Counterintuitive recommendations based upon temporary conditions

• US 10,275,451 B2
• Filed: 07/11/2017
• Issued: 04/30/2019
• Est. Priority Date: 07/11/2017
• Status: Active Grant

• Current Assignee: Maplebear Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Bhowmick, Arindam, Chivardi, Carlos, Hatfield, Jennifer M., Hurlebaus, Gregory S., Scherpa, Josef
• Primary Examiner(s): McFadden, Susan I
• Application Number:
  US15/646,304
• Publication Number:
  US 20190018835A1
• Time in Patent Office: 658 Days
• Field of Search: 704 9
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute

Abstract

A system and method for providing counter intuitive recommendations to a user. A user profile is obtained for the user. A determination that a trigger condition has occurred for the user. The duration of the trigger condition is also determined. The trigger condition is associated with the user'"'"'s profile. A request for a recommendation is received, and a list of recommendations is obtained. The recommendations are compared against the trigger condition to determine if the recommendation is compatible with the trigger condition. Those recommendations determined not to be compatible with the trigger condition are removed from the set of recommendations provided to the user.

Claims

1. A method for providing counter intuitive recommendations to a user comprising:

obtaining a user profile for the user;

determining that a trigger condition has occurred to the user, wherein the trigger condition is programmatically determined by analyzing information related to the user extracted from data sources used to generate the user profile;

determining a duration of the trigger condition;

associating the determined trigger condition with the user profile;

receiving a request for a recommendation from the user;

generating, programmatically, a set of recommendations based on the user profile;

determining if recommendations in the set of recommendations are compatible with the trigger condition; and

removing from the set of recommendation those recommendations that are determined not to be compatible with the trigger condition.

2. The method of claim 1 wherein removing filters the set of recommendations.

3. The method of claim 1 wherein the trigger condition is determined from a post to a social media site.

4. The method of claim 1 wherein determining the duration of the trigger condition is determined from a post to a social media site.

5. The method of claim 1 wherein determining the duration of the trigger condition is determined by analyzing electronic documents related to the trigger condition.

6. The method of claim 1 wherein associating the trigger condition with the user profile does not modify the user profile.

7. The method of claim 1 further comprising removing the association between the trigger condition and the user profile after the duration of the trigger condition has passed.

8. A computer program product embodies on one or more non-transitory computer readable storage mediums, having computer executable instructions that when executed by at least one computer having at least one processor, executes a method for providing counter intuitive recommendations to a user comprising:

obtaining a user profile for the user;

determining that a trigger condition has occurred to the user;

determining a duration of the trigger condition;

associating the determined trigger condition with the user profile;

receiving a request for a recommendation;

generating a set of recommendations based on the user profile;

determining if recommendations in the set of recommendations are compatible with the trigger condition; and

removing from the set of recommendation those recommendations that are determined not to be compatible with the trigger condition.

9. The computer program product of claim 8 wherein removing filters the set of recommendations.

10. The computer program product of claim 8 wherein the trigger condition is determined by analyzing information related to the user from data sources used to generate the user profile.

11. The computer program product of claim 10 wherein the trigger condition is determined from a post to a social media site.

12. The computer program product of claim 10 wherein determining the duration of the trigger condition is determined from a post to a social media site.

13. The computer program product of claim 10 wherein determining the duration of the trigger condition is determined by analyzing electronic documents related to the trigger condition.

14. The computer program product of claim 8 wherein associating the trigger condition with the user profile does not modify the user profile.

15. The computer program product of claim 8 further comprising removing the association between the trigger condition and the user profile after the duration of the trigger condition has passed.

16. A recommendation system configured to provide counter intuitive recommendations to at least one user comprising:

at least one processor;

at least one memory component;

a recommender engine configured to provide a recommendation to the at least one user;

the recommendation system configured to execute a method of;

obtaining a user profile for the user;

determining that a trigger condition has occurred to the user;

determining a duration of the trigger condition;

associating the determined trigger condition with the user profile;

receiving a request for a recommendation;

generating a set of recommendations based on the user profile;

determining if recommendations in the set of recommendations compatible with the trigger condition; and

removing from the set of recommendation those recommendations that are determined not to be compatible with the trigger condition.

17. The system of claim 16 wherein removing filters the set of recommendations.

18. The system of claim 16 wherein the trigger condition is determined by analyzing information related to the user from data sources used to generate the user profile.

19. The system of claim 18 wherein the trigger condition is determined from a post to a social media site, and wherein determining the duration of the trigger condition is determined from a post to a social media site.