Method and system for generating and using a computer user's personal interest profile

• US 6,539,375 B2
• Filed: 08/04/1999
• Issued: 03/25/2003
• Est. Priority Date: 08/04/1998
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Kawasaki, Charles
• Primary Examiner(s): Alam, Hosain T.
• Application Number:
  US09/368,392
• Publication Number:
  US 20010011264A1
• Time in Patent Office: 1,329 Days
• Field of Search: 707/5, 707/6, 707/4, 707/104, 709/217-219, 705/7-11, 705/37, 706/15, 706/16
• US Class Current: 1/1
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3438 monitoring of user actions tracking the activity of the user H04L67/535
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 2201/875 Monitoring of systems including the internet
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A method and system of this invention that provides for profiling a user of the Internet according to predefined categories of interest is described herein. This invention includes scanning content information of an Internet user to generate unknown data and processing unknown data to determine its relevance to predefined categories of interest. This relevance is indicated in a matching rating system, analyzing attributes such as length of time reviewing content information, frequency of encounter, recency, strength and closeness. With comparisons such as these, this invention generates a match of the unknown data with the predefined categories to form a profile of the user that may ultimately be used to target offers to users based upon the profile.

Claims

1. A method for creating an initial interest profile for an Internet user comprising:

scanning content information responsive to use of such content by the Internet user to generate a set of unknown data;

collecting representative data sets of areas of interest to develop a corresponding plurality of predefined categories;

processing the unknown data using a plurality of category based recognizers to compare the unknown data to the plurality of predefined categories to determine the unknown data set'"'"'s relevance to each of the predefined categories; and

generating one or more matches of the unknown data set with the corresponding predefined categories of the category based recognizers and aggregating the one or more matches on a per-data set basis to create said initial interest profile of the user.

2. A method as recited in claim 1 wherein the initial interest profile of the user provides a level of interest for the matched ones of the predefined categories of the category based recognizers.

3. A method as recited in claim 1 wherein the relevance of unknown data to predefined categories is measured in a matching rating system.

4. A method as recited in claim 3, wherein the matching rating system analyzes the unknown data according to length of time reviewing the content information.

5. A method as recited in claim 3, wherein the matching rating system analyzes the unknown data according to frequency of encounter.

6. A method as recited in claim 3, wherein the matching rating system analyzes the unknown data according to a statistical measure of how recently the matching information was reviewed.

7. A method as recited in claim 3, wherein the matching rating system analyzes the unknown data according to an aging algorithm.

8. A method as recited in claim 3, wherein the matching rate indicates strength of the unknown data with respect to the predefined categories.

9. A method as recited in claim 3, wherein the matching rate indicates closeness of the unknown data with respect to the predefined categories.

10. A method as recited in claim 1, wherein one of the predefined categories is related to one of sports, games, business, investing, health, hobbies, technology, arts, politics, social issues, weather and news.

11. A method as recited in claim 1, where the content information is in the form of e-mail.

12. A method as recited in claim 1, where the content information is in the form of Web pages.

13. A method as recited in claim 1, where the content information is in the form of chat streams.

14. A method as recited in claim 1, where the content information is in the form of UseNet Information.

15. A method as recited in claim 1, where the content information is in the form of push information.

16. A method as recited in claim 1, where the method is carried out by an Internet Service Provider.

17. A method as recited in claim 1, wherein the user has an Internet communication device and the method is carried out on the user'"'"'s Internet communication device.

18. A method as recited in claim 1, wherein the user communicates on the Internet through an Internet hub and the method is carried out at the hub.

19. A method as recited in claim 1 further comprising reporting the initial interest profile to a tracker that operates in conjunction with an offer manager to prepare and dispense offers to the user based upon the initial user profile.

20. A method of creating an initial interest profile of an Internet user, comprising:

collecting representative data sets of areas of interest to develop a corresponding plurality of pre-defined categories;

processing the data sets by algorithms and weighted rules to form a first category based recognizer for one of the plurality of pre-defined categories to be used in conjunction with other similarly formed category based recognizers of the other pre-defined categories;

scanning content information responsive to the use by an Internet user to form an unknown data set;

processing the unknown data set using said first category based recognizer of the pre-defined category and other similarly formed category based recognizers of the other pre-defined categories to determine the unknown data set'"'"'s relevance to each of the pre-defined categories; and

generating one or more matches of the unknown data set with the pre-defined categories of the category based recognizers and aggregating the one or more matches on a per-data set basis to create an initial interest profile of the user.

21. A method as recited in claim 20, wherein said plurality of category based recognizers of other predefined categories are formed in a similar manner to said first category based recognizer.

22. A method as recited in claim 20 wherein the recognizer is related to one of sports, games, business, investing, health, hobbies, technology, arts, politics, social issues, weather and news.

23. A method as recited in claim 20, wherein the processing step comprises:

breaking down the content information into discrete pieces of data; and

passing the discrete pieces of data into the category based recognizers to be compared to the corresponding predefined categories to generate one or more matches of the unknown data set with the corresponding predefined categories of the category based recognizers.

24. A method as recited in claim 20, wherein the processing step occurs in real time.

25. A method as recited in claim 20, wherein the processing step is delayed.

26. A method as recited in claim 20 wherein the initial profile is stored on the client installation.

27. A method as recited in claim 20 wherein the initial profile is stored on the server installation.

28. A method as recited in claim 20 wherein the processing of unknown data is circumventable by the user.

29. A system for creating an initial interest profile for a user of the Internet, comprising:

a processor configured to scan content information responsive to the use by an Internet user to generate an unknown data set;

a processor configured to collect representative data sets of areas of interest to develop a corresponding plurality of predefined categories;

a processor configured to process the unknown data using a plurality of category based recognizers corresponding to the plurality of pre-defined categories to determine the unknown data set'"'"'s relevance to each of said predefined categories; and

a processor to generate one or more matches of the unknown data set with the predefined categories and aggregating the one or more matches on a per-data set basis to create said initial interest profile of the user.

30. A system for creating an initial profile of an Internet user, comprising one or more processors configured to:

collect representative data sets of areas of interest to develop a corresponding plurality of pre-defined categories;

process the data sets by algorithms and weighted rules to form a plurality of category based recognizers, one for each of said pre-defined categories to be used;

scan content information responsive to the use of such content by an Internet user to generate an unknown data set;

process the unknown data set against said plurality of category based recognizers to determine the unknown data set'"'"'s relevance to each of the plurality of pre-defined categories; and

generate one or more matches of the unknown data set with the pre-defined categories of the category based recognizers and aggregating the one or more matches on a per-data set basis to create an initial interest profile of the user.

31. A system for creating and using an initial interest profile for an Internet user, comprising one or more processors to:

scan content information responsive to use of such content by the Internet user to generate a set of unknown data;

collect representative data sets of areas of interest to develop a corresponding plurality of predefined categories;

process the unknown data using a plurality of category based recognizers to compare the unknown data to the plurality of pre-defined categories to determine the unknown data set'"'"'s relevance to each of said predefined categories;

generate one or more matches of the unknown data set with the predefined categories and aggregating the one or more matches on a per-data set basis to create said initial interest profile of the user; and

report the initial interest profile to a tracker that operates in conjunction with an offer manager to prepare and dispense offers to the user based upon the user'"'"'s initial interest profile.

32. A system as recited in claim 31, wherein the offers dispensed to the users are dispensed via the Internet.