Method and system for searching data based on identified subset of categories and relevance-scored text representation-category combinations

• US 7,409,336 B2
• Filed: 06/19/2003
• Issued: 08/05/2008
• Est. Priority Date: 06/19/2003
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Siebel Systems Inc. (Oracle Corporation)
• Inventors: Pak, Wai H., Zhang, Yunfei, Caltabiano, Marc Alexander, Saputra, Sia Henry
• Primary Examiner(s): SMITS, TALIVALDIS IVARS
• Application Number:
  US10/465,338
• Publication Number:
  US 20040260534A1
• Time in Patent Office: 1,874 Days
• Field of Search: 704/9, 704/7, 704/10, 704/8, 707/1
• US Class Current: 704/9
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: Y10S 707/99931 Database or file accessing

Abstract

A method and system for analyzing natural language text to identify a set of categories of data in a knowledge base associated with the natural language text and selecting a category from the set of categories is provided. The method and system further provides automatically providing a single category if the set of categories only contains the single category. The method and system also provides that each category in the knowledge base is associated with a stored text representation of a sample natural language text and a score for the text representation-category combination, wherein the score is representative of a relative relevance of the text representation-category combination. The method and system further provide for modifying the score associated with the text representation-category combination of a selected category using feedback provided upon the selection.

Claims

1. A method comprising:

analyzing natural language text to identity a set of categories of data associated with the natural language text, wherein

the set of categories of data associated with the natural language text are a subset of categories associated with data in a knowledge base,

each category in the knowledge base is associated with a stored text representation of a sample natural language text for the category and a score for the text representation-category combination, and

the score is representative of a relative relevance of the text representation-category combination;

when the set of categories of data associated with the natural language text includes only one category,

automatically providing first data associated with the one category from the knowledge base; and

when the set of categories of data associated with the natural language text includes more than one category,

presenting the set of categories of data associated with the natural language text for selection of a selected category,

providing second data associated with the selected category from the knowledge base, and

modifying the score associated with the text representation-category combination of the selected category using feedback provided upon said selection.

2. The method of claim 1 wherein

the providing the first data comprises:

automatically sending a response to the natural language text, wherein

the response comprises the first data.

3. The method of claim 1 wherein

the providing the second data comprises:

sending a response to the natural language text, wherein

the response comprises the second data.

4. The method of claim 1 wherein

the presenting the set of categories comprises:

providing the text representation-category score for each category.

5. The method of claim 1 wherein

the data in the knowledge base comprise at least one of:

a solution;

a resolution; and

a template.

6. The method of claim 1 wherein

the data in the knowledge base comprise a solution to a problem stated in the natural language text.

7. The method of claim 6 wherein

the solution comprises a plurality of language-specific versions of the solution;

the solution is associated with one category of a plurality of categories; and

each language-specific version of the solution is associated with the one category.

8. The method of claim 1 wherein said providing first data is performed without user selection of the one category from the knowledge base.

9. The method of claim 1 further comprising:

receiving the natural language text from an external message source via a communication manager; and

transmitting the first data or second data using the communication manager.

10. The method of claim 1 further comprising:

analyzing a second natural language text to identify the selected category, wherein

the association of the selected category with the representation of the natural language text is used in said analyzing the second natural language text.

11. An application program interface comprising:

an analyzing function to analyze natural language text to identify a set of categories associated with the natural language text, wherein

the set of categories are a subset of categories associated with data in a knowledge base,

each category in the knowledge base is associated with a stored text representation of a sample natural language text for the category and a score for the text representation-category combination, and

the score is representative of a relative relevance of the text representation-category combination;

a providing function to provide data associated with a category from the knowledge base;

a presenting function to present the set of categories associated with the natural language text for selection of a selected category; and

a modifying function to modify the score associated with the text representation-category combination of the selected category using feedback provided upon said selection.

