System and method for making search for document in accordance with query of natural language

• US 20060206463A1
• Filed: 03/14/2006
• Published: 09/14/2006
• Est. Priority Date: 03/14/2005
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Solutions Corporation (Toshiba Corporation)
• Inventors: Sasaki, Akemi, Sasaki, Koichi, Takachio, Katsuhiko
• Granted Patent: US 7,765,201 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems

Abstract

A first interface accepts a user specified first question sentence. A question analysis unit analyzes the first question sentence. When the first question sentence queries a plurality of matters, the question analysis unit generates a plurality of second question sentences for individually querying each of the plurality of matters from the first question sentence. A search engine makes searches for documents which match respective matters queried by the plurality of second question sentences from a morphological index database in accordance with the plurality of second question sentences. A second interface provides a user with a search result for the first question having reflected thereon results of document searches for the plurality of second question sentences by the search engine.

Claims

1. A system for making a search for a document in accordance with a query of a natural language, comprising:

a first interface which accepts a user specified first question sentence represented in a natural language;

question analysis means for analyzing the first question sentence accepted by the first interface, the question analysis means generating a plurality of second question sentences for individually querying each of a plurality of matters from the first question sentence when the first question sentence queries the plurality of matters;

a search engine configured to make searches for documents which match respective matters queried by the plurality of second question sentences from a morphological index database by index searches according to the plurality of second question sentences generated by the question analysis means, the morphological index database storing morphological analysis results for a plurality of documents as indexes; and

a second interface which provides a user with a search result for the first question having reflected thereon results of document searches for the plurality of second question sentences by the search engine.

2. The system according to claim 1, further comprising concatenation means for generating a search result document which represents a search result for the first question by concatenating search results for the plurality of second question sentences, results of document searches for the plurality of second question sentences by the search engine being reflected on the search results for the plurality of second question sentences,

wherein the second interface provides a user with a search result document generated by the concatenation means as a search result for the first question.

3. The system according to claim 2, wherein, when a plurality of search results exist with respect to one of the plurality of second question sentences and the plurality of search results include a plurality of search results analogous to each other, the concatenation means handles only one of the analogous search results as a search result for the one second question sentence.

4. The system according to claim 2, further comprising a storage unit which stores tuning information including a concatenation condition relevant to concatenation by the concatenation means,

wherein the concatenation means concatenates search results for the plurality of second question sentences in accordance with the tuning information stored in the storage unit.

5. The system according to claim 4, further comprising abstract generation means for generating an abstract of a document acquired by a document search for each of the plurality of second question sentences by the search engine,

wherein the tuning information specifies which of a document acquired by the document search by the search engine and an abstract of the document generated by the abstract generation means is used as a search result for each of the plurality of second n sentences to be concatenated with each other by the concatenation means, and

the concatenation means selects either one of the document acquired by the document search by the search engine and the abstract of the document generated by the abstract generation means as the search result for each of the plurality of second question sentences to be concatenated with each other in accordance with the tuning information.

6. The system according to claim 4, further comprising a third interface which provides a user with a user interface screen for causing the user to specify the concatenation condition, the third interface storing in the storage unit the tuning information including the concatenation condition specified by the user on the user interface screen.

7. The system according to claim 6, wherein the user interface screen includes an area which causes a user to specify which of the document acquired by the document search by the search engine and the abstract of the document generated by the abstract generation means is used as a search result for each of the plurality of second question sentences to be concatenated with each other by the concatenation means.

8. The system according to claim 6, wherein:

the user interface screen includes an area which causes a user to specify a maximum number of lines of a document which is usable for concatenation by the concatenation means, and

when the number of lines of a document to be concatenated exceeds the maximum number of lines specified by the user on the user interface screen, the concatenation means uses an abstract of the document instead of the document to be concatenated.

9. The system according to claim 6, wherein, when a plurality of search results exist with respect to one of the plurality of second question sentences, the user interface screen includes an area which causes a user to instruct the system whether to concatenate the plurality of search results with each other as a search result for the one second question sentence.

10. The system according to claim 2, wherein the concatenation means sets link information for referring documents acquired by document searches for the plurality of second question sentences by the search engine to a search result document which represents a search result for the first question sentence.

11. A method for making a search for a document in accordance with a query of a natural language, comprising:

accepting a user specified first question sentence represented in a natural language;

analyzing the accepted first question sentence, the analyzing including generating a plurality of second question sentences for individually querying each of a plurality of matters from the first question sentence when the first question sentence queries the plurality of matters;

making searches for documents which match respective matters queried by the plurality of second question sentences from a morphological index database by index searches according to the plurality of second question sentences, the morphological index database storing morphological analysis results for a plurality of documents as indexes; and

providing a user with a search result for the first question having reflected thereon results of document searches for the plurality of second question sentences.

12. The method according to claim 11, further comprising generating a search result document which represents a search result for the first question sentence by concatenating search results for the plurality of the second question sentences, results of document searches for the plurality of second question sentences being reflected on the search results for the plurality of second question sentences,

wherein a user is provided with the generated search result document as a search result for the first question sentence.

13. A computer program product for use in a document search in accordance with a query of a natural language, comprising:

computer-readable program code means for causing a computer to accept a user specified first question sentence represented in a natural language;

computer-readable program code means for causing the computer to analyze for the accepted first question sentence and generation of a plurality of second question sentences for individually querying each of a plurality of matters from the first question sentence when the first question sentence queries the plurality of matters;

computer-readable program code means for causing the computer to search for documents which match respective matters queried by the plurality of second question sentences from a morphological index database by executing index searches in accordance with the plurality of second question sentences, the morphological index database storing morphological analysis results for a plurality of documents as indexes; and

computer-readable program code means for causing the computer to provide a user with a search result for the first question sentence having reflected thereon results of document searches for the plurality of second question sentences.

14. The computer program product according to claim 13, further comprising computer-readable program code means for causing the computer to generate a search result document which represents a search result for the first question by concatenating search results for the plurality of the second question sentences, results of document searches for the plurality of second question sentences being reflected on the search results for the plurality of second question sentences,

wherein a user is provided with the generated search result document as a search result for the first question sentence.