UNIFIED NUMERICAL AND SEMANTIC ANALYTICS SYSTEM FOR DECISION SUPPORT

• US 20120011139A1
• Filed: 07/12/2010
• Published: 01/12/2012
• Est. Priority Date: 07/12/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Grandison, Tyrone W., Harrison, Colin G., Katircioglu, Kaan K., Paraszczak, Jurij R., DRISSI, Youssef
• Granted Patent: US 8,538,915 B2
• Time in Patent Office: Days
• US Class Current: 707/760
• CPC Class Codes: G06F 16/2452 Query translation

Abstract

A system and method for responding to a query. An original query is received. A first semantic query and a second semantic query are extracted from the information of the original query. The first semantic query is transformed, based upon semantic analysis, into a numeric model query. The second semantic query is submitted to a semantic analyzer and the numeric model query is submitted to a numeric model analyzer. A response for the second semantic query and a response for the numeric model query are integrated into an answer for the original query.

Claims

1. A method for responding to a query, the method comprising:

performing the following with a processor;

receiving an original query;

extracting a first semantic query and a second semantic query from the original query, the first semantic query comprising a quantitative action term;

transforming, based upon semantic analysis of the quantitative action term, the first semantic query into a numeric model query;

submitting the second semantic query to a semantic analyzer;

submitting the numeric model query to a numeric model analyzer; and

integrating, into an answer for the original query, a response for the second semantic query and a response for the numeric model query.

2. The method of claim 1, further comprising accepting the original query from a user as a natural language question.

3. The method of claim 1, further comprising:

extracting an additional numeric model query from the original query; and

submitting the additional numeric model query to the numeric model analyzer,

wherein the integrating further comprising integrating a response for the additional numeric model query into the answer for the original query.

4. The method of claim 1, further comprising:

maintaining, within the numeric model analyzer, at least one mathematical model;

identifying, in response to the numeric model query, additional data for the at least one mathematical model to use to respond to the numeric model query;

submitting, to the semantic analyzer, a semantic query to obtain the additional data; and

generating, with the at least one mathematical model and based upon the additional data, the response for the numeric model query.

5. The method of claim 1, further comprising:

providing the answer to a user;

collecting, subsequent to providing the answer to the user, data reflecting an impact of an action taken by the user, the action being based on the answer;

analyzing the data reflecting the impact of the action taken by the user; and

updating, based on the analyzing, at least one model within at least one of the semantic analyzer and the numeric model analyzer.

6. The method of claim 5, wherein the answer is used to support a public policy decision,

the collecting comprising receiving at least one of at least one blog, at least one letter, and at least one data stream, and

the analyzing comprising performing semantic analysis on the at least one blog, at least one letter, and at least one data stream.

7. A system for responding to a query, the system comprising:

a memory;

a processor communicatively coupled to the memory, wherein the processor comprises;

an instruction processor configured to;

receive an original query;

extract a first semantic query and a second semantic query from the original query, the first semantic query comprising a quantitative action term;

transform, based upon semantic analysis of the quantitative action term, the first semantic query into a numeric model query;

submit the second semantic query to a semantic analyzer;

submit the numeric model query to a numeric model analyzer; and

integrate, into an answer for the original query, a response for the second semantic query and a response for the numeric model query.

8. The system of claim 7, the instruction processor receives the original query from a user as a natural language question.

9. The system of claim 7, the instruction processor further configured to:

extract an additional numeric model query from the original query; and

submit the additional numeric model query to the numeric model analyzer,

wherein the instruction processor is further configured to integrate by performing processing comprising integrating a response for the additional numeric model query into the answer for the original query.

10. The system of claim 7, wherein the instruction processor is further configured to:

maintain, within the numeric model analyzer, at least one mathematical model;

identify, in response to the numeric model query, additional data for the at least one mathematical model to use to respond to the numeric model query;

submit, to the semantic analyzer, a semantic query to obtain the additional data; and

generate, with the at least one mathematical model and based upon the additional data, the response for the numeric model query.

11. The system of claim 7, wherein the instruction processor is further configured to:

provide the answer to a user;

collect, subsequent to providing the answer to the user, data reflecting an impact of an action taken by the user, the action being based on the answer;

analyze the data reflecting the impact of the action taken by the user; and

update, based on the analyzing, at least one model within at least one of the semantic analyzer and the numeric model analyzer.

12. The system of claim 11, wherein the answer is used to support a public policy decision,

wherein the instruction processor is further configured to collect by performing processing comprising receiving at least one of at least one blog, at least one letter, and at least one data stream, and

wherein the instruction processor is configured to analyze by performing processing comprising performing semantic analysis on the at least one blog, at least one letter, and at least one data stream.

13. A computer program product for responding to a query, the computer program product comprising:

a storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising;

receiving an original query;

extracting a first semantic query and a second semantic query from the original query, the first semantic query comprising a quantitative action term;

transforming, based upon semantic analysis of the quantitative action term, the first semantic query into a numeric model query;

submitting the second semantic query to a semantic analyzer;

submitting the numeric model query to a numeric model analyzer; and

integrating, into an answer for the original query, a response for the second semantic query and a response for the numeric model query.

14. The computer program product of claim 13, the method further comprising receiving the original query from a user as a natural language question.

15. The computer program product of claim 13, the method further comprising:

extracting an additional numeric model query from the original query; and

submitting the additional numeric model query to the numeric model analyzer, and

wherein the integrating further comprises integrating a response for the additional numeric model query into the answer for the original query.

16. The computer program product of claim 13, the method further comprising:

maintaining, within the numeric model analyzer, at least one mathematical model;

identifies, in response to the numeric model query, additional data for the at least one mathematical model to use to respond to the numeric model query;

submitting, to the semantic analyzer, a semantic query to obtain the additional data; and

generating, with the at least one mathematical model and based upon the additional data, the response for the numeric model query.

17. The computer program product of claim 13, the method further comprising:

providing the answer to a user;

collecting, subsequent to providing the answer to the user, data reflecting an impact of an action taken by the user, the action being based on the answer;

analyzing the data reflecting the impact of the action taken by the user; and

updating, based on the analyzing, at least one model within at least one of the semantic analyzer and the numeric model analyzer.

18. The computer program product of claim 17, wherein the answer is used to support a public policy decision,

the collecting comprising receiving at least one of at least one blog, at least one letter, and at least one data stream, and

the analyzing comprising performing semantic analysis on the at least one blog, at least one letter, and at least one data stream.