JPH1145255A - Document retrieval device and computer-readable recording medium where program making computer function as same device is recorded - Google Patents

Abstract

PROBLEM TO BE SOLVED: To retrieve necessary information in real time during the editing of a document by retrieving a corresponding subdocument from a storage means according to the vector representation of an inputted retrieval condition. SOLUTION: This device is equipped with clients 100 which output retrieval conditions for retrieving desired descriptions in a document and a retrieval engine which can perform vector space retrieval and Boolean retrieval by generating a dislocation file 102 from a document data base(DB) 101 and further equipped with a retrieval server 103 which inputs the retrieval conditions from the clients 100 and retrieves the corresponding documents by using the dislocation file 102 according to the retrieval condition. Then an arbitrary range of the document displayed on a screen is specified and the structure of the character string within the range is analyzed; and a retrieval condition is generated by using the character string within the specified range and converted into vector representation. Further, the retrieval server 103 retrieves a subdocument according to the vector representation of the inputted retrieval condition.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] The present invention uses a description of a document being edited displayed on a screen as a query, and searches a sub-document in which some of the sentences constituting the document are collected. The present invention relates to a document search apparatus capable of obtaining a description in a directly related document as a search result, and a computer-readable recording medium storing a program for causing a computer to function as the apparatus.

[0002]

2. Description of the Related Art With the development of computers, documents recorded and stored using paper as a medium have been developed.
It has become common to handle it as electronic information,
A large number of electronic documents are to be stored in a database.

[0003] By the way, as a large number of digitized documents are accumulated, a search technology that can easily find a desired document from a large number of documents becomes important. In particular, in today's world where everyone works on a computer, it is possible to construct a search system that allows even a novice computer user to easily search for a desired document without using a special technique. This is an important point.

[0004] One technique for facilitating retrieval includes a technique that enables a human to input a query using a natural language that is usually used. This technology has been adopted in many search systems with the development of natural language processing technology in recent years.

[0005]

However, according to the conventional search system, it is possible to input a query in a natural language, thereby facilitating the input operation.
If you want to search and refer to information related to the document you are editing with a word processor, etc., you need to start the search software separately, enter a query, and perform the search process. There is a problem that the operation is troublesome and lacks convenience.

In the case of performing a search using the vector space method, a document to be searched and a query are converted into a vector expression, a similarity between the document and the query is obtained, and a document exceeding a predetermined threshold is searched. A process of outputting as a search result is performed. Here, if the document to be searched includes multiple topics, each topic is averaged by converting the document to a vector expression. Even when a high topic is included in the document, the similarity between the entire document and the query may be small, and the document may be treated as a document with low relevance to the query. there were.

[0007] Further, since the above-mentioned conventional search system searches for a document corresponding to an input query, it is inconvenient when a sentence or paragraph including a description directly corresponding to the query is desired. there were. In other words, since the document itself can be obtained as a search result, it is necessary to search for a necessary description from the document obtained by the search when it is necessary to cite a description of a certain matter. This is because, in the conventional search system, the entire document is a search target, and it is impossible to search a partial range such as a sentence or a paragraph.

The present invention has been made in view of the above, and has as its object to improve the convenience of search processing by enabling necessary information to be searched in real time while editing a document. I do.

Further, the present invention has been made in view of the above, and when a search is performed using a vector space method,
An object of the present invention is to ensure that a document including a plurality of topics can be searched.

Further, the present invention has been made in view of the above, and a sub-document in which some of sentences constituting a document are collected is to be searched, and a description in a document directly related to a search condition is searched. The purpose of the present invention is to make it possible to support creation of a quotation or a comment.

[0011]

According to a first aspect of the present invention, there is provided a document search apparatus for performing a search process using a vector space method, wherein each sentence constituting a document is an arbitrary number. Storage means for dividing a sentence or a group of sentences for each paragraph, defining the divided group as a sub-document, converting a prepared document into a vector expression in units of the sub-document, and storing the same; Range designating means for designating an arbitrary range of the displayed document; analyzing means for analyzing the structure of the character string in the range designated by the range designating means; and Search condition generating means for generating a search condition using a character string in a specified range, and a vector expression for the search condition generated by the search condition generating means Conversion means for converting, on the basis of the vector representation of the search condition input from said converting means, a search means for searching said sub-document corresponding from said storage means, those provided with.

According to a second aspect of the present invention, in the document search apparatus according to the first aspect, the search means obtains a similarity between a vector expression of the search condition and a vector expression of the sub-document, A sub-document whose obtained similarity exceeds a predetermined threshold is selected, and a list in which the selected sub-documents are arranged according to the similarity is output as a search result.

According to a third aspect of the present invention, there is provided the document search apparatus according to the first or second aspect, further comprising: designation means for designating a method of classifying sentences constituting the document; and the designation means. Generating means for generating the sub-document from the document based on the sentence segmentation method specified via the storage means, wherein the storing means converts the sub-document generated by the generating means into a vector expression. Is stored.

According to a fourth aspect of the present invention, there is provided a document search apparatus according to any one of the first to third aspects.
A selecting unit for selecting a desired sub-document based on a search result by the searching unit; a specifying unit for specifying an arbitrary place of the document displayed on the screen;
Insertion means for inserting the sub-document selected by the selection means at the location specified by the specification means.