12. A system comprising:

analyzing means for analyzing natural language text to identify a set of categories of data associated with the natural language text, wherein

the set of categories are a subset of categories associated with data in a knowledge base,

each category in the knowledge base is associated with a stored text representation of a sample natural language text for the category and a score for the text representation-category combination, and

the score is representative of a relative relevance of the text representation-category combination;

first providing means for automatically providing first data associated with one category from the knowledge base, when the set of categories comprises only the one category;

presenting means for presenting the set of categories of data associated with the natural language text for selection of a selected category when the set of categories includes more than one category;

second providing means for providing second data associated with the selected category from the knowledge base; and

modifying means for modifying the score associated with the text representation-category combination of the selected category using feedback provided upon said selection.

13. The system of claim 12 wherein

the first providing means comprise:

sending means for automatically sending a response to the natural language text, wherein

the response comprises the first data.

14. The system of claim 12 wherein

the second providing means comprise:

sending means for sending a response to the natural language text, wherein

the response comprises the second data.

15. A system comprising:

an analyzing module configured to analyze natural language text to identify a set of categories of data associated with the natural language text, wherein

the set of categories are a subset of categories associated with data in a knowledge base,

each category in the knowledge base is associated with a stored text representation of a sample natural language text for the category and a score for the text representation-category combination, and

the score is representative of a relative relevance of the text representation-category combination;

a first providing module configured to provide first data associated with one category from the knowledge base, when the set of categories of data associated with the natural language text includes only the one category;

a presenting module configured to present the set of categories of data associated with the natural language text for selection of a selected category when the set of categories of data includes more than one category;

a second providing module configured to provide second data associated with the selected category from the knowledge base; and

a modifying module configured to modify the score associated with the text representation-category combination of the selected category using feedback provided upon said selection.

16. The system of claim 15 wherein

the first providing module comprises:

a sending module configured to automatically send a response to the natural language text, wherein

the response comprises the first data.

17. The system of claim 15 wherein

the second providing module comprises:

a sending module configured to send a response to the natural language text, wherein

the response comprises the second data.

18. A computer system comprising:

a processor for executing instructions; and

a memory for storing the instructions, wherein the instructions comprise;

analyzing instructions configured to analyze natural language text to identify a set of categories of data associated with the natural language text, wherein

the set of categories are a subset of categories associated with data in a knowledge base,

each category in the knowledge base is associated with a stored text representation of a sample natural language text for the category and a score for the text representation-category combination, and

the score is representative of a relative relevance of the text representation-category combination;

first providing instructions configured to provide first data associated with one category from the knowledge base, when the set of categories of data includes only the one category;

presenting instructions configured to present the set of categories of data associated with the natural language text for selection of a selected category when the set of categories of data includes more than one category;

second providing instructions configured to provide second data associated with the selected category from the knowledge base; and

modifying instructions configured to modify the score associated with the text representation-category combination of the selected category using feedback provided upon said selection.

19. The computer system of claim 18 wherein

the first providing instructions comprise:

sending instructions configured to automatically send a response to the natural language text, wherein

the response comprises the first data.

20. The computer system of claim 18 wherein

the second providing instructions comprise:

sending instructions configured to send a response to the natural language text, wherein

the response comprises the second data.

21. A computer-readable medium comprising:

analyzing instructions configured to analyze natural language text to identify a set of categories of data associated with the natural language text, wherein

the set of categories are a subset of categories associated with data in a knowledge base,

each category in the knowledge base is associated with a stored text representation of a sample natural language text for the category and a score for the text representation-category combination, and

the score is representative of a relative relevance of the text representation-category combination;

first providing instructions configured to provide first data associated with one category from the knowledge base, when the set of categories of data includes only the one category;

presenting instructions configured to present the set of categories of data associated with the natural language text for selection of a selected category when the set of categories of data includes more than one category;

second providing instructions configured to provide second data associated with the selected category from the knowledge base; and

modifying instructions configured to modify the score associated with the text representation-category combination of the selected category using feedback provided upon said selection.

22. The computer-readable medium of claim 21 wherein

the first providing instructions comprise:

sending instructions configured to automatically send a response to the natural language text, wherein

the response comprises the first data.

23. The computer-readable medium of claim 21 wherein

the second providing instructions comprise:

sending instructions configured to send a response to the natural language text, wherein

the response comprises the second data.