AUTOMATIC, PERSONALIZED ONLINE INFORMATION AND PRODUCT SERVICES

• US 20100122178A1
• Filed: 01/22/2010
• Published: 05/13/2010
• Est. Priority Date: 12/28/1999
• Status: Active Grant

• Current Assignee: Personalized User Model LLP
• Original Assignee: Personalized User Model LLP
• Inventors: Konig, Yochai, Twersky, Roy, Berthold, Michael R.
• Granted Patent: US 8,301,764 B2
• Time in Patent Office: Days
• US Class Current: 715/738
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/53 using third party service providers
• CPC Class Codes: H04L 67/55 Push-based network services
• CPC Class Codes: H04L 67/75 Indicating network or usage conditions on the user display
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing

Abstract

A method for providing automatic, personalized information services to a computer user includes the following steps: transparently monitoring user interactions with data during normal use of the computer; updating user-specific data files including a set of user-related documents; estimating parameters of a learning machine that define a User Model specific to the user, using the user-specific data files; analyzing a document to identify its properties; estimating the probability that the user is interested in the document by applying the document properties to the parameters of the User Model; and providing personalized services based on the estimated probability. Personalized services include personalized searches that return only documents of interest to the user, personalized crawling for maintaining an index of documents of interest to the user; personalized navigation that recommends interesting documents that are hyperlinked to documents currently being viewed; and personalized news, in which a third party server customized its interaction with the user. The User Model includes continually-updated measures of user interest in words or phrases, web sites, topics, products, and product features. The measures are updated based on both positive examples, such as documents the user bookmarks, and negative examples, such as search results that the user does not follow. Users are clustered into groups of similar users by calculating the distance between User Models.

Claims

1. A computer-implemented method for providing personalized information services to a user, the method comprising:

displaying a web page using a browser program running on the computer;

selecting a plurality of related documents based on said web page and based on an estimated probability that the related documents are of interest to the user; and

presenting said selected related documents to the user.

2. The method of claim 1, further comprising:

transparently monitoring user interactions with data while the user is engaged in normal use of said browser program;

analyzing the monitored data to determine documents of interest to the user;

estimating parameters of a user-specific learning machine based at least in part on the documents of interest to the user,

wherein selecting said related documents comprises for each of a plurality of related documents;

identifying properties of the related document, and applying the identified properties of the related document to the user-specific learning machine to estimate a probability that the related document is of interest to the user.

3. The method of claim 2, further comprising analyzing the monitored data to determine documents not of interest to the user, and wherein estimating parameters of a user-specific learning machine further comprises estimating parameters of a user-specific learning machine based at least in part on the documents not of interest to the user.

4. The method of claim 2, wherein monitoring user interactions with data for a document comprises monitoring at least one type of data selected from the group consisting of information about the document, whether the user viewed the document, information about the user'"'"'s interaction with the document, context information, the user'"'"'s degree of interest in the document, time spent by the user viewing the document, whether the user followed at least one link contained in the document, and a number of links in the document followed by the user.

5. The method of claim 2, wherein said plurality of related documents correspond to a respective plurality of products.

6. The method of claim 2, wherein using the estimated probabilities for the respective plurality of related documents to present at least a portion of the related documents to the user comprises presenting to the user at least said portion of the related documents based on the estimated probability that the related document is of interest to the user and the relevance of the related document to the web page displayed to the user.

7. The method of claim 2, wherein identifying properties of the retrieved document comprises identifying properties selected from the properties consisting of a topic associated with the related document, at least one product feature extracted from the related document, an author of the related document, and an age of the related document.