SYSTEM AND METHOD FOR NATURAL LANGUAGE QUERYING

• US 20130262361A1
• Filed: 04/02/2013
• Published: 10/03/2013
• Est. Priority Date: 04/02/2012
• Status: Active Grant

• Current Assignee: Capricorn Holdings Pte, Ltd.LTD.
• Original Assignee: Playence GmbH
• Inventors: Arroyo, Sinuh, Lpez Cobo, Jos Manuel, Rey, Guillermo Alvaro, Alonso, Silvestre Losada
• Granted Patent: US 9,406,020 B2
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

A system and method for information retrieval are presented. A natural language query is received from a client computer. The natural language query is analyzed to identify a plurality of terms, and a relationship between a pair of terms in the plurality of terms is determined using a knowledge model. The knowledge model defines a plurality of entities and interrelationships between one or more of the plurality of entities for a knowledge domain. A triple statement is constructed using the relationship between the pair of terms, and a query is executed against a knowledge base using the triple statement to generate a set of results. The knowledge base identifies a plurality of items, each of the plurality of items is associated with at least one annotation identifying at one of the entities in the knowledge model. The set of results are transmitted to the client computer.

Claims

1. An information retrieval system, comprising:

a knowledge model database configured to store a knowledge model for a knowledge domain, the knowledge model defining a plurality of entities and interrelationships between one or more of the plurality of entities;

a knowledge base identifying a plurality of items, each of the plurality of items being associated with at least one annotation identifying at one of the entities in the knowledge model; and

a query processing server configured to;

receive, from a client computer, a natural language query using a computer network,

analyze the natural language query to identify a plurality of terms,

determine a relationship between a pair of terms in the plurality of terms using the knowledge model,

construct a triple statement using the relationship between the pair of terms,

execute a query against the knowledge base using the triple statement to generate a set of results, and

transmit, to the client computer, the set of results.

2. The system of claim 1, wherein the query processing server is configured to:

analyze the natural language query using named entity recognition.

3. The system of claim 1, wherein the knowledge model database is configured as a triplestore.

4. The system of claim 1, wherein the query processing server is configured to:

determine a distance between each term in the pair of terms using the knowledge model.

5. The system of claim 4, wherein the query processing server is configured to, when the distance between each term in the pair of terms is two or greater, discard the term pair.

6. The system of claim 1, wherein the query processing server is configured to:

determine a type of each term in the pair of terms, where the type is one of an instance type, a concept type, and a relationship type.

7. The system of claim 6, wherein the query processing server is configured to:

when the type of each term in the pair of terms is the instance type or the concept type, analyze each of the plurality of the terms to identify a linking term having a type that is the relationship type, where the linking term links the pair of terms in the knowledge model.

8. A method for information retrieval, comprising:

receiving, from a client computer, a natural language query using a computer network;

analyzing the natural language query to identify a plurality of terms;

determining a relationship between a pair of terms in the plurality of terms using a knowledge model, the knowledge model defining a plurality of entities and interrelationships between one or more of the plurality of entities for a knowledge domain;

constructing a triple statement using the relationship between the pair of terms;

executing a query against a knowledge base using the triple statement to generate a set of results, the knowledge base identifying a plurality of items, each of the plurality of items being associated with at least one annotation identifying at one of the entities in the knowledge model; and

transmitting, to the client computer, the set of results.

9. The method of claim 8, including analyzing the natural language query using named entity recognition.

10. The method of claim 8, wherein the knowledge model database is configured as a triplestore.

11. The method of claim 8, including determining a distance between each term in the pair of terms using the knowledge model.

12. The method of claim 11, including, when the distance between each term in the pair of terms is two or greater, discarding the term pair.

13. The method of claim 8, including determining a type of each term in the pair of terms, where the type is one of an instance type, a concept type, and a relationship type.

14. The method of claim 13, including, when the type of each term in the pair of terms is the instance type or the concept type, analyzing each of the plurality of the terms to identify a linking term having a type that is the relationship type, where the linking term links the pair of terms in the knowledge model.

15. A non-transitory computer-readable medium containing instructions that, when executed by a processor, cause the processor to perform the steps of:

receiving, from a client computer, a natural language query using a computer network;

analyzing the natural language query to identify a plurality of terms;

determining a relationship between a pair of terms in the plurality of terms using a knowledge model, the knowledge model defining a plurality of entities and interrelationships between one or more of the plurality of entities for a knowledge domain;

constructing a triple statement using the relationship between the pair of terms;

executing a query against a knowledge base using the triple statement to generate a set of results, the knowledge base identifying a plurality of items, each of the plurality of items being associated with at least one annotation identifying at one of the entities in the knowledge model; and

transmitting, to the client computer, the set of results.

16. The medium of claim 15, including instructions that, when executed by a processor, cause the processor to perform the steps of:

analyzing the natural language query using named entity recognition.

17. The medium of claim 15, including instructions that, when executed by a processor, cause the processor to perform the steps of:

determining a distance between each term in the pair of terms using the knowledge model.

18. The medium of claim 17, including instructions that, when executed by a processor, cause the processor to perform the steps of, when the distance between each term in the pair of terms is two or greater, discarding the term pair.

19. The medium of claim 15, including instructions that, when executed by a processor, cause the processor to perform the steps of:

determining a type of each term in the pair of terms, where the type is one of an instance type, a concept type, and a relationship type.

20. The medium of claim 19, including instructions that, when executed by a processor, cause the processor to perform the steps of, when the type of each term in the pair of terms is the instance type or the concept type, analyzing each of the plurality of the terms to identify a linking term having a type that is the relationship type, where the linking term links the pair of terms in the knowledge model.