STRUCTURED NATURAL LANGUAGE QUERY AND KNOWLEDGE SYSTEM

• US 20070294233A1
• Filed: 08/28/2007
• Published: 12/20/2007
• Est. Priority Date: 10/31/2002
• Status: Active Grant

• Current Assignee: NEC Solution Innovators, Ltd (NEC Corporation)
• Original Assignee: Biomedical Objects Incorporated
• Inventors: Sheu, Phillip, Kitazawa, Atsushi
• Granted Patent: US 7,620,542 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A structured natural language query and knowledge system is provided to allow a user who lacks programming skills to enter a database query or a rule in the form of a structured natural language sentence. The scope of the sentence is preferably defined by an improved object relational query language, an object relational algebra, or both. Command and conditions that appear in natural language form are defined with corresponding formal query texts. A user is prompted to compose a structured natural language sentence using the defined commands and conditions. The user-selected command and its arguments appear as the verb phrase of a structured natural language sentence. The user-selected conditions and their parameters appear as the adjective phrases of the sentence. The sentence is parsed and changed into a translated formal query text for formal database query and rule processing.

Claims

1. A computer-implemented method of translating an imperative natural language sentence into formal query text, the method comprising:

receiving a natural language sentence;

parsing the natural language sentence to identify one or more verb phrases of the sentence;

parsing the natural language sentence to identify one or more noun phrases of the sentence;

determining from each parsed natural language verb phrase one or more defined general methods;

determining from each parsed natural language noun phrase one or more data source elements; and

using the one or more determined general methods and the one or more determined data source elements to create a formal query text in an object relational algebra.

2. The method of claim 1, farther comprising searching a database for data entries stored within the database that satisfies the formal query text.

3. The method of claim 2, further comprising providing through a user interface one or more data entries stored within the database that satisfy the formal query text.

4. The method of claim 1, further comprising:

parsing the natural language sentence to identify one or more adjective phrases of the sentence;

determining from each parsed natural language adjective phrase one or more defined conditions; and

wherein the one or more defined conditions are used with the one or more determined general methods and the one or more determined data source elements to create the formal query text.

5. The method of claim 1, wherein at least one of the defined data source elements comprises a set of objects, a table, or a class.

6. The method of claim 1, wherein at least one defined general methods is capable of returning a value other than a Boolean true or false value.

7. A system for translating an imperative natural language sentence into formal query text, the system comprising:

a database comprising a plurality of data objects, the database further comprising a plurality of user-defined general methods, a plurality of data source elements, and a plurality of user-defined conditions;

a parsing module, the parsing module configured to parse a natural language sentence to identify one or more verb phrases of the sentence, one or more noun phrases and an optional one or more adjective phrases; and

a translation module in communication with the database, the translation module configured to (a) determine from a natural language verb phrase one or more defined general methods, (b) determine from each noun phrase one or more data source elements, and (c) determine from each optional adjective phrase one or more defined conditions, the translation module further configured to create formal query text in an object relational algebra from the one or more determined general methods, the one or more determined data source elements, and the optional one or more determined conditions.

8. The system of claim 7, further comprising a formal query processing module in communication with the database, the formal query process module configured to search the database for data objects that satisfy a formal query text.

9. The system of claim 8, further comprising a user interface in communication with the formal query processing module, the user interface adapted to receive from a user a natural language sentence.

10. The system of claim 7, wherein the user interface is further adapted to convey to a user data entries from the database found by the formal query processing module to satisfy a formal query text.

11. The system of claim 7, wherein at least one of the defined data source elements comprises a set of objects, a table, or a class.

12. The system of claim 7, wherein at least one of the defined general methods is capable of returning a value other than a Boolean true or false value.

13. A computer-implemented method of creating a query in an object-relational algebra, the method comprising:

prompting a user to choose one or more previously defined object-relational algebra general methods and/or one or more object-relational algebra operators;

prompting the user to choose from a list of defined data source elements as one or more arguments to the one or more methods selected and/or the one or more operators selected;

prompting the user to choose an optional one or more conditions from at least a set of defined conditions, and prompting the user to specify one or more parameters for each selected condition; and

using object-relational algebra to create a query with the responses received from the user.

14. The method of claim 13, further comprising receiving from a user, in response to a prompt for an argument of a general method or a parameter of a condition, a constant or a variable that is declared to be a range variable, a bag variable, a set variable, a temporary variable, a temporary bag variable, or a temporary set variable.

15. The method of claim 13, further comprising receiving from a user, in response to a prompt for an argument of a general method or a parameter of a condition, a previously created constant or variable.

16. The method of claim 13, further comprising receiving from a user, in response to a prompt for a data source element, an object relational query created recursively.

17. A system for creating a query in an object-relational algebra, the system comprising:

a database comprising previously defined general methods, object-relational algebra operators, defined data source elements, defined conditions;

a user interface adapted to prompt a user to choose one or more previously defined object-relational algebra general methods and/or one or more object-relational algebra operators;

the user interface further adapted to prompt the user to choose from a list of defined data source elements as one or more arguments to the one or more methods selected and/or the one or more operators selected;

the user interface further adapted to prompt the user to choose an optional one or more conditions from at least a set of defined conditions, and prompting the user to specify one or more parameters for each selected condition; and

a query translation module configured to use object-relational algebra to create a query with the responses received from the user.

18. The system of claim 17, further comprising a formal query processing module in communication with the database, the formal query process module configured to search the database for data entries that satisfy a formal query text.

19. The system of claim 17, wherein the user interface is further adapted to convey to a user data entries from the database found by the formal query processing module to satisfy a formal query text.

20. The system of claim 17, wherein the data source elements comprise a constant or a variable that is declared to be a range variable, a bag variable, a set variable, a temporary variable, a temporary bag variable, or a temporary set variable.

21. The system of claim 17, wherein the parameters of a condition comprise a constant or a variable that is declared to be a range variable, a bag variable, a set variable, a temporary variable, a temporary bag variable, or a temporary set variable.

22. The system of claim 17, wherein the data source elements comprise a previously created constant or variable.

23. The system of claim 17, wherein the parameters of a condition comprise a previously created constant or variable.

24. The system of claim 17, wherein the data source elements comprise an object relational query created recursively.