EXPLICIT SIGNALS PERSONALIZED SEARCH

• US 20150278348A1
• Filed: 03/28/2014
• Published: 10/01/2015
• Est. Priority Date: 03/28/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Paruchuri, Sandeep, Howard, Robert, Brown, Jared Adam, Hamilton, Colleen Elizabeth, Nash, Paul Robert
• Granted Patent: US 9,710,546 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06Q 30/0271 Personalized advertisement

Abstract

Methods, systems, and computer program products are provided that enable users to provide explicit declarations that are used to generate recommendations for the users. An explicit declaration is received from a user of a user device. The explicit declaration is configured to influence a subsequent recommendation. The words of the explicit declaration are processed to generate a record. A recommendation rule is generated based on the generated record. The recommendation rule is executed to generate a recommendation for the user. The generated recommendation is provided to the user.

Claims

1. A method in a user device, comprising:

receiving an explicit declaration from a user of the user device, the explicit declaration is configured to influence a subsequent recommendation;

processing the explicit declaration to generate a record;

generating a recommendation rule based on the generated record; and

executing the recommendation rule to generate a recommendation for the user.

2. The method of claim 1, wherein said processing the explicit declaration to generate a record comprises:

performing natural language processing on a series of words of the explicit declaration to extract one or more key features; and

generating the record to include the extracted one or more key features.

3. The method of claim 1, wherein said executing comprises:

matching the recommendation rule with one or more environmental triggers; and

executing the matching recommendation rule to perform at least one of generating the recommendation for the user or collecting additional data toward subsequent generation of the recommendation for the user.

4. The method of claim 3, wherein the one or more environmental triggers include at least one of a time, a location, a person, an application or service, a request from the user for data, or a request by the user for a recommendation.

5. The method of claim 1, wherein said executing the recommendation rule to generate a recommendation for the user comprises:

issuing a query to generate query results; and

wherein the method further comprises;

providing at least a portion of the query results to the user in the recommendation.

6. The method of claim 1, wherein the explicit declaration includes a recommendation provided from a person, the method further comprising:

adjusting a status of the person as an influencer on the user based on a reaction by the user to the recommendation provided by the person, a positive reaction by the user being indicated by at least one of the user actioning or liking the recommendation provided by the person, and a positive reaction of the user being indicated by at least one of the user not actioning or indicating a dislike for the recommendation provided by the person.

7. The method of claim 1, further comprising:

launching a question and answer session with the user in response to the explicit declaration.

8. A recommendation system implemented in at least one computing device, comprising:

a voiced input interface configured to receive an explicit declaration in the form of speech from a user of a computing device, the explicit declaration includes a series of words and is configured to influence a subsequent recommendation;

a speech processing module configured to process the series of words of the explicit declaration to generate a record;

a rules generator configured to generate a recommendation rule based on the generated record, the recommendation rule including a logical expression;

a recommendation engine configured to execute the recommendation rule to generate a recommendation for the user; and

an output interface configured to provide the generated recommendation to the user.

9. The recommendation system of claim 8, wherein the speech processing module is configured to:

perform natural language processing on the series of words of the explicit declaration to extract one or more key features; and

generate the record to include the extracted one or more key features.

10. The recommendation system of claim 8, wherein the recommendation engine is configured to:

match the recommendation rule with one or more environmental triggers; and

execute the matching recommendation rule to perform at least one of generating the recommendation for the user or collecting additional data toward subsequent generation of the recommendation for the user.

11. The recommendation system of claim 10, wherein the one or more environmental triggers include at least one of a time, a location, a person, an application or service, a request from the user for data, or a request by the user for a recommendation.

12. The recommendation system of claim 8, wherein the voiced input interface, the speech processing module, the rules generator, and the recommendation engine are located in a user device of the user.

13. The recommendation system of claim 8, wherein at least one of the rules generator or the recommendation engine is located at least partially at a server that is separate from a user device to which the user provided the explicit declaration.

16. A computer-readable storage medium comprising computer-executable instructions that, when executed by a processor, perform a method comprising:

receiving an explicit declaration from a user of the user device, the explicit declaration is configured to influence a subsequent recommendation;

processing the explicit declaration to generate a record;

generating a recommendation rule based on the generated record; and

executing the a recommendation rule to generate a recommendation for the user.

17. The computer-readable storage medium of claim 16, wherein said executing comprises:

matching the recommendation rule with one or more environmental triggers; and

executing the matching recommendation rule to perform at least one of generating the recommendation for the user or collecting additional data toward subsequent generation of the recommendation for the user.

18. The computer-readable storage medium of claim 17, wherein said executing the recommendation rule to generate a recommendation for the user comprises:

issuing a query to generate query results; and

wherein the method further comprises;

providing at least a portion of the query results to the user in the recommendation.

19. The computer-readable storage medium of claim 17, wherein the explicit declaration includes a recommendation provided from a person, the method further comprising:

adjusting a status of the person as an influencer on the user based on a reaction by the user to the recommendation provided by the person, a positive reaction by the user being indicated by at least one of the user actioning or liking the recommendation provided by the person, and a positive reaction of the user being indicated by at least one of the user not actioning or indicating a dislike for the recommendation provided by the person.

20. The computer-readable storage medium of claim 17, further comprising:

launching a question and answer session with the user in response to the explicit declaration.