FUZZY USERS' ATTRIBUTES PREDICTION BASED ON USERS' BEHAVIORS

• US 20110131166A1
• Filed: 12/01/2010
• Published: 06/02/2011
• Est. Priority Date: 12/01/2009
• Status: Active Grant

• Current Assignee: Hulu LLC (The Walt Disney Company)
• Original Assignee: Hulu LLC (The Walt Disney Company)
• Inventors: Zhang, Qi, Tom, Richard W., Yang, Ting-hao, Liao, Yupeng, Zheng, Hua, Li, Hang
• Granted Patent: US 8,756,184 B2
• Time in Patent Office: Days
• US Class Current: 706/25
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/043 based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A method, apparatus, system, article of manufacture, and computer readable storage medium provide the ability to predict and utilize a user'"'"'s attributes. A sample user behavior and a sample user attribute are collected. A model is trained based on the sample user behavior and sample user attribute. Using the model, a probability of a predicted user attribute based on the sample user behavior is predicted. Using the model and the probability, the predicted user attribute is fuzzily determined based on a real user behavior. The predicted user attribute is used to improve a user'"'"'s experience.

Claims

1. A computer-implemented method for utilizing a user'"'"'s predicted attributes, comprising:

collecting a sample user behavior and a sample user attribute;

training a model based on the sample user behavior and sample user attribute;

predicting, using the model, a probability of a predicted user attribute based on the sample user behavior;

fuzzily determining, using the model and the probability, the predicted user attribute based on a real user behavior; and

utilizing the predicted user attribute to improve a user'"'"'s experience.

2. The computer-implemented method of claim 1, wherein the model comprises a neural network model.

3. The computer-implemented method of claim 2, wherein the training a model step comprises:

representing the sample user behavior as an input node having an input weight;

representing the sample user attribute as an output node having an output weight; and

determining one or more functions based using one or more processing nodes, wherein the one or more functions are configured to produce the output weight based on the input weight.

4. The computer-implemented method of claim 3, wherein the training further comprises combining additional sample user behaviors and additional sample attributes from multiple users with the sample user behavior and sample user attribute.

5. The computer-implemented method of claim 1, wherein the predicting step comprises:

processing the sample user behavior in the model to produce the predicted attribute;

comparing a distribution of the sample user attribute for one or more sample users to the predicted attribute to determine a probability for the predicted attribute based on a number of sample users that actually have the predicted attribute.

6. The computer-implemented method of claim 1, wherein the predicting step determines the probability based on a least squared fit analysis based on the predicted user attribute and sample user behavior.

7. The computer-implemented method of claim 1, wherein the fuzzily determining comprises:

processing the real user behavior in the model to produce the predicted user attribute and a cumulative probability for the predicted user attribute.

8. The computer-implemented method of claim 1, wherein the utilizing comprises transmitting a personalized recommendation to a user.

9. The computer-implemented method of claim 1, wherein the utilizing comprises transmitting targeted advertisement to a user.

10. The computer-implemented method of claim 1, further comprising collecting a user'"'"'s feedback to improve the model by repeating the training using the user'"'"'s feedback.

11. An apparatus for utilizing a user'"'"'s predicted attributes in a computer system comprising:

(a) a computer having a memory;

(b) an application executing on the computer, wherein the application is configured to;

(i) collect a sample user behavior and a sample user attribute;

(ii) train a model based on the sample user behavior and sample user attribute;

(iii) predict, using the model, a probability of a predicted user attribute based on the sample user behavior;

(iv) fuzzily determine, using the model and the probability, the predicted user attribute based on a real user behavior; and

(v) utilize the predicted user attribute to improve a user'"'"'s experience.

12. The apparatus of claim 11, wherein the model comprises a neural network model.

13. The apparatus method of claim 12, wherein the application is configured to train a model by:

representing the sample user behavior as an input node having an input weight;

representing the sample user attribute as an output node having an output weight; and

determining one or more functions based using one or more processing nodes, wherein the one or more functions are configured to produce the output weight based on the input weight.

14. The apparatus of claim 13, wherein the application is further configured to train by combining additional sample user behaviors and additional sample attributes from multiple users with the sample user behavior and sample user attribute.

15. The apparatus of claim 11, wherein the application is configured to predict by:

processing the sample user behavior in the model to produce the predicted attribute;

comparing a distribution of the sample user attribute for one or more sample users to the predicted attribute to determine a probability for the predicted attribute based on a number of sample users that actually have the predicted attribute.

16. The apparatus of claim 11, wherein the application is configured to predict by determining the probability based on a least squared fit analysis based on the predicted user attribute and sample user behavior.

17. The apparatus of claim 11, wherein the application is configured to fuzzily determine by:

processing the real user behavior in the model to produce the predicted user attribute and a cumulative probability for the predicted user attribute.

18. The apparatus of claim 11, wherein the application is configured to utilize by transmitting a personalized recommendation to a user.

19. The apparatus of claim 11, wherein the application is configured to utilize by transmitting targeted advertisement to a user.

20. The apparatus of claim 11, wherein the application is configured to further collect a user'"'"'s feedback to improve the model by repeating the training using the user'"'"'s feedback.

21. A computer readable storage medium encoded with computer program instructions which when accessed by a computer cause the computer to load the program instructions to a memory therein creating a special purpose data structure causing the computer to operate as a specially programmed computer, executing a method of utilizing a user'"'"'s predicted attributes, comprising:

(a) collecting, in the specially programmed computer, a sample user behavior and a sample user attribute;

(b) training, in the specially programmed computer, a model based on the sample user behavior and sample user attribute;

(c) predicting, in the specially programmed computer, using the model, a probability of a predicted user attribute based on the sample user behavior;

(d) fuzzily determining, in the specially programmed computer, using the model and the probability, the predicted user attribute based on a real user behavior; and

(e) utilizing, in the specially programmed computer, the predicted user attribute to improve a user'"'"'s experience.

22. The computer readable storage medium of claim 21, wherein the model comprises a neural network model.

23. The computer readable storage medium of claim 22, wherein the training a model comprises:

representing the sample user behavior as an input node having an input weight;

representing the sample user attribute as an output node having an output weight; and

determining one or more functions based using one or more processing nodes, wherein the one or more functions are configured to produce the output weight based on the input weight.

24. The computer readable storage medium of claim 23, wherein the training further comprises combining additional sample user behaviors and additional sample attributes from multiple users with the sample user behavior and sample user attribute.

25. The computer readable storage medium of claim 21, wherein the predicting comprises:

processing the sample user behavior in the model to produce the predicted attribute;

comparing a distribution of the sample user attribute for one or more sample users to the predicted attribute to determine a probability for the predicted attribute based on a number of sample users that actually have the predicted attribute.

26. The computer readable storage medium of claim 21, wherein the predicting determines the probability based on a least squared fit analysis based on the predicted user attribute and sample user behavior.

27. The computer readable storage medium of claim 21, wherein the fuzzily determining comprises:

processing the real user behavior in the model to produce the predicted user attribute and a cumulative probability for the predicted user attribute.

28. The computer readable storage medium of claim 21, wherein the utilizing comprises transmitting a personalized recommendation to a user.

29. The computer readable storage medium of claim 21, wherein the utilizing comprises transmitting targeted advertisement to a user.

30. The computer readable storage medium of claim 21, further comprising collecting a user'"'"'s feedback to improve the model by repeating the training using the user'"'"'s feedback.