Automated learning and gesture based interest processing

• US 10,101,820 B2
• Filed: 07/21/2016
• Issued: 10/16/2018
• Est. Priority Date: 07/21/2016
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Creamer, Thomas E., Katzen, Erik H., Patel, Sumit
• Primary Examiner(s): Saini, Amandeep
• Application Number:
  US15/216,060
• Publication Number:
  US 20180024639A1
• Time in Patent Office: 817 Days
• Field of Search: 382103
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 2203/011 Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

A system, method and program product for processing user interests. A system is provided that includes: a gesture management system that receives gesture data from a collection device for an inputted interest of a user; a pattern detection system that receives and analyzes behavior data associated with the inputted interest; an interest affinity scoring system that calculates an affinity score for the inputted interest based on the gesture data and an analysis of the behavior data; a dynamic classification system that assigns a dynamically generated tag to the inputted interest based on an inputted context associated with the inputted interest; and a user interest database that stores structured interest information for the user, including a unique record for the inputted interest that includes the affinity score and dynamically generated tag.

Claims

1. A system for processing user interests, comprising:

an interface for receiving an inputted interest and an inputted context from a user, wherein the inputted context includes a natural language input;

a gesture management system that receives gesture data from a collection device with the inputted interest to identify a gesture from a set of gestures predefined by the user;

a pattern detection system that receives behavior data associated with the inputted interest and determines whether the behavior data includes a recognized behavior pattern based on previously collected behavior data of the user, in which the recognized behavior pattern was not predefined by the user;

an interest affinity scoring system that calculates an affinity score for the inputted interest based on an identified gesture and a recognized behavior pattern;

a dynamic classification system that assigns a dynamically generated tag to the inputted interest based on the natural language input; and

a user interest database that stores structured interest information for the user, including a unique record for the inputted interest that includes the affinity score and dynamically generated tag.

2. The system of claim 1, wherein each gesture in the set of set of gestures defined by the user includes a first indicator of relevance to the user.

3. The system of claim 2, wherein previously collected behavior data is stored in a user interest database.

4. The system of claim 3, wherein recognized behavior patterns are correlated by a learning system with a second indicator of relevance to the user.

5. The system of claim 4, wherein the interest affinity scoring system utilizes the first indicator of relevance and the second indicator of relevance to calculate the affinity score.

6. The system of claim 1, wherein the natural language input is used to form the dynamically generated tag.

7. The system of claim 1, wherein the dynamically generated tag and affinity score are periodically reevaluated and updated in response to a received additional inputted context associated with the inputted interest.

8. A computer program product stored on a computer readable storage medium, which when executed by a computing system, processes user interests, the program product comprising:

program code for receiving an inputted interest from a user and an inputted context, wherein the inputted context includes at least one of a natural language input, a time parameter and a location parameter;

program code that receives gesture data from a collection device with the inputted interest to identify a gesture from a set of gestures predefined by the user;

program code that receives behavior data associated with the inputted interest and determines whether the behavior data includes a recognized behavior pattern based on previously collected behavior data of the user, in which the recognized behavior pattern was not predefined by the user;

program code that calculates an affinity score for the inputted interest based on an identified gesture and a recognized behavior pattern;

program code that assigns a dynamically generated tag to the inputted interest based on the inputted context associated with the inputted interest; and

program code that stores structured interest information for the user, including a unique record for the inputted interest that includes the affinity score and dynamically generated tag.

9. The program product of claim 8, wherein each gesture in the set of gestures defined by the user includes a first indicator of relevance to the user.

10. The program product of claim 9, wherein previously collected behavior data is stored in a user interest database.

11. The program product of claim 10, wherein recognized behavior patterns are correlated by a learning system with a second indicator of relevance to the user.

12. The program product of claim 11, further comprising program code that utilizes the first indicator of relevance and the second indicator of relevance to calculate the affinity score.

13. The program product of claim 8, code wherein natural language input is used to form the dynamically generated tag.

14. The program product of claim 8, wherein the dynamically generated tag and affinity score are periodically reevaluated and updated in response to a received additional inputted context associated with the inputted interest.