Product recommendations based on collaborative filtering of user data

• US 7,860,759 B2
• Filed: 08/05/2009
• Issued: 12/28/2010
• Est. Priority Date: 06/29/2005
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Stoppelman, Michael
• Primary Examiner(s): Shah; Amee A
• Application Number:
  US12/536,166
• Publication Number:
  US 20090299880A1
• Time in Patent Office: 510 Days
• Field of Search: 705/26, 705/27
• US Class Current: 705/26.8
• CPC Class Codes: G06F 16/904 Browsing; Visualisation therefor for navigating the web G06F16/954; browsing optimisation for the web G06F16/957
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 30/0641 Shopping interfaces

Abstract

A system gathers user behavior data from a group of web retailers and/or non-web retailers, analyzes the user behavior data to identify product recommendations for products offered by the web retailers, and provides one of the identified product recommendations in connection with a product page associated with one of the web retailers.

Claims

1. A method performed by one or more server devices, the method comprising:

gathering, by one or more processors of the one or more server devices, user behavior data from a plurality of web retailers;

analyzing, by one or more processors of the one or more server devices, the user behavior data to identify product recommendations for products offered by the plurality of web retailers;

receiving, by one or more processors of the one or more server devices, a request associated with a web retailer, of the plurality of web retailers, and a product provided by the web retailer;

identifying, by one or more processors of the one or more server devices and based on the request, one or more product recommendations, of the product recommendations, associated with the product, based on a plurality of products offered by the web retailer; and

providing, by one or more processors of the one or more server devices, at least one of the one or more product recommendations in connection with a product page associated with the product.

2. A method performed by one or more server devices, the method comprising:

receiving, by one or more processors of the one or more server devices, a request associated with a web retailer and a product provided by the web retailer;

determining, by one or more processors of the one or more server devices, a plurality of products offered for sale by the web retailer;

identifying, by one or more processors of the one or more server devices and in response to the request, one or more product recommendations relating to the product, based on user behavior data associated with a plurality of web retailers;

identifying, by one or more processors of the one or more server devices, at least one of the one or more product recommendations based on the plurality of products offered for sale by the web retailer; and

providing, by one or more processors of the one or more server devices, the at least one of the one or more product recommendations and a product page associated with the product.

3. The method of claim 2, where the determining the plurality of products offered for sale by the web retailer comprises at least one of:

crawling a web site of the web retailer, and identifying the plurality of products based on information on the crawled site;

or

analyzing a site map of the web site of the web retailer, and identifying the plurality of products based on information obtained by analyzing the site map.

4. The method of claim 2, where the providing the at least one of the one or more product recommendations and the product page comprises:

providing at least one link, within the product page, corresponding to the at least one of the one or more product recommendations.

5. The method of claim 4, further comprising:

receiving, from a client device, selection of the at least one link; and

redirecting the client device to another product page that is associated with a product corresponding to the at least one of the one or more product recommendations.

6. The method of claim 4, further comprising:

charging the web retailer based on one or more selections of the at least one link.

7. The method of claim 2, where the providing the at least one of the one or more product recommendations and the product page, comprises:

providing statistical information associated with purchase activity of one or more customers, the statistical information being based on the one or more customers accessing the product page.

8. The method of claim 2, where the identifying the at least one of the one or more product recommendations comprises:

receiving information associated with product pages accessed by one or more users from a plurality of web retailers and information associated with product information pages accessed by one or more users from a plurality of non-web retailers; and

identifying the at least one of the one or more product recommendations based on the plurality of products offered for sale by the web retailer and the received information.

9. A system comprising:

one or more server devices comprising;

means for receiving a request, the request including information identifying a web retailer and a product page of a product provided by the web retailer;

means for determining at least one other product offered for sale by the web retailer;

means for identifying, in response to the request, a plurality of product recommendations relating to the product based on user behavior data gathered from a plurality of web retailers;

means for identifying one or more of the plurality of product recommendations based on the at least one other product offered for sale by the web retailer; and

means for providing the one or more of the plurality of product recommendations and the product page.

10. The system of claim 9, where the means for providing the one or more of the plurality of product recommendations and the product page comprises:

means for providing a link for each of the one or more of the plurality of product recommendations.

11. The system of claim 10, further comprising:

means for receiving selection of the link by a client device; and

means for redirecting the client device to another product page associated with a product that is associated with one of the one or more of the plurality of product recommendations.

12. The system of claim 11, further comprising:

means for charging the web retailer in response to the selection of the link.

13. The system of claim 9, where the one or more of the plurality of product recommendations are provided in a pop-up window in conjunction with the product page.

14. The system of claim 9, where the means for providing the one or more of the plurality of product recommendations comprises:

means for providing percentage information related to purchase activity of one or more users in response to the one or more users accessing the product page.

15. A system, comprising:

a memory to store instructions; and

a processor to execute the instructions in the memory to;

gather user behavior data associated with a plurality of web retailers,

receive, from a client device, a request associated with a web retailer and a product page of a product provided by the web retailer,

identify products offered for sale by the web retailer,

determine, based on the request and the gathered user behavior data, product recommendations that are associated with the product,

identify at least one of the product recommendations that matches one of the products offered for sale by the web retailer, and

provide the at least one of the product recommendations to the client device.

16. The system of claim 15, where the processor is further to:

gather information associated with at least one of one or more product information pages accessed by at least one user, or an amount of time that the at least one user spent accessing the one or more product information pages,

where, when determining the product recommendations, the processor is further to;

identify, from the gathered information, another product as recommended for the product if the other product occurs in conjunction with the product a threshold number of times.

17. The system of claim 15, where the processor is further to:

receive information relating to user purchase activity, and

identify, based on the received information, products that users purchased together,

where, the processor is to determine the product recommendations that are associated with the product based on the identified products that users purchased together.

18. The system of claim 15, where, when providing the at least one of the product recommendations, the processor is further to:

provide the at least one of the product recommendations as at least one link within the product page,

where the processor is further to;

receive selection of the at least one link, and

redirect the client device to another product page, corresponding to the at least one of the product recommendations.

19. The system of claim 15, where, when providing the at least one of the product recommendations, the processor is further to:

provide information regarding a percentage of customers that purchased another product after accessing the product page.

20. The system of claim 15, where the processor is further to:

receive information associated with one or more product pages accessed by at least one user, or an amount of time that the at least one user spent accessing the one or more product pages,

store the received information, and

analyze the received information to identify one or more product recommendations related to one or more products offered for sale by one or more web retailers.

21. The system of claim 15, where, when identifying the products offered for sale by the web retailer, the processor is further to at least one of:

crawl a web site of the web retailer, and identify the products based on information on the crawled site;

or

analyze a site map of the web site of the web retailer, and identify the products based on information obtained by analyzing the site map.