Inferring cues for use with digital assistant

Patent metadata

Field	Value
Publication number	US-10997512-B2
Application number	US-201514792268-A
Country	US
Kind code	B2
Filing date	Jul 6, 2015
Priority date	May 25, 2015
Publication date	May 4, 2021
Grant date	May 4, 2021

Abstract

Systems and methods for inferring user traits based on indirect questions. Indirect questions may be generated based on one or more triggers. The answers to the indirect questions provide cues to a system as to whether a user has one or more attributes associated with a trait. This information may be used to personalize a computing device.

First claim

What is claimed:

1. A computing system comprising at least one processor operatively coupled to at least one computer storage device, the device storing instructions that, when executed, are capable of performing a method comprising:
receiving from a user, based on interaction with a digital assistant, a query with one or more words that are included within an inference field of a trait, the trait being characterized by a set of inference fields;
responsive to the query, generating an indirect question associated with the trait, wherein the indirect question is directed to an inference field that is not populated within the set of inference fields of the trait;
providing the indirect question to the user;
receiving a response to the indirect question;
based on the response to the indirect question, assigning a confidence score to the trait;
assigning the trait to the user in accordance with determining that the confidence score is above a predetermined threshold; and
automatically personalizing the user interface of the computing device based on the assignment of the trait, wherein the personalized user interface includes content that relates to the trait.

2. The computing system of claim 1 , wherein the method further comprises:
comparing the score with a predetermined threshold;
determining that the trait is likely when the score is greater than the predetermined threshold;
populating the trait with trait information based on the at least one inference field that corresponds to the response; and
providing the personalized user interface.

3. The computing system of claim 2 , wherein the populating the trait with the trait information occurs by populating a user profile with the trait information.

4. The computing system of claim 1 , wherein the determination of the trait being likely is done using a Bayesian model.

5. The computing system of claim 1 , further comprising:
receiving a trigger preceding generating the indirect question, wherein the trigger is at least one of: a query with at least one word that is included within the at least one inference field of the trait, and
interaction with a digital assistant; and
when the at least one inference field of the trait is without information, generating the indirect question.

6. The computing system of claim 1 , wherein the generating the indirect question comprises selecting the indirect question from a predetermined list in a database.

7. The computing system of claim 1 , wherein the received response is received through one of: a gesture input, text input, or voice input, and wherein the personalized the user interface includes one or more of:
a shortcut to quickly access information relating to the trait,
a response separating information correlating to the trait,
a media application providing information correlating to the trait,
a home page of a web browser based on the trait, and
a background of the user interface based on the trait.

8. A computer implemented method of personalizing a user interface of a computing device based on a trait of an operator, the method comprising:
receiving from a user, based on interaction with a digital assistant, a query with one or more words that are included within an inference field of a trait, the trait being characterized by a set of inference fields;
responsive to the query, generating an indirect question associated with the trait, wherein the indirect question is directed to an inference field that is not populated within the set of inference fields of the trait;
providing the indirect question to the user;
receiving a response to the indirect question;
based on the response to the indirect question, assigning a confidence score to the trait;
assigning the trait to the user in accordance with determining that the confidence score is above a predetermined threshold; and
automatically personalizing the user interface of the computing device based on the assignment of the trait, wherein the personalized user interface includes content that relates the trait.

9. The method of claim 8 further comprising:
comparing the score with a predetermined threshold;
determining that the trait is likely when the score is greater than the predetermined threshold;
populating the trait with trait information based on the at least one inference field that corresponds to the response; and
providing the personalized user interface.

10. The method of claim 9 , wherein the populating the trait with the trait information occurs by populating a user profile with the trait information.

11. The method of claim 8 , wherein the determination of the trait being likely is done using a Bayesian model.

12. The method of claim 8 , further comprising receiving a trigger preceding generating the indirect question, wherein the trigger is at least one of:
a query with words that relate to the at least one inference field of the trait, and
interaction with a digital assistant.

13. The method of claim 8 , wherein the generating the indirect question comprises selecting the indirect question from a predetermined list in a database.

14. The method of claim 8 , wherein the received response is received through a gesture input, and wherein the personalized the user interface one or more of:
a shortcut to quickly access information relating to the trait,
a response separating information correlating to the trait,
a media application providing information correlating to the trait,
a home page of a web browser based on the trait, and
a background of the user interface based on the trait.

15. A computer storage device storing instructions that, when executed, perform a method, the method comprising:
receiving from a user, based on interaction with a digital assistant, a query with one or more words that are included within an inference field of a trait, the trait being characterized by a set of inference fields;
responsive to the query, generating an indirect question associated with the trait, wherein the indirect question is directed to an inference field that is not populated within the set of inference fields of the trait;
providing the indirect question to the user;
receiving a response to the indirect question;
based on the response to the indirect question, assigning a confidence score to the trait;
assigning the trait to the user in accordance with determining that the confidence score is above a predetermined threshold; and
automatically personalizing the user interface of on the computing device based on the assignment of the trait, wherein the personalized user interface includes content that relates to the trait.

16. The computer storage device of claim 15 , wherein the method further comprises:
comparing the score with a predetermined threshold;
determining that the trait is likely when the score is greater than the predetermined threshold;
populating the trait with trait information based on the at least one inference field that corresponds to the response; and
providing the personalized user interface.

17. The computer storage device of claim 16 , wherein populating the trait with the trait information occurs by populating a user profile with the trait information.

18. The computer storage device of claim 15 , wherein the determination of the trait being likely is done using a Bayesian model.

19. The computer storage device of claim 15 , wherein the method further comprises receiving a trigger prior to generating the indirect question, and wherein the trigger is at least one of:
a query with words

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Novotny Margaret
• Miller Jacob
• Wagner William
• Pesenson Yelisaveta
• Shelander Aryn
• Stevens Sheena
• Russo Claudio
• Graepel Thore
• Gordon Andrew D
• Miles Christopher E

Classifications

• G06N3/006 Primary

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• G06N7/01 Primary

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06N5/048 Primary

  Fuzzy inferencing · CPC title

• G06N7/00

  Computing arrangements based on specific mathematical models · CPC title