Constructing concepts from a task specification

• US 10,162,852 B2
• Filed: 12/16/2013
• Issued: 12/25/2018
• Est. Priority Date: 12/16/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chiticariu, Laura, Cypher, George A., Krishnamurthy, Rajasekar, Li, Yunyao, Yang, Huahai
• Primary Examiner(s): Pyo, Monica M
• Application Number:
  US14/107,077
• Publication Number:
  US 20150169742A1
• Time in Patent Office: 1,835 Days
• Field of Search: 707769-771
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/2452 Query translation
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems

Abstract

Embodiments relate to facilitating construction of concepts from a task specification. A method includes receiving, from a user via a user interface, a task specification in natural language form. The method also includes parsing the task specification into a plurality of components, and searching a database for an existing concept having a pattern that approximates at least a portion of the plurality of components. The concept includes semantic meanings that are representable by textual patterns. The method further includes identifying any components of the plurality of components that are not included in the existing concept, and building a new concept that combines the existing concept and the components of the plurality of components that are not included in the existing concept.

Claims

1. A computer-implemented method, comprising:

receiving, from a user via a user interface, a task specification in natural language form;

parsing, by a processor, the task specification into a plurality of components by performing a grammatical analysis to identify the plurality of components and relationships among the plurality of components, wherein the plurality of components comprise a primary term, a verb, a subject, and a modifier;

creating, by the processor, a search query from the plurality of components and the relationships among the plurality of components, wherein the search query comprises selectable options for determining the relationships;

searching, by the processor and using the search query, a database for an existing concept having a pattern that approximates at least a portion of the plurality of components, the concept including semantic meanings that are representable by textual patterns;

identifying, by the processor, any components of the plurality of components that are not included in the existing concept;

building, by the processor, a new concept that combines the existing concept and the components of the plurality of components that are not included in the existing concept; and

displaying, via the user interface, the new concept in natural language form, decomposed components of the new concept, and corresponding relationships between the new concept and the decomposed components of the new concept, wherein the corresponding relationships are displayed through a connective line between the new concept and the decomposed components of the new concept.

2. The method of claim 1, further comprising displaying, via the user interface, the existing concept in natural language form.

3. The method of claim 1, further comprising displaying, via the user interface, decomposed components of the existing concept and corresponding relationships.

4. The method of claim 1, further comprising displaying, via the user interface, a relationship between the existing concept and the new concept through a connective line.

5. The method of claim 1, further comprising:

providing, via the user interface, an option to modify at least one of;

the existing concept and corresponding relationships; and

the new concept and corresponding relationships, and

amending, in response to user input via the user interface, the at least one of the existing concept and corresponding relationships and the new concept and corresponding relationships to reflect modifications from the user input.

6. The method of claim 1, wherein the new concept represents a first concept, the method further comprising:

building a second concept from the components of the plurality of components that are not included in the existing concept.

7. The method of claim 6, further comprising:

displaying, via the user interface, the second concept, corresponding components of the second concept, and corresponding relationships.

8. The method of claim 6, further comprising:

determining relationships between the existing concept, the first concept, and the second concept from contextual information derived from components of the existing concept, the components of the first concept, and the components of the second concept.

9. The method of claim 1, further comprising:

receiving, via the user interface, another task specification in natural language form;

parsing the other task specification into another plurality of components;

searching the database for an existing concept having a pattern that approximates at least a portion of the other plurality of components;

upon determining that no existing concept is stored in the database, creating a third concept for the task specification that includes the other plurality of components and relationships among the other plurality of components; and

displaying the third concept via the user interface.

10. The method of claim 1, wherein the new concept that combines the existing concept and the components of the plurality of components that are not included in the existing concept represents a union of the existing concept and the components of the plurality of components that are not included in the existing concept.

11. A computer program product, comprising:

a computer readable storage medium having program code embodied therewith, the program code executable by a processor to implement;

receiving, from a user via a user interface, a task specification in natural language form;

parsing, by the processor, the task specification into a plurality of components by performing a grammatical analysis to identify the plurality of components and relationships among the plurality of components, wherein the plurality of components comprise a primary term, a verb, a subject, and a modifier;

creating, by the processor, a search query from the plurality of components and the relationships among the plurality of components, wherein the search query comprises selectable options for determining the relationships;

searching, by the processor and using the search query, a database for an existing concept having a pattern that approximates at least a portion of the plurality of components, the concept including semantic meanings that are representable by textual patterns;

identifying, by the processor, any components of the plurality of components that are not included in the existing concept;

building, by the processor, a new concept that combines the existing concept and the components of the plurality of components that are not included in the existing concept; and

displaying, via the user interface, the new concept in natural language form, decomposed components of the new concept, and corresponding relationships between the new concept and the decomposed components of the new concept, wherein the corresponding relationships are displayed through a connective line between the new concept and the decomposed components of the new concept.

12. The computer program product of claim 11, wherein the program code executable by the computer further implements displaying, via the user interface:

the existing concept in natural language form, decomposed components of the existing concept, and corresponding relationships; and

a relationship between the existing concept and the new concept.

13. The computer program product of claim 12, wherein the program code executable by the computer further implements:

providing, via the user interface, an option to modify at least one of;

the existing concept and corresponding relationships; and

the new concept and corresponding relationships, and

amending, in response to user input via the user interface, the at least one of the existing concept and corresponding relationships and the new concept and corresponding relationships to reflect modifications from the user input.

14. The computer program product of claim 11, wherein the new concept represents a first concept, and the program code executable by the computer further implements:

building a second concept from the components of the plurality of components that are not included in the existing concept.

15. The computer program product of claim 14, wherein the program code executable by the computer further implements:

displaying, via the user interface, the second concept, corresponding components of the second concept, and corresponding relationships.

16. The computer program product of claim 14, wherein the program code executable by the computer further implements:

determining relationships between the existing concept, the first concept, and the second concept from contextual information derived from components of the existing concept, the components of the first concept, and the components of the second concept.

17. A system, comprising:

a memory having computer readable computer instructions; and

a processor for executing the computer readable instructions to perform a method comprising;

receiving, from a user via a user interface, a task specification in natural language form;

parsing, by the processer, the task specification into a plurality of components by performing a grammatical analysis to identify the plurality of components and relationships among the plurality of components, wherein the plurality of components comprise a primary term, a verb, a subject, and a modifier;

creating, by the processor, a search query from the plurality of components and the relationships among the plurality of components, wherein the search query comprises selectable options for determining the relationships;

searching, by the processor and using the search query, a database for an existing concept having a pattern that approximates at least a portion of the plurality of components, the concept including semantic meanings that are representable by textual patterns;

identifying, by the processor, any components of the plurality of components that are not included in the existing concept;

building, by the processor, a new concept that combines the existing concept and the components of the plurality of components that are not included in the existing concept; and

displaying, via the user interface, the new concept in natural language form, decomposed components of the new concept, and corresponding relationships between the new concept and the decomposed components of the new concept, wherein the corresponding relationships are displayed through a connective line between the new concept and the decomposed components of the new concept.