatus, a product category associated with the first product based on the determined respective correspondence;

identifying a first set of one or more second products, the first set of second products having one or more attributes corresponding to the one or more category attributes associated with the product category of the first product;

calculating, by data processing apparatus, respective distances between the one or more specific product attributes of the first product and corresponding attributes of products in the first set of second products;

determining that one or more of the calculated respective distances satisfy a threshold;

in response to the determining, identifying at least one product in the first set of second products as a suggested product based on the determination that the threshold is satisfied by one of the calculated respective distances; and

providing the at least one identified product as a suggestion in response to the query.

26. The system of claim 25 in which the query comprises one or more of a product brand and a product model.

27. The system of claim 26 in which the query comprises the product brand, and wherein the operations further comprise identifying a popular product model associated with the product brand as the suggested product.

28. The system of claim 25 in which the category attributes comprise attributes that occur in one or more of the prior queries.

29. The system of claim 25 in which one of the category attributes is received from one or more of:

one of the client devices, a system administrator, a merchandiser, and a manufacturer of the product.

30. The system of claim 25 wherein identifying the suggested product is based on a count of a number of times documents containing the suggested product were selected by users from search results for one or more of the prior queries.

31. The system of claim 25 in which identifying the suggested product is based on a promotion associated with the suggested product.

32. The system of claim 25, further including operations comprising providing a price for the suggested product.

33. The system of claim 32 in which receiving a user selection of the suggested product initiates a process in which a user can purchase the suggested product.

34. The system of claim 32 in which receiving a user selection of the suggested product'"'"'s price initiates a process in which a user can view one or more of product ratings, product reviews, product previews and product comparisons.

35. The system of claim 25, further including operations comprising receiving input selecting the suggested product and causing the documents to be searched for the suggested product.

36. The system of claim 25 in which the query comprises a product brand and a product model, and wherein identifying the second product as a suggested product comprises selecting one or more other product models of the product brand where a distance between attributes of the other product models and the product model satisfies a criterion.