Question-answering system

• US 9,471,668 B1
• Filed: 01/21/2016
• Issued: 10/18/2016
• Est. Priority Date: 01/21/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Alupului, Mariana, Ames, Andrea L., Pesot, Joseph F., Pierce, Robert, Collopy, Beth Anne M., Steinmetz, David C.
• Primary Examiner(s): Ly, Anh
• Application Number:
  US15/002,713
• Time in Patent Office: 271 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]

Abstract

A computer program product and method provides a question and answer service that accepts an initial first question from a user and analyzes the question by a first generation subsystem to generate a first answer. A second generation subsystem of the question and answer service is configured to generate a second question based at least in-part on keywords from the first question and the first answer.

Claims

1. A computer implemented method of operating a question-answering system comprising:

receiving a first question input into a user interface by a user;

analyzing the first question by a computer device utilizing a corpus of data;

outputting a computer generated first answer to the first question;

outputting a computer generated second question based at least in-part on the first question, wherein the second question is based in-part on the first answer; and

selecting keywords of the first answer by the computer device to at least in-part generate the second question.

2. The method set forth in claim 1 further comprising:

selecting of the second question by the user.

3. The method set forth in claim 2 further comprising:

analyzing the second question by the computer device; and

outputting a computer generated second answer to the second question.

4. The method set forth in claim 3, wherein the second question is one of a plurality of second question available for selection by the user.

5. The method set forth in claim 3, wherein the first answer is generated by a first generation subsystem of the question and answer system.

6. The method set forth in claim 5, wherein the second question is generated by a second generation subsystem of the question-answering system.

7. The method set forth in claim 6, wherein the second answer is generated by the first generation subsystem.

8. The method set forth in claim 1, wherein the second question is semantically similar to the first question.

9. The method set forth in claim 1, further comprising:

utilizing a pre-created taxonomy template by the computer device for, at least in-part, generating the second question.

10. The method set forth in claim 9, wherein the pre-created taxonomy template is based on a subject of the corpus of data.

11. A computer program product for providing a question and answer service, the computer program product comprising:

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

receiving a first question from a user and generate a first answer to the question based on an analysis of the first question utilizing a corpus of data; and

generating a second question based at least in-part on keywords from the first question and the first answer.

12. The computer program product set forth in claim 11, wherein the first generation subsystem includes an Alchemy API service.

13. The computer program product set forth in claim 12, wherein the Alchemy API service includes an Entity and Keyword Extraction API service.

14. The computer program product set forth in claim 13, wherein the second generation subsystem includes a concept-tagging API service.

15. The computer program product set forth in claim 14, wherein the Alchemy API service is configured to provide a set of synonyms associated with the first generation question, and wherein the concept-tagging API is configured to provide a set of keywords associated with at least one concept associated with the first generation answer.

16. The computer program product set forth in claim 15, wherein the second generation subsystem includes a compare process configured to omit words from the set of keywords that are found in the set of synonyms.

17. The computer program product set forth in claim 16, wherein a corpus taxonomy service is applied to the set of keywords after omitting common words to the set of synonyms.