Answering time-sensitive questions

Patent metadata

Field	Value
Publication number	US-9613091-B2
Application number	US-201615273738-A
Country	US
Kind code	B2
Filing date	Sep 23, 2016
Priority date	Aug 7, 2014
Publication date	Apr 4, 2017
Grant date	Apr 4, 2017

Abstract

A method providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP) is provided. The method may include receiving the input question. The method may also include performing natural language processing (NLP) analysis on the input question to extract a required value phrase. The method may further include forming at least one mathematical equation based on the extracted required value phrase. Additionally, the method may include forming at least one interim question based on the extracted required value phrase. The method may further include solving the at least one formed mathematical equation and the at least one formed interim question. The method may also include narrating the answer to the input question in natural language based on the solved at least one interim question or the solved at least one mathematical equation.

First claim

What is claimed is:

1. A method for providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP), the method comprising:
creating and maintaining an online T-Word Dictionary, wherein creating and maintaining the online T-Word Dictionary comprises:
determining a relationship between a plurality of T-Words and a plurality of corresponding values, wherein the plurality of corresponding values include a plurality of related lookup phrases and a plurality of concept terms;
mapping the plurality of T-Words to the plurality of corresponding values based on the determined relationship; and
storing the mapped plurality of T-Words to the plurality of corresponding values in the online T-Word Dictionary;

receiving the input question, wherein the input question is entered by a user via a graphical user interface associated with a first computer;
performing natural language processing (NLP) analysis on the input question to extract a required value phrase;
forming at least one mathematical equation based on the extracted required value phrase, wherein forming the at least one mathematical equation comprises:
identifying the at least one time-sensitive word or the at least one time-sensitive phrase contained in the received input question, wherein a value associated with the identified at least one time-sensitive word or the at least one time-sensitive phrase varies according to a particular point in time, and wherein the identifying comprises communicating online with a second computer to access the online T-Word Dictionary; and
resolving the identified at least one time-sensitive word or the at least one time-sensitive phrase contained in the received input question, wherein the resolving comprises communicating online with the second computer to access the online T-Word Dictionary and recursively mapping a plurality of variables associated with the identified at least one time-sensitive word or the at least one time-sensitive phrase to at least one formula contained in the T-Word Dictionary;

determining the answer to the input question in natural language based on the solved at least one mathematical equation, wherein the determining comprises the first computer interacting with an on-line question-answer system to search an internet, a plurality of online data repositories, a plurality of online databases, and a plurality of online corpuses according to the value associated with the identified at least one time-sensitive word or the at least one time-sensitive phrase at the particular point in time; and
narrating the answer to the input question in natural language based on the solved at least one mathematical equation.

2. The method of claim 1 further comprising:
determining at least one relevant variable based on the extracted required value phrase; and
determining at least one current value for the at least one determined relevant variable.

3. The method of claim 1 , wherein identifying the at least one time-sensitive word or the at least one time-sensitive phrase comprises the use of a T-Word Dictionary.

4. The method of claim 1 , wherein an output from the natural language processing (NLP) is stored in a temporary repository or held in memory.

5. The method of claim 3 , wherein the T-Word Dictionary comprises a set of T-Words and their corresponding values.

6. The method of claim 2 , wherein determining the at least one current value comprises asking at least one interim question to at least one of a question-answer system by searching an internet; by searching a data repository or database; and by searching a Corpus.

7. The method of claim 3 , wherein the T-word Dictionary comprises the use of a text list; a key-value pair; an XML; or a table in a data repository.

8. The method of claim 1 , wherein performing natural language processing (NLP) analysis on the input question comprises at least one of performing part-of-speech (POS) tagging; performing parsing or syntactic analysis; performing phrase chunking; performing named entity recognition (NER); and determining a typed dependency.

9. A computer system for providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP), the computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
creating and maintaining an online T-Word Dictionary, wherein creating and maintaining the online T-Word Dictionary comprises:
determining a relationship between a plurality of T-Words and a plurality of corresponding values, wherein the plurality of corresponding values include a plurality of related lookup phrases and a plurality of concept terms;
mapping the plurality of T-Words to the plurality of corresponding values based on the determined relationship; and
storing the mapped plurality of T-Words to the plurality of corresponding values in the online T-Word Dictionary;

receiving the input question, wherein the input question is entered by a user via a graphical user interface associated with a first computer;
performing natural language processing (NLP) analysis on the input question to extract a required value phrase;
forming at least one mathematical equation based on the extracted required value phrase, wherein forming the at least one mathematical equation comprises:
identifying the at least one time-sensitive word or the at least one time-sensitive phrase contained in the received input question, wherein a value associated with the identified at least one time-sensitive word or the at least one time-sensitive phrase varies according to a particular point in time, and wherein the identifying comprises communicating online with a second computer to access the online T-Word Dictionary; and
resolving the identified at least one time-sensitive word or the at least one time-sensitive phrase contained in the received input question, wherein the resolving comprises communicating online with the second computer to access the online T-Word Dictionary and recursively mapping a plurality of variables associated with the identified at least one time-sensitive word or the at least one time-sensitive phrase to at least one formula contained in the T-Word Dictionary;

determining the answer to the input question in natural language based on the solved at least one mathematical equation, wherein the determining comprises the first computer interacting with an on-line question-answer system to search an internet, a plurality of online data repositories, a plurality of online databases, and a plurality of online corpuses according to the value associated with the identified at least one time-sensitive word or the at least one time-sensitive phrase at the particular point in time; and
narrating the answer to the input question in natural language based on the solved at least one mathematical equation.

10. The computer system of claim 9 , further comprising:
determining at least one relevant variable based on the extracted required value phrase; and
determining at least one current value for the at least one determined relevant variable.

11. The computer system of claim 9 , wherein identifying the at least one time-sensitive word or the at least one time-sensitive phrase comprises the use of a T-Word Dictionar

Assignees

• IBM

Inventors

• Mungi Ashish
• Mustafi Joy

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/3344

  using natural language analysis · CPC title

• G06F40/253

  Grammatical analysis; Style critique · CPC title

• G06F16/3329

  Natural language query formulation · CPC title