Method and apparatus for generating recommendations based on user preferences and environmental characteristics

• US 20020142722A1
• Filed: 04/03/2001
• Published: 10/03/2002
• Est. Priority Date: 04/03/2001
• Status: Active Grant

• Current Assignee: Sisvel S.p.A. (Fineur International S.A.)
• Original Assignee: Philips Electronics North America Corporation (Koninklijke Philips N.V.)
• Inventors: Lee, Mi-Suen, Gutta, Srinivas, Agnihotri, Lalitha
• Granted Patent: US 7,412,202 B2
• Time in Patent Office: Days
• US Class Current: 455/45
• CPC Class Codes: H04H 60/40 for identifying broadcast time
• CPC Class Codes: H04H 60/51 of receiving stations
• CPC Class Codes: H04H 60/65 for using the result on users' side
• CPC Class Codes: H04N 21/42202 environmental sensors, e.g. for detecting temperature, luminosity, pressure, earthquakes
• CPC Class Codes: H04N 21/44222 Analytics of user selections, e.g. selection of programs or purchase activity monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/4524 involving the geographical location of the client retrieval from the Internet by querying based on geographical locations G06F16/9537; systems specially adapted for using geographical information in broadcast systems H04H60/70; protocols in which the network application is adapted for the location of the user terminal in communication control or processing H04L67/52; services making use of the location of users or terminals in wireless networks H04W4/02; locating users or terminals in wireless networks H04W64/00
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/454 Content or additional data filtering, e.g. blocking advertisements
• CPC Class Codes: H04N 21/4665 involving classification methods, e.g. Decision trees
• CPC Class Codes: H04N 21/4755 for defining user preferences, e.g. favourite actors or genre retrieval personalisation and generation of user profiles for the retrieval of video data G06F16/739; user profiles in network data switching protocols H04L67/306
• CPC Class Codes: H04N 21/8106 involving special audio data, e.g. different tracks for different languages
• CPC Class Codes: H04N 7/163 by receiver means only

Abstract

A recommendation system is disclosed that generates recommendations for one or more items based on user preferences and one or more environmental factors. The user'"'"'s preferences are learned under various environmental conditions using an environmental data collection system. The observed environmental conditions may include, for example, location, characteristics of the location, weather or characteristics of the user'"'"'s motion, such as a rate of movement. For each positive and negative behavioral example, a number of attributes of the selected item are classified in the user profile together with the prevailing environmental conditions. When recommending an item, the disclosed recommender retrieves the user preferences and evaluates the current environmental conditions. A recommendation score can be generated for each available item based on the user'"'"'s demonstrated preferences under similar environmental conditions, such as in the same or a similar geographic area or under similar weather conditions.

Claims

1. A method for recommending an item to a user, comprising the steps of:

observing preferences of said user under one or more environmental conditions; and

generating a recommendation score for said item based on features of said item and said observed preferences of said user under said one or more environmental conditions.

2. The method of claim 1, wherein said item is a radio station.

3. The method of claim 1, wherein said item is content.

4. The method of claim 1, wherein said item is a product.

5. The method of claim 1, wherein said one or more environmental conditions is a location.

6. The method of claim 1, wherein said one or more environmental conditions is one or more characteristics of a location.

7. The method of claim 1, wherein said one or more environmental conditions is a weather condition.

8. The method of claim 1, wherein said one or more environmental conditions is a characteristic of motion of said user.

9. The method of claim 1, wherein said observed preferences of said user under said one or more environmental conditions are recorded in a profile.

10. The method of claim 9, wherein said observed preferences of said user under said one or more environmental conditions are recorded in a profile as a set of rules by a decision tree recommender.

11. A method for recommending an item to a user, comprising the steps of:

obtaining preferences of said user under one or more environmental conditions;

obtaining information characterizing one or more environmental characteristics for a given time; and

generating a recommendation score for said item based on features of said item, said obtained preferences of said user under said one or more environmental conditions and said one or more environmental characteristics for a given time.

12. The method of claim 11, wherein said item is a radio station.

13. The method of claim 11, wherein said item is content.

14. The method of claim 11, wherein said item is a product.

15. The method of claim 11, wherein said one or more environmental conditions is a user location at said given time.

16. The method of claim 11, wherein said one or more environmental conditions is one or more characteristics of a location.

17. The method of claim 11, wherein said one or more environmental conditions is a weather condition at said given time.

18. The method of claim 11, wherein said one or more environmental conditions is a characteristic of motion of said user.

19. The method of claim 11, wherein said observed preferences of said user under said one or more environmental conditions are recorded in a profile.

20. The method of claim 19, wherein said observed preferences of said user under said one or more environmental conditions are recorded in a profile as a set of rules by a decision tree recommender.

21. A system for recommending an item to a user, comprising:

a memory for storing computer readable code; and

a processor operatively coupled to said memory, said processor configured to;

observe preferences of said user under one or more environmental conditions; and

generate a recommendation score for said item based on features of said item and said observed preferences of said user under said one or more environmental conditions.

22. The system of claim 21, wherein said item is a radio station.

23. The system of claim 21, wherein said item is content.

24. The system of claim 21, wherein said item is a product.

25. The system of claim 21, wherein said one or more environmental conditions is a location.

26. The system of claim 21, wherein said one or more environmental conditions is one or more characteristics of a location.

27. The system of claim 21, wherein said one or more environmental conditions is a weather condition.

28. The system of claim 21, wherein said one or more environmental conditions is a characteristic of motion of said user.

29. The system of claim 21, wherein said observed preferences of said user under said one or more environmental conditions are recorded in a profile.

30. The system of claim 29, wherein said observed preferences of said user under said one or more environmental conditions are recorded in a profile as a set of rules by a decision tree recommender.

31. A system for recommending an item to a user, comprising:

a memory for storing computer readable code; and

a processor operatively coupled to said memory, said processor configured to;

obtain preferences of said user under one or more environmental conditions;

obtain information characterizing one or more environmental characteristics for a given time; and

generating a recommendation score for said item based on features of said item, said obtained preferences of said user under said one or more environmental conditions and said one or more environmental characteristics for a given time.

32. The system of claim 31, wherein said one or more environmental conditions is a user location at said given time.

33. The system of claim 31, wherein said one or more environmental conditions is one or more characteristics of a location.

34. The system of claim 31, wherein said one or more environmental conditions is a weather condition at said given time.

35. The system of claim 31, wherein said one or more environmental conditions is a characteristic of motion of said user.

36. The system of claim 31, wherein said observed preferences of said user under said one or more environmental conditions are recorded in a profile.

37. The system of claim 36, wherein said observed preferences of said user under said one or more environmental conditions are recorded in a profile as a set of rules by a decision tree recommender.

38. An article of manufacture for recommending an item to a user, comprising:

a computer readable medium having computer readable code means embodied thereon, said computer readable program code means comprising;

a step to observe preferences of said user under one or more environmental conditions; and

a step to generate a recommendation score for said item based on features of said item and said observed preferences of said user under said one or more environmental conditions.

39. An article of manufacture for recommending an item to a user, comprising:

a computer readable medium having computer readable code means embodied thereon, said computer readable program code means comprising;

a step to obtain preferences of said user under one or more environmental conditions;

a step to obtain information characterizing one or more environmental characteristics for a given time; and

a step to generate a recommendation score for said item based on features of said item, said obtained preferences of said user under said one or more environmental conditions and said one or more environmental characteristics for a given time.