Effective ingesting data used for answering questions in a question and answer (QA) system

Patent metadata

Field	Value
Publication number	US-9542496-B2
Application number	US-201414295556-A
Country	US
Kind code	B2
Filing date	Jun 4, 2014
Priority date	Jun 4, 2014
Publication date	Jan 10, 2017
Grant date	Jan 10, 2017

Abstract

A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer (QA) system, for effectively ingesting data for answering questions in the QA system. A received input question having a set of question characteristics is parsed, which are compared to question characteristics associated with a set of previous questions. Responsive to the set of question characteristics matching the question characteristics associated with one or more previous questions above a related-question predetermined threshold, identification is made as to whether answers to the one or more previous questions were obtained from static information sources or real-time information sources. Responsive to the answers to the one or more previous questions being obtained from the real-time information sources above the predetermined real-time threshold, real-time information sources related to the characteristics of the input question are initially utilized to answer the input question.

First claim

What is claimed is:

1. A method, in a data processing system comprising a processor and a memory configured to implement a question and answer (QA) system, for effectively ingesting data for answering questions in the QA system, the method comprising:
parsing, by a processor in the QA system, a received input question having a set of question characteristics;
comparing, by the processor, the set of question characteristics found in the received input question to question characteristics associated with a set of previous questions;
responsive to the set of question characteristics found in the received input question matching the question characteristics associated with one or more previous questions in the set of previous questions above a related-question predetermined threshold, identifying, by the processor, whether answers to the one or more previous questions were obtained from static information sources or real-time information sources; and
responsive to the answers to the one or more previous questions being obtained from the real-time information sources above the predetermined real-time threshold, initially utilizing, by the processor, real-time information sources related to the characteristics of the input question to answer the input question.

2. The method of claim 1 , further comprising:
responsive to the answers to the one or more previous questions failing to be obtained from the real-time information sources above the predetermined real-time threshold and responsive to the answers to the one or more previous questions being obtained from the static information sources above a predetermined static threshold, initially utilizing, by the processor, static information sources related to the characteristics of the input question to answer the input question.

3. The method of claim 1 , further comprising:
responsive to the answers to the one or more previous questions failing to be obtained from the real-time information sources above the predetermined real-time threshold and responsive to the answers to the one or more previous questions failing to be obtained from the static information sources above a predetermined static threshold, initially utilizing, by the processor, both real-time information sources and static information sources related to the characteristics of the input question to answer the input question.

4. The method of claim 1 , wherein static information sources are information sources that exhibit permanence.

5. The method of claim 1 , wherein real-time information sourc information sources that exhibit impermanence.

6. The method of claim 1 , further comprising:
responsive to the set of question characteristics found in the received input question failing to matching the question characteristics associated with one or more previous questions in the set of previous questions above the related-question predetermined threshold, analyzing, by the processor, the input question for relevance to trending topics; and
responsive to a topic of the input question matching a trending topic, initially utilizing, by the processor, real-time information sources related to the topic of the input question to answer the input question.

7. The method of claim 6 , further comprising:
responsive to a topic of the input question failing to match a trending topic, initially utilizing, by the processor, both real-time information sources and static information sources related to the topic of the input question to answer the input question.

8. The method of claim 1 , further comprising:
receiving, by the processor, an indication of an external event; and
ingesting, by the processor, data related to the external event prior to receiving the input question.

9. A computer program product comprising a non-transitory computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:
parse a received input question having a set of question characteristics;
compare the set of question characteristics found in the received input question to question characteristics associated with a set of previous questions;
responsive to the set of question characteristics found in the received input question matching the question characteristics associated with one or more previous questions in the set of previous questions above a related-question predetermined threshold, identify whether answers to the one or more previous questions were obtained from static information sources or real-time information sources; and
responsive to the answers to the one or more previous questions being obtained from the real-time information sources above the predetermined real-time threshold, initially utilize real-time information sources related to the characteristics of the input question to answer the input question.

10. The computer program product of claim 9 , wherein the computer readable program further causes the computing device to:
responsive to the answers to the one or more previous questions failing to be obtained from the real-time information sources above the predetermined real-time threshold and responsive to the answers to the one or more previous questions being obtained from the static information sources above a predetermined static threshold, initially utilize static information sources related to the characteristics of the input question to answer the input question.

11. The computer program product of claim 9 , wherein the computer readable program further causes the computing device to:
responsive to the answers to the one or more previous questions failing to be obtained from the real-time information sources above the predetermined real-time threshold and responsive to the answers to the one or more previous questions failing to be obtained from the static information sources above a predetermined static threshold, initially utilize both real-time information sources and static information sources related to the characteristics of the input question to answer the input question.

12. The computer program product of claim 9 , wherein the computer readable program further causes the computing device to:
responsive to the set of question characteristics found in the received input question failing to matching the question characteristics associated with one or more previous questions in the set of previous questions above the related-question predetermined threshold, analyze the input question for relevance to trending topics; and
responsive to a topic of the input question matching a trending topic, initially utilize real-time information sources related to the topic of the input question to answer the input question.

13. The computer program product of claim 12 , wherein the computer readable program further causes the computing device to:
responsive to a topic of the input question failing to match a trending topic, initially utilize both real-time information sources and static information sources related to the topic of the input question to answer the input question.

14. The computer program product of claim 9 , wherein the computer readable program further causes the computing device to:
receive an indication of an external event; and
ingest data related to the external event prior to receiving the input question.

15. An apparatus comprising:
a processor; and
a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to:
parse a received input question having a set of question characteristi

Assignees

• IBM

Inventors

• Dettman Elizabeth T
• Dubbels Joel C
• Freed Andrew R
• Petri John E
• Schroeder Michael W

Classifications

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/24 Primary

  Querying · CPC title

• G06F17/30867 Primary

  Physics · mapped topic

• G06F17/30654

  Physics · mapped topic

• G06F16/3329 Primary

  Natural language query formulation · CPC title