Item recommendations

Patent metadata

Field	Value
Publication number	US-10970770-B2
Application number	US-201816118127-A
Country	US
Kind code	B2
Filing date	Aug 30, 2018
Priority date	Jun 29, 2005
Publication date	Apr 6, 2021
Grant date	Apr 6, 2021

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.

First claim

What is claimed is:

1. A computer-implemented method for generating product recommendations using collaborative filtering, comprising:
receiving, by one or more product recommendation system servers and from multiple web retailer servers that are associated with a set of web retailers, user behavior data relating to user non-purchase activity on product information pages that are provided by the multiple web retailer servers that are associated with the set of web retailers;
identifying, by the one or more product recommendation system servers and for each product that is associated with the product information pages that are provided by the multiple web retailer servers that are associated with a set of web retailers, a different product that is associated with the product information pages, and a number of times that one or more of the set of web retailers promotes the product with the different product on product information pages that users access during online sessions;
in response to determining that one or more of the set of web retailers has promoted a first product with a second product at least a predetermined threshold number of times on product information pages that users access during online sessions, determining, by the one or more product recommendation system servers that the first product is to be promoted with the second product in product information pages that are provided by one or more different web retailer servers that are associated with a different web retailer that is not included in the set of web retailers; and
generating and providing, by the one or more product recommendation system server and to the one or more different web retailer servers that are associated with the different web retailer that is not included in the set of web retailers, computer code to be inserted in one or more web pages of the different web retailer that is not included in the set of web retailers, the computer code, when executed by a web browser of a potential customer of the different web retailer, generating a product information page for the first product that includes a hyperlink to a product information page for the second product.

2. The method of claim 1 , wherein the product information pages includes review pages, price comparison pages, and product description pages.

3. The method of claim 1 , comprising:
receiving, by the one or more product recommendation system servers, additional user behavior data relating to user purchase activity on product information pages that are provided by the multiple web retailer servers that are associated with the set of web retailers.

4. The method of claim 1 , wherein the different product is identified in response to determining that the product and the different product have been purchased together.

5. The method of claim 1 , comprising:
determining that an amount of the user behavior data exceeds a threshold amount; and
wherein the computer code is generated and provided in response to determining that the amount of the user behavior data exceeds the threshold amount.

6. A system for generating product recommendations using collaborative filtering, the system comprising:
one or more computers; and
one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
receiving, by one or more product recommendation system servers and from multiple web retailer servers that are associated with a set of web retailers, user behavior data relating to user non-purchase activity on product information pages that are provided by the multiple web retailer servers that are associated with the set of web retailers;
identifying, by the one or more product recommendation system servers and for each product that is associated with the product information pages that are provided by the multiple web retailer servers that are associated with a set of web retailers, a different product that is associated with the product information pages, and a number of times that one or more of the set of web retailers promotes the product with the different product on product information pages that users access during online sessions;
in response to determining that one or more of the set of web retailers has promoted a first product with a second product at least a predetermined threshold number of times on product information pages that users access during online sessions, determining, by the one or more product recommendation system servers that the first product is to be promoted with the second product in product information pages that are provided by one or more different web retailer servers that are associated with a different web retailer that is not included in the set of web retailers; and
generating and providing, by the one or more product recommendation system server and to the one or more different web retailer servers that are associated with the different web retailer that is not included in the set of web retailers, computer code to be inserted in one or more web pages of the different web retailer that is not included in the set of web retailers, the computer code, when executed by a web browser of a potential customer of the different web retailer, generating a product information page for the first product that includes a hyperlink to a product information page for the second product.

7. The system of claim 6 , wherein the product information pages includes review pages, price comparison pages, and product description pages.

8. The system of claim 6 , wherein the operations comprise:
receiving, by the one or more product recommendation system servers, additional user behavior data relating to user purchase activity on product information pages that are provided by the multiple web retailer servers that are associated with the set of web retailers.

9. The system of claim 6 , wherein the different product is identified in response to determining that the product and the different product have been purchased together.

10. The system of claim 6 , wherein the operations comprise:
determining that an amount of the user behavior data exceeds a threshold amount; and
wherein the computer code is generated and provided in response to determining that the amount of the user behavior data exceeds the threshold amount.

11. A non-transitory computer-readable storage device encoded with computer program instructions that, when executed by one or more computers, cause the one or more computers to perform operations for generating product recommendations using collaborative filtering, the operations comprising:
receiving, by one or more product recommendation system servers and from multiple web retailer servers that are associated with a set of web retailers, user behavior data relating to user non-purchase activity on product information pages that are provided by the multiple web retailer servers that are associated with the set of web retailers;
identifying, by the one or more product recommendation system servers and for each product that is associated with the product information pages that are provided by the multiple web retailer servers that are associated with a set of web retailers, a different product that is associated with the product information pages, and a number of times that one or more of the set of web retailers promotes the product with the different product on product information pages that users access during online sessions;
in response to determining that one or more of the set of web retailers has promoted a first product with a second product at least a predetermined threshold number of times on product information pages that users acces

Assignees

• Google Llc

Inventors

• Stoppelman Michael

Classifications

• G06Q30/0269

  based on user profile or attribute · CPC title

• G06Q30/0641

  utilising user interfaces specially adapted for shopping · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06F16/904

  Browsing; Visualisation therefor (for navigating the web G06F16/954; browsing optimisation for the web G06F16/957) · CPC title

• G06Q30/0255

  based on user history · CPC title