Apparatus, system, and method for natural language processing

• US 8,943,094 B2
• Filed: 09/22/2009
• Issued: 01/27/2015
• Est. Priority Date: 09/22/2009
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Next IT Corporation (Verint Systems Incorporated)
• Inventors: Miller, Tanya M, Zartler, Mark, Brown, Fred
• Primary Examiner(s): Chau, Dung K
• Application Number:
  US12/564,546
• Publication Number:
  US 20110071819A1
• Time in Patent Office: 1,953 Days
• Field of Search: None
• US Class Current: 707/771
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/258 Data format conversion from or to a database
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/43 Querying
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

Various embodiments are described for searching and retrieving documents based on a natural language input. A computer-implemented natural language processor electronically receives a natural language input phrase from an interface device. The natural language processor attributes a concept to the phrase with the natural language processor. The natural language processor searches a database for a set of documents to identify one or more documents associated with the attributed concept to be included in a response to the natural language input phrase. The natural language processor maintains the concepts during an interactive session with the natural language processor. The natural language processor resolves ambiguous input patterns in the natural language input phrase with the natural language processor. The natural language processor includes a processor, a memory and/or storage component, and an input/output device.

Claims

1. A method, comprising:

electronically receiving, by a computer-implemented natural language processor, a natural language input phrase from an interface device during an interactive session;

attributing, by the natural language processor, a concept to the natural language input phrase, wherein the concept is a breakdown of one or more ideas in the natural language input phrase and the attributing is based at least in part on determining a pattern among terms in the natural language input phrase;

associating a word in the natural language input phrase with the concept;

searching a database, by the natural language processor, for a set of documents to identify one or more documents associated with the attributed concept to be included in a response to the natural language input phrase;

causing the response to be provided to a user, the response including the one or more identified documents associated with the attributed concept;

maintaining, by the natural language processor, the concept during the interactive session between the natural language processor and the interface device;

receiving another natural language input phrase during the interactive session; and

determining that one or more ambiguous words in the another natural language input phrase correspond to the word that is associated with the concept.

2. The method of claim 1, wherein the concept comprises any one or more patterns of:

one or more vocab terms comprising a grouping of unambiguous synonyms and misspellings,

one or more helper terms comprising words that have no unambiguous synonyms,

one or more building blocks, individual building blocks comprising one or more of a list of vocab/helper terms or a list of concepts, or

one or more dictionary text files, tabular text data files, regular expressions, lex types and other constructs to impact scoring, and contextual awareness.

3. The method of claim 1, further comprising:

identifying, by the natural language processor, a goal associated with the natural language input phrase; and

initiating, by the natural language processor, an interactive dialog between the interface device and the natural language processor to acquire information associated with the goal.

4. The method of claim 3, further comprising:

assigning, by the natural language processor, a primary goal variable to be used to complete the identified goal;

receiving a tangential request, wherein the tangential request is unrelated to the identified goal;

completing, by the natural language processor, the tangential request; and

returning, by the natural language processor, to the primary goal variable.

5. The method of claim 1, wherein the searching further comprises:

performing, by the natural language processor, a primary search in the database based on the natural language input phrase;

providing, by the natural language processor, a primary response in accordance with the primary search;

performing, by the natural language processor, a secondary search in the database after the primary search; and

providing, by the natural language processor, a secondary response to the interface device in accordance with the secondary search.

6. The method of claim 5, wherein the performing the primary search comprises searching the database, by the natural language processor, for concepts attributed to the natural language input phrase;

and

wherein the performing the secondary search comprises searching, by the natural language processor, on material concepts identified in the natural language input phrase.

7. The method of claim 6, further comprising providing to the interface device, by the natural language processor, related responses based on the secondary search.

8. The method of claim 1, further comprising:

creating, by the natural language processor, multiple concept matching units; and

prompting the interface device, by the natural language processor, for clarification of ambiguous concepts contained in the multiple concept matching units.

9. The method of claim 1, wherein the pattern among the terms in the natural language input phrase comprises an ordering of any two or more of vocab terms, helper terms, or building blocks of the natural language input phrase.

