MOBILE BASED LEXICON AND FORECASTING

• US 20150293899A1
• Filed: 04/11/2014
• Published: 10/15/2015
• Est. Priority Date: 04/11/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Baughman, Aaron K., Dolph, Blaine H., Sakthi, Palani, Khan, Kamran R., Paez, Carlos A. Jr.
• Granted Patent: US 9,430,461 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• 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 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

An approach is provided for ranking candidate answers to a natural language question. A natural language question is received from a user of a mobile device. Candidate answers to the received natural language question are generated. A lexicon is generated based on contextual information of the user determined by the mobile device. Contextual information of the user is forecasted based on usage of the mobile device. Based in part on the lexicon and the forecasted contextual information, the candidate answers to the natural language question are ranked.

Claims

1. A method of ranking candidate answers to a natural language question, the method comprising the steps of:

a computer receiving the natural language question from a user of a mobile device;

the computer generating candidate answers to the received natural language question;

the computer generating a lexicon based on contextual information of the user determined by the mobile device;

the computer forecasting contextual information of the user based on usage of the mobile device; and

based in part on the lexicon and the forecasted contextual information, the computer ranking the candidate answers to the natural language question.

2. The method of claim 1, wherein the step of forecasting contextual information includes forecasting contextual information that includes a combination of:

applications that the user has run on the mobile device;

websites visited by the user via a browser provided by the mobile device;

textual articles displayed on the mobile device that were read by the user;

terms entered by the user into a search engine via the mobile device;

multimedia content captured by the mobile device and viewed by the user;

a geographic location of the user;

data specifying functions of the body of the user; and

data specifying movements of the user.

3. The method of claim 1, further comprising the computer adjusting weights of a machine learning ensemble based on the forecasted contextual information, wherein the machine learning ensemble includes (1) logistic regression phases and routes, (2) dimensions of evidence refinement, (3) probability density functions, classification techniques, and regression techniques, (4) natural language processing systems, or (5) a data retrieval system.

4. The method of claim 1, wherein the step of forecasting the contextual information includes utilizing a software-based forecaster that employs mobile-based time series manipulation and pattern recognition, autoregressive integrated moving average (ARIMA) based modeling, lag-based modeling, residual calculations, or probability density based functions.

5. The method of claim 4, wherein the step of forecasting the contextual information includes querying the user whose response provides additional information to the forecaster so that inferences by the forecaster about the contextual information are increased as compared to inferences by the forecaster without the additional information.

6. The method of claim 1, wherein the step of generating the lexicon includes generating the lexicon based on the contextual information determined by the mobile device, which includes at least one of:

(1) textual information displayed by the mobile device to the user, (2) multimedia information displayed by the mobile device to the user, and (3) applications run on the mobile device by the user.

7. The method of claim 1, further comprising the computer disambiguating senses of words in the lexicon based on the forecasted contextual information.

8. The method of claim 1, further comprising providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable program code in the computer, the program code being executed by a processor of the computer to implement the steps of receiving, generating candidate answers, generating the lexicon, forecasting, and ranking.

9. A computer program product, comprising:

a computer-readable, storage device; and

a computer-readable program code stored in the computer-readable, storage device, the computer-readable program code containing instructions that are carried out by a central processing unit (CPU) of a computer system to implement a method of ranking candidate answers to a natural language question, the method comprising the steps of;

the computer system receiving the natural language question from a user of a mobile device;

the computer system generating candidate answers to the received natural language question;

the computer system generating a lexicon based on contextual information of the user determined by the mobile device;

the computer system forecasting contextual information of the user based on usage of the mobile device; and

based in part on the lexicon and the forecasted contextual information, the computer system ranking the candidate answers to the natural language question.

10. The program product of claim 9, wherein the step of forecasting contextual information includes forecasting contextual information that includes a combination of:

applications that the user has run on the mobile device;

websites visited by the user via a browser provided by the mobile device;

textual articles displayed on the mobile device that were read by the user;

terms entered by the user into a search engine via the mobile device;

multimedia content captured by the mobile device and viewed by the user;

data specifying characteristics of the environment in proximity to the user, the characteristics measured by one or more sensors coupled to the mobile device;

a geographic location of the user;

data specifying functions of the body of the user; and

data specifying movements of the user.

11. The program product of claim 9, wherein the method further comprises the computer system adjusting weights of a machine learning ensemble based on the forecasted contextual information, wherein the machine learning ensemble includes (1) logistic regression phases and routes, (2) dimensions of evidence refinement, (3) probability density functions, classification techniques, and regression techniques, (4) natural language processing systems, or (5) a data retrieval system.

12. The program product of claim 9, wherein the step of forecasting the contextual information includes utilizing a software-based forecaster that employs mobile-based time series manipulation and pattern recognition, autoregressive integrated moving average (ARIMA) based modeling, lag-based modeling, residual calculations, or probability density based functions.

13. The program product of claim 12, wherein the step of forecasting the contextual information includes querying the user whose response provides additional information to the forecaster so that inferences by the forecaster about the contextual information are increased as compared to inferences by the forecaster without the additional information.

14. The program product of claim 9, wherein the step of generating the lexicon includes generating the lexicon based on the contextual information determined by the mobile device, which includes at least one of:

(1) textual information displayed by the mobile device to the user, (2) multimedia information displayed by the mobile device to the user, and (3) applications run on the mobile device by the user.

15. A computer system comprising:

a central processing unit (CPU);

a memory coupled to the CPU; and

a computer readable storage device coupled to the CPU, the storage device containing instructions that are executed by the CPU via the memory to implement a method of ranking candidate answers to a natural language question, the method comprising the steps of;

the computer system receiving the natural language question from a user of a mobile device;

the computer system generating candidate answers to the received natural language question;

the computer system generating a lexicon based on contextual information of the user determined by the mobile device;

the computer system forecasting contextual information of the user based on usage of the mobile device; and

based in part on the lexicon and the forecasted contextual information, the computer system ranking the candidate answers to the natural language question.

16. The computer system of claim 15, wherein the step of forecasting contextual information includes forecasting contextual information that includes a combination of:

applications that the user has run on the mobile device;

websites visited by the user via a browser provided by the mobile device;

textual articles displayed on the mobile device that were read by the user;

terms entered by the user into a search engine via the mobile device;

multimedia content captured by the mobile device and viewed by the user;

data specifying characteristics of the environment in proximity to the user, the characteristics measured by one or more sensors coupled to the mobile device;

a geographic location of the user;

data specifying functions of the body of the user; and

data specifying movements of the user.

17. The computer system of claim 15, wherein the method further comprises the computer system adjusting weights of a machine learning ensemble based on the forecasted contextual information, wherein the machine learning ensemble includes (1) logistic regression phases and routes, (2) dimensions of evidence refinement, (3) probability density functions, classification techniques, and regression techniques, (4) natural language processing systems, or (5) a data retrieval system.

18. The computer system of claim 15, wherein the step of forecasting the contextual information includes utilizing a software-based forecaster that employs mobile-based time series manipulation and pattern recognition, autoregressive integrated moving average (ARIMA) based modeling, lag-based modeling, residual calculations, or probability density based functions.

19. The computer system of claim 18, wherein the step of forecasting the contextual information includes querying the user whose response provides additional information to the forecaster so that inferences by the forecaster about the contextual information are increased as compared to inferences by the forecaster without the additional information.

20. The computer system of claim 15, wherein the step of generating the lexicon includes generating the lexicon based on the contextual information determined by the mobile device, which includes at least one of:

(1) textual information displayed by the mobile device to the user, (2) multimedia information displayed by the mobile device to the user, and (3) applications run on the mobile device by the user.