Natural language based search engine and methods of use therefor

• US 20060224569A1
• Filed: 07/11/2005
• Published: 10/05/2006
• Est. Priority Date: 03/31/2005
• Status: Abandoned Application

• Current Assignee: Jiles Incorporated
• Original Assignee: Jiles Incorporated
• Inventors: DeSanto, John A., Fischer, Gordon H., Flowers, John S.
• Application Number:
  US11/178,513
• Publication Number:
  US 20060224569A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/295 Named entity recognition

Abstract

There is provided a search engine or other electronic search application that receives an inputted query in natural language. The search engine or application augments data derived from the query with additional data, for example, one or more concept link identifiers, that are in addition to concept link identifiers, derived from a standard output, resulting from the query being parsed by a parser. This additional data, based on the inputted query, potentially results in a more defined set and more accurate listing of one or more responses from the search engine or electronic search application.

Claims

1. A method for providing at least one response to at least one query in natural language, comprising:

populating a data store by obtaining documents from at least a portion of a corpus, isolating sentences from the documents, parsing the sentences into linked pairs of words in accordance with predetermined relationships, assigning concept identifiers to each word of the linked pair of words, assigning concept link identifiers to each pair of concept identifiers corresponding to each linked pair of words, and, combining the concept link identifiers for each sentence into a statement;

receiving an inputted query in natural language;

parsing the query into linked pairs of words, one word of the pair of words at a first position, and another word of the pair of words at a second position, each linked pair of words associated with a relational connector;

determining if the relational connector associated with each linked pair of words matches a predetermined relational connector, and if there is a match, creating an additional pair of words whose positions are opposite those of the pair of words whose relational connector matched the predetermined relational connector;

assigning concept identifiers to each word of each linked pair of words;

assigning concept link identifiers to each pair of concept identifiers corresponding to each linked pair of words;

combining the concept link identifiers into a query statement;

analyzing the query statement and the statements in the data store for matches between concept link identifiers;

isolating statements in the data store having at least one concept link identifier that matches at least one concept link identifier in the query statement; and

,

providing at least one sentence corresponding to at least one isolated statement in the data store as a response to the natural language query.

2. The method of claim 1, additionally comprising:

providing access to at least one document from which the at least one sentence, corresponding to the at least one matched statement, was isolated.

3. The method of claim 1, wherein the predetermined relationships are defined by a parser.

4. The method of claim 3, wherein the parser includes the Link Grammar Parser.

5. The method of claim 1, wherein isolating statements in the data store includes, isolating statements in the data store having the greatest number of concept links that match the greatest number of concept links in the query statement.

6. The method of claim 1, wherein assigning concept identifiers to each word of the query includes, performing a lookup in the data store for the concept identifier matching the word from the query.

7. The method of claim 6, wherein assigning concept link identifiers includes, performing a lookup in the data store for paired concept identifiers matching the paired concept identifiers from the query.

8. A method for analyzing a query to a search engine, comprising:

creating related pairs of words in the query, each of the related pairs of words including a relational connector, each of the related pairs of words including one word at a first position and one word at a second position;

identifying related pairs of words that include a relational connector that matches a relational connector from a collection of at least one predetermined relational connector;

creating additional related pairs of words from the identified pairs of words, including, changing the positions of the words from the identified pairs of words;

assigning concept identifiers to the each of the words in each of the related pairs of words;

creating pairs of concept identifiers by applying the assigned concept identifiers to each word in the related pairs of words;

assigning concept link identifiers to each pair of concept identifiers; and

,

combining all of the concept link identifiers into a query statement.

9. The method of claim 8, wherein all of the concept link identifiers of the query statement define a master set, where N is the number of concept link identifiers in the master set;

and,

creating a power set from the master set including, creating a plurality of subsets from the master set, the plurality of subsets defining members of the power set, the power set including at least one member of N concept link identifiers and at least N members of one concept link identifier.

10. The method of claim 8, wherein the creating related pairs of words, including the relational connectors includes, parsing the query in a parser.

11. The method of claim 10, wherein the parser includes the Link Grammar Parser.

12. The method of claim 8, additionally comprising:

analyzing a plurality of stored statements, the stored statements formed of a plurality of concept link identifiers, with the members of the power set, the analysis including, determining matches of the concept link identifiers in the stored statements with all of the concept link identifiers in each member of the power set.

13. The method of claim 12, additionally comprising:

isolating stored statements with concept link identifiers that match all of the concept link identifiers in a member of the power set.

14. The method of claim 13, wherein the stored statements with the greatest number of concept links, matching all of the concept links in the member of the power set with the greatest number of concept links, are assigned the highest rank.

15. The method of claim 14, wherein at least one stored statement of the highest rank is isolated.

16. The method of claim 15, wherein the at least one isolated stored statement is determined to be a response to the query.

17. The method of claim 16, wherein the at least one isolated stored statement corresponds to at least one sentence of a document, and, the at least one sentence is returned to a predetermined location.

