Adjusting Fact-Based Answers to Consider Outcomes

• US 20160171392A1
• Filed: 02/23/2016
• Published: 06/16/2016
• Est. Priority Date: 11/19/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Allen, Corville O., Chung, Albert A., Freed, Andrew R.
• Granted Patent: US 10,664,763 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2322 using timestamps
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3331 Query processing
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 25/63 for estimating an emotional state

Abstract

A method, system and computer-usable medium are disclosed for adjusting fact-based answers provided by a question/answer (QA) system. A user submits a question to the QA system, where it is categorized into a question type. The QA system then processes the question to generate an answer. The QA system then generates an answer adjustment if it is determined that the question type and answer meet a predicted undesirable outcome. The answer adjustment may include a warning, a disclaimer, a recommendation, an alternative fact-based answer, a referral to an assistance service, or any combination thereof.

Claims

1. A computer-implemented method for adjusting answers to a question asked of a question/answer (QA) system, comprising:

receiving a question as user input from a user, the question being received by the QA system;

categorizing the question into a question type;

processing the question to generate an answer; and

generating an answer adjustment if it is determined that the question type and the answer correspond to a potentially undesirable outcome criteria.

2. The method of claim 1, wherein the answer adjustment is at least one member of the set of:

a warning;

a disclaimer;

an alternative answer

an assistance service;

a recommendation; and

a referral to an assistance service.

3. The method of claim 1, wherein the QA system is trained to identify a question that might lead to an undesirable outcome.

4. The method of claim 3, wherein the method of the training is selected from a group consisting of:

manual;

automated; and

learning.

5. The method of claim 1, wherein the answer and the answer adjustment are provided to the user.

6. The method of claim 1, further comprising generating and retaining a time-stamped record comprising:

the question;

the answer;

the answer adjustment; and

identification information associated with the user.

7-20. -20. (canceled)