Natural language database querying

• US 20050050042A1
• Filed: 08/20/2004
• Published: 03/03/2005
• Est. Priority Date: 08/20/2003
• Status: Abandoned Application

• Current Assignee: Marvin Elder
• Original Assignee: Marvin Elder
• Inventors: Elder, Marvin
• Application Number:
  US10/923,394
• Publication Number:
  US 20050050042A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries

Abstract

The invention teaches preparing data sources for a natural language query. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. 37 CFR 1.72(b).

Claims

1. A method, comprising, sequentially:

receiving a natural language request, the natural language request being convertible to text comprising at least one phrase, where the phrase comprises at least one word;

interpreting the request by classifying each word or phrase according to a rules set based on language rules that identify the parts of speech;

generating an executable database query based on the classified word or phrase; and

sending the database query to a data source.

2. The method of claim 1 further comprising extracting a result set from the data source.

3. The method of claim 2 further comprising formatting the answer to the database query for user presentation.

4. The method of claim 3 further comprising delivering an answer to the database query.

5. The method of claim 3 wherein formatting places the answer that comprises data in a table format.

6. The method of claim 3 wherein formatting places the answer that comprises data in a natural language format.

7. The method of claim 1 wherein the natural language request is made in English.

8. The method of claim 1 wherein the database query is an SQL database query.

9. The method of claim 1 wherein the natural language request does not impose a strict syntax structure on the user

10. The method of claim 1 wherein the natural language request does not impose a strict word definition requirement on the user.

11. The method of claim 1 wherein interpreting the request comprises parsing the text by referencing a Semantic Phrase Repository.

12. The method of claim 11 further comprising locating noun phrases in a Conceptual Object Repository.

13. The method of claim 12 further comprising generating a clarification dialog if the database query fails to match all of the phrases in the request with references either in a Semantic Phrase Repository or in a Conceptual Object Repository.

14. The method of claim 13 further comprising allowing the user to add references in a Semantic Phrase Repository or in a Conceptual Object Repository to produce an accurate interpretation of the request.

15. The method of claim 1 wherein the natural language request is received as audible speech, and then converting speech to text prior to interpreting the request.

16. The method of claim 15 further comprising assisting a speech to text conversion application in disambiguating speech objects by providing a reference in a Semantic Phrase Repository or in a Conceptual Object Repository.

17. A machine-readable memory storage device that enables a user to perform natural language database searches, by sequentially:

receiving a natural language request, the natural language request being convertible to text comprising at least one phrase, where the phrase comprises at least one word;

interpreting the request by classifying each word or phrase according to a rules set based on language rules that identify the parts of speech;

generating an executable database query based on the classified word or phrase;

sending the database query to a data source, and

extracting a result set from the data source.

18. A specific computing device that enables a user to perform natural language database searches, by sequentially:

receiving a natural language request, the natural language request being convertible to text comprising at least one phrase, where the phrase comprises at least one word;

interpreting the request by classifying each word or phrase according to a rules set based on language rules that identify the parts of speech;

generating an executable database query based on the classified word or phrase;

sending the database query to a data source, and

formatting the answer to the database query for user presentation.