System, method, and article of manufacture for utilizing implicit ratings in collaborative filters

• US 6,108,493 A
• Filed: 10/07/1996
• Issued: 08/22/2000
• Est. Priority Date: 10/08/1996
• Status: Expired due to Term

• Current Assignee: Regents of The University of Minnesota (University of Minnesota)
• Original Assignee: Regents of The University of Minnesota (University of Minnesota)
• Inventors: Konstan, Joseph A., Riedl, John T., Miller, Bradley N.
• Primary Examiner(s): Asta, Frank J.
• Assistant Examiner(s): PIERCE, IVAN
• Application Number:
  US08/725,580
• Time in Patent Office: 1,415 Days
• Field of Search: 395/200.47, 395/200.48, 395/200.49, 395/61, 307/52, 364/526.26, 380/9, 380/49, 707/2, 707/4
• US Class Current: 709/219
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation

Abstract

A prediction information system for use between a user and an electronic rating broker is provided. The prediction information system includes a user interface for presenting items as information to the user. An input mechanism receives data input by the user. A processor in cooperation with the user interface and the input mechanism performs an algorithm for: obtaining a particular implicit measure, generating an implicit rating as a function of the particular implicit measure, submitting the implicit rating to the rating broker, receiving prediction results for other items from the rating broker, and presenting the prediction results to the user through the user interface. In addition, a method for operating an electronic rating broker on a computer system in order to provide prediction information to a user based on implicit ratings is provided. Also, a storage device readable by a computer system for implementing this method is provided.

Claims

1. A prediction information system for use between a user and a collaborative filtering electronic rating broker, comprising:

(a) user interface means for presenting items as information to the user;

(b) input means for receiving data input by the user;

(c) processing means, operatively coupled to the user interface means and input means, for obtaining a particular implicit measure, generating an implicit rating as a function of the particular implicit measure, submitting the implicit rating to the collaborative filtering rating broker, receiving prediction results for other items from the collaborative filtering, rating broker, and presenting the prediction results to the user on the user interface means.

2. The prediction information system of claim 1 wherein the processing means comprises means for obtaining the particular implicit measure from the user through the input means based on criteria selected from a group consisting of:

user time spent viewing a particular item, user time spent listening to a particular item, and user time spent sampling a particular item.

3. The prediction information system of claim 1 wherein the processing means comprises means for obtaining the particular implicit measure from a user through the input means based on subsequent actions taken, the subsequent actions taken being selected from a group consisting of:

a user viewing details of a particular item after viewing only a title, saving a particular item, forwarding a particular item, saving a return address of a particular item, deleting a particular item, replying to a particular item, and printing a particular item.

4. The prediction information system of claim 1 wherein the input means comprises means for obtaining a plurality of implicit measures including the particular implicit measure and the processing means comprises means for generating the implicit rating as a function of the plurality of implicit measures.

5. The prediction information system of claim 1 wherein the input means comprises means for obtaining a plurality of implicit measures including the particular implicit measure and the processing means comprises means for generating a plurality of implicit ratings as a function of the plurality of implicit measures.

6. The prediction information system of claim 1 wherein the processing means comprises means for deriving the implicit rating from the particular implicit measure using a receiver operating curve (ROC).

7. The prediction information system of claim 6 wherein the processing means comprises means for deriving the ROC from the items, a signal to noise characterization, and a plurality of implicit measures including the particular implicit measure.

8. The prediction information system of claim 7 wherein the processing means comprises means for deriving the signal to noise characterization from a set of explicit ratings.

9. The prediction information system of claim 6 wherein the processing means comprises means for deriving rating threshold values for converting a plurality of implicit measures to implicit ratings from the ROC the plurality of implicit measures including the particular implicit measure.

10. The prediction information system of claim 1 wherein the processing means comprises means for deriving a quality metric receiver operating curve (ROC) of a mapping between an implicit measure and an implicit rating, the mapping being based on the items, a signal to noise characterization, and predictions from a prediction engine.

11. The prediction information system of claim 10 wherein the processing means comprises means for deriving a plurality of quality metric ROCs each of which corresponds to a different mapping and for selecting one of the mappings for subsequent use based on the plurality of quality metric ROCs.