18. The method of claim 17, wherein access to the document that included the at least one sentence is provided at the predetermined location in association with the returned sentence.

19. A method for analyzing a query to a search engine, comprising:

creating related pairs of words from the natural language of the query, each of the related pairs of words including a relational connector, each of the related pairs of words including one word at a first position and one word at a second position;

identifying related pairs of words that include a relational connector that matches a relational connector from a collection of at least one predetermined relational connector;

creating additional related pairs of words from the identified pairs of words, including, changing the positions of the words from the identified pairs of words;

assigning concept identifiers to the each of the words in each of the related pairs of words;

assigning concept link identifiers to each pair of concept identifiers; and

,

combining all of the concept link identifiers into a query statement.

20. The method of claim 19, wherein all of the concept link identifiers of the query statement define a master set, where N is the number of concept link identifiers in the master set;

and,

creating a power set from the master set including, creating a plurality of subsets from the master set, the plurality of subsets defining members of the power set, the power set including at least one member of N concept link identifiers and at least N members of one concept link identifier.

21. The method of claim 20, wherein the creating related pairs of words includes, parsing the query in a parser.

22. The method of claim 20, additionally comprising:

analyzing a plurality of stored statements, the stored statements formed of a plurality of concept link identifiers, with the members of the power set, the analysis including, determining matches of the concept link identifiers in the stored statements with all of the concept link identifiers in each member of the power set.

23. The method of claim 20, additionally comprising:

isolating stored statements with concept link identifiers that match all of the concept link identifiers in a member of the power set.

24. The method of claim 23, wherein the stored statements with the greatest number of concept links, matching all of the concept links in the member of the power set with the greatest number of concept links, are assigned the highest rank.

25. The method of claim 24, wherein at least one stored statement of the highest rank is isolated.

26. The method of claim 25, wherein the at least one isolated stored statement is determined to be a response to the query.

27. The method of claim 26, wherein the at least one isolated stored statement corresponds to at least one sentence of a document, and, the at least one sentence in natural language and the at least one sentence is returned to a predetermined location.

28. The method of claim 27, wherein access to the document that included the at least one sentence is provided at the predetermined location in association with the returned sentence.

29. A method for creating additional concept links from a set of concept pairs derived from a received query, for providing at least one response to the query, comprising:

reordering the positions of words in word pairs corresponding to concept pairs, that have a predetermined relational connector, to form new concept pairs, and,

adding the new concept pairs to the set of concept pairs.

30. The method of claim 29, wherein reordering the positions of the words in the word pairs includes switching the positions of the words in the word pairs.

31. The method of claim 29, wherein the relational connector is derived from a parser.

32. The method of claim 29, wherein the concept pairs are compared to corresponding data in a structured representation.

33. The method of claim 32, wherein the data in the structured representation includes concept link identifiers.

34. The method of claim 33, wherein concept pairs are assigned concept link identifiers, if a concept link identifier exists in the structured representation.

35. The method of claim 34, wherein the concept link identifiers are used to establish a query statement.

36. A system for providing at least one response to a received query, comprising:

at least one storage media for storing concept identifiers and concept link identifiers extracted from a corpus; and

,

a processor in communication with the at least one storage media, the processor programmed to;

create related pairs of words from the query, each of the related pairs of words including a relational connector, each of the related pairs of words including one word at a first position and one word at a second position;

identify related pairs of words that include a relational connector that matches a relational connector from a collection of at least one predetermined relational connector;

create additional related pairs of words from the identified pairs of words, including, changing the positions of the words from the identified pairs of words;

assign concept identifiers to the each of the words in each of the related pairs of words;

create pairs of concept identifiers by applying the assigned concept identifiers to each word in the related pairs of words;

assign concept link identifiers to each pair of concept identifiers; and

,

combine all of the concept link identifiers into a query statement.

37. The system of claim 36, wherein the processor is additionally programmed to:

arrange all of the concept link identifiers of the query statement into a master set, where N is the number of concept link identifiers in the master set; and

,

create a power set from the master set including, creating a plurality of subsets from the master set, the plurality of subsets defining members of the power set, the power set including at least one member of N concept link identifiers and at least N members of one concept link identifier.

38. The system of claim 37, wherein the processor is additionally programmed to:

analyze a plurality of statements stored in the at least one storage media, the statements stored in the at least one storage media being formed of a plurality of concept link identifiers, with the members of the power set, and, analyzing the plurality of statements stored in the at least one storage media with the members of the power set including, determining matches of the concept link identifiers in the stored statements with all of the concept link identifiers in each member of the power set.

39. The system of claim 38, wherein the processor is additionally programmed to:

isolate the statements stored in the at least one storage media that have concept link identifiers that match all of the concept link identifiers in a member of the power set.

40. The system of claim 39, wherein the processor is additionally programmed to:

select at least one of the statements stored in the at least one storage media that have been isolated, to provide at least one response to the query.

41. The system of claim 36, wherein the at least one storage media includes a structured representation of the corpus.