10. The method of claim 1, wherein the pattern among the terms in the natural language input phrase comprises a proximity of any two or more of vocab terms, helper terms, or building blocks of the natural language input phrase.

11. The method of claim 1, wherein one or more of the receiving the natural language input phrase, the attributing or the searching is performed at least in part by an information retrieval engine (IRE).

12. The method of claim 1, wherein the one or more identified documents do not contain a term expressly found in the natural language input phrase.

13. The method of claim 1, further comprising searching the set of documents in the database, by the natural language processor, to identify one or more documents containing at least one term found in the natural language input phrase.

14. The method of claim 13, further comprising ranking, by the natural language processor, a plurality of documents in the set of documents based at least in part on terms in each of the plurality of documents that match a term in the natural language input phrase.

15. The method of claim 14, further comprising organizing, by the natural language processor, the plurality of documents based at least in part on the ranking.

16. The method of claim 1, further comprising indexing, by the natural language processor, the set of documents according to one or both of vocabulary terms or concepts.

17. One or more non-transitory computer-readable media having computer-readable instructions thereon which, when executed by a computer, implement the method of claim 1.

18. A system, comprising:

one or more processors; and

memory, communicatively coupled to the one or more processors, storing one or more modules configured to;

electronically receive a natural language input phrase from an interface device;

attribute a concept to the natural language input phrase, wherein the concept is a breakdown of one or more ideas in the input phrase and the attributing is based at least in part on a pattern among terms in the natural language input phrase;

associate a word in the natural language input phrase with the concept;

search a database of a set of documents to identify one or more documents associated with the attributed concept to be included in a response to the natural language input phrase;

maintain the concept during an interactive session between the natural language processor and the interface device;

receive an ambiguous natural language input phrase during the interactive session; and

determine that the ambiguous natural language input phrase has a same meaning as the word that is associated with the concept.

19. The system of claim 18, wherein the one or more modules are further configured to:

store in the memory the word that is associated with the concept.

20. The system of claim 18, wherein the one or more modules are further configured to:

identify a goal associated with the natural language input phrase; and

initiate an interactive dialog between the interface device and the natural language processor to acquire information associated with the goal.

21. The system of claim 20, wherein the one or more modules are further configured to:

request additional information from the interface device when the identified goal cannot be completed;

assign a primary goal variable to be used to complete the identified goal;

receive a tangential request;

process the tangential request;

complete the tangential request; and

return the completed tangential request to the primary goal variable to complete the primary goal.

22. The system of claim 18, wherein the one or more modules are further configured to:

perform a primary search in the database based on the natural language input phrase;

provide a primary response in accordance with the primary search;

perform a secondary search in the database after the primary search; and

provide a secondary response to the interface device in accordance with the secondary search.

23. The system of claim 18, wherein the one or more modules are further configured to:

create multiple concept matching units; and

prompt the interface device for clarification of ambiguous concepts contained in the multiple concept matching units.

24. The system of claim 18, wherein the pattern among the terms in the natural language input phrase comprises an ordering of any two or more of vocab terms, helper terms, or building blocks of the natural language input phrase.

25. The system of claim 18, wherein the one or more modules are further configured to search the set of documents in the database to identify one or more documents containing at least one term found in the natural language input phrase.

26. The system of claim 18, wherein the one or more modules are further configured to index the set of documents according to one or both of vocabulary terms or concepts.

27. One or more non-transitory computer-readable media having computer-readable instructions thereon which, when executed by a computing device, cause the computing device to perform operations comprising:

receiving natural language input of a user;

identifying one or more components of the natural language input and a pattern of the one or more components, the pattern including at least one of an order of the one or more components or a proximity of the one or more components to each other, the one or more components including a vocab term component representing at least one of an unambiguous synonym of a term in the natural language input or a spelling variation of a term in the natural language input;

identifying a concept of the natural language input based at least in part on the pattern of the one or more components;

receiving ambiguous natural language input of the user; and

determining a meaning of the ambiguous natural language input of the user based at least in part on the concept of the natural language input.