12. The prediction information system of claim 10 wherein the processing means comprises means for determining if a plurality of implicit ratings including the particular implicit measure are better than a set of explicit ratings based on the quality metric ROC.

13. The prediction information system of claim 1 wherein the processing means and rating broker are located within a single apparatus.

14. The prediction information system of claim 1 wherein the processing means comprises means for communicating with the rating broker through an interactive network.

15. The prediction information system of claim 14 wherein the user interface means, input means, and processing means together form a client computing device which is operatively coupled through the interactive network to a server which executes a process that performs functions of the rating broker.

16. The prediction information system of claim 14 wherein the processing means comprises a first processing means and a second processing means which together perform the operations of the processing means, and wherein the user interface means, input means, and first processing means together form a client computing device which is operatively coupled through the interactive network to a server which comprises the second processing means and which executes a process that performs functions of the rating broker.

17. A method of operating a collaborative filtering electronic rating broker on a computer system in order to provide prediction information to a user, comprising steps of:

(a) presenting items as information to the user on a display device;

(b) obtaining d particular implicit measure from the user based on the items through an input device;

(c) generating an implicit rating as a function of the particular implicit measure;

(d) submitting the particular implicit rating to the collaborative filtering rating broker;

(e) receiving prediction results for other items from the collaborative filtering rating broker; and

(f) presenting the prediction results to the user as the prediction information on the display device.

18. The method of claim 17 wherein the obtaining step comprises deriving the implicit measure based on criteria selected from a group consisting of:

user time spent viewing a particular item, user time spent listening to a particular item, and user time spent sampling a particular item.

19. The method of claim 17 wherein the obtaining step comprises deriving the implicit measure based on subsequent actions taken, the subsequent actions taken being selected from a group consisting of:

a user viewing details of a particular item after viewing only a title, saving a particular item, forwarding a particular item, saving a return address of a particular item, deleting a particular item, replying to a particular item, and printing a particular item.

20. The method of claim 17 wherein the generating step comprises deriving the implicit rating as a function of a plurality of implicit measures including the particular implicit measure.

21. The method of claim 17 wherein the generating step comprises generating a plurality of implicit ratings as a function of a plurality of implicit measures including the particular implicit measure.

22. The method of claim 17 wherein the generating step comprises deriving the implicit rating from the particular implicit measure using a receiver operating curve (ROC).

23. The method of claim 22 wherein the generating step further comprises deriving the ROC from the items, a signal to noise characterization, and a plurality of implicit measures including the particular implicit measure.

24. The method of claim 23 wherein the generating step further comprises deriving the signal to noise characterization from a set of explicit ratings.

25. The method of claim 22 wherein the generating step further comprises deriving rating threshold values for converting a plurality of implicit measures to implicit ratings from the ROC, the plurality of implicit measures including the particular implicit measure.

26. The method of claim 17 further comprising a step of deriving a quality metric receiver operating curve (ROC) of a mapping between an implicit measure and an implicit rating, the mapping being based on the items, a signal to noise characterization, and predictions from a prediction engine.

27. The method of claim 26 wherein the deriving step comprises deriving a plurality of quality metric ROCs each of which corresponds to a different mapping, the method further comprising a step of selecting one of the mappings for subsequent use based on the plurality of quality metric ROCs.

28. The method of claim 26 further comprising a step of determining if a plurality of implicit ratings including the particular implicit measure are better than a set of explicit ratings based on the quality metric ROC.

29. A program storage device readable by a computer system tangibly embodying a program of instructions executable by the computer system to perform a method of operating an electronic collaborative filtering rating broker on a computer system in order to provide prediction information to a user, the method comprising steps of:

(a) presenting items as information to thc user on a display device;

(b) obtaining a particular implicit measure from the user based on the items through an input device;

(c) generating an implicit rating as a function of the particular implicit measure;

(d) submitting the particular implicit rating to the collaborate filtering rating broker;

(e) receiving prediction results for other items from the collaborative filtering rating broker; and

(f) presenting the prediction results to the user as the prediction information on the display device.