According to a fifth aspect of the present invention, there is provided a computer-readable recording medium on which a program for causing a computer to function as each means of the document search apparatus according to any one of the first to fourth aspects is recorded. is there.

[0016]

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram showing an embodiment of a document search apparatus according to the present invention and a computer-readable recording medium storing a program for causing a computer to function as the apparatus. explain.

[First Embodiment] FIG. 1 is a system configuration diagram of a document search apparatus according to a first embodiment. The document search device shown in FIG. 1 includes a plurality of clients 100 that output search conditions for searching for a desired description in a document, a document DB
(Database) A search engine capable of generating the transposed file 102 from the database 101 and performing a vector space search (for example, CLARITECH's CLARI)
T), the search condition is input from the client 100, and the transposed file 102 is
Search server 1 that searches for a description in a corresponding document by using
And a network 104 for connecting the client 100, the search server 103, and the like.

In FIG. 1, a document DB 101 stores a plurality of documents created by the client 100 or the like. The stored documents include word processing documents and SGM.
Any type of document, such as a structured document such as L or HTML, may be used. In the first embodiment, the document DB
Although a part of the document stored in 101 is to be searched,
The search target is not limited to those in the document DB 101.

The transposed file 102 generally has a document DB
101 defines the relationship between a plurality of documents in 101 and a plurality of index words extracted from each of the plurality of documents, and indicates how important a certain index word is in each document. In addition, a corresponding document can be searched using the index word. In the document search apparatus according to the first embodiment, the transposed file 102 is used not for searching a document but for searching a part of a document (subdocument described later).

More specifically, one document is divided into units of an arbitrary number of sentences called sub-documents, and the noun phrase serving as the index word is extracted from the sub-documents. Then, for each of the extracted noun phrases, statistical information such as the appearance frequency in the sub-document and the distribution in the entire document DB 101 is obtained, and each sub-document is converted into a vector expression using the obtained statistical information for each noun phrase. This process is performed for all sub-documents in the document, and stored in the transposition file 102.

Each index word can be weighted according to the degree of importance in the corresponding document. In addition, when performing a search for not only a sub-document but also a document, a vector expression of the document may be generated in advance based on the vector expression of the sub-document, or generated at the time of the search. You can do it.

Client 100 and search server 10
Reference numeral 3 includes a personal computer, a workstation, and the like. FIG. 2 is a schematic block diagram showing the processing of the client 100. Client 100
Specifies an arbitrary range in a document being edited by an application program such as a word processor or spreadsheet software (document displayed on the screen), and specifies a character string in the specified range as a query 200 to start a search. The input device 207 such as a mouse, the query 200 is input, and the input query 200 is subjected to morphological analysis and syntax using a dictionary 202 storing part-of-speech information and a grammar dictionary 203 for analyzing the dependency of each word. It includes a natural language processing module 201 that performs an analysis process such as analysis, generates a search condition 206 including a noun phrase corresponding to the index word of the transposed file 102, and outputs the generated search condition 206 to the search server 103. .

FIG. 3 is a schematic block diagram showing the processing of the search server 103. The search server 103 performs a process of registering a document in the document DB 101 in the transposed file 102 and a search process using a vector space method.

The search server 103 includes a document DB 101
Input the document from, and recognize the format of the document,
Analysis processing such as morphological analysis, syntax analysis, and noun phrase extraction is performed using a dictionary 301 storing part-of-speech information and a grammar dictionary 302 for analyzing the dependency of each word, and the like. Natural language processing module 3 for generating a document set 303 including a list
And a database build component 304 that inputs the document set 303 generated by the natural language processing module 300, converts each subdocument in the input document set 303 into a vector expression, and registers the vector expression in the transposed file 102. , Client 1
Input search condition 206 from 00, and input search condition 2
For each of the noun phrases constituting No. 06, statistical information such as the frequency of appearance in the query 200 and the distribution in the entire document DB 101 is calculated, and the search condition 206 is converted into a vector expression using the obtained statistical information for each noun phrase. A query build component 305 that generates a document 306 and a query document 306 generated by the query build component 305 are input, and the vector of each subdocument in the transposed file 102 is compared with the vector of the query document 306. do it,
A score corresponding to the degree of similarity with the query document 306 is given to each sub-document, a sub-document given a score exceeding a predetermined threshold is selected to generate a sub-document list 308, and the generated sub-document list 308 And a search engine 307 that outputs as a search result.

Although FIG. 1 shows a configuration in which the document DB 101 and the transposed file 102 are independently connected to the network 104, these may be directly connected to the search server 103. In FIG. 1, the document search device according to the first embodiment is connected to a network 104.
However, the configuration is such that the processing of the client 100 shown in FIG. 2 is performed by the natural language processing module 300 of the search server 103 shown in FIG. The document search device according to the first embodiment can be configured by a computer.

Next, the operation of the document search apparatus having the above-described configuration will be described with respect to (1) a process of generating an inverted file,
(2) Sub-document search processing will be described in detail.

(1) Transposition File Generation Process FIG. 4 is a flowchart showing a transposition file generation process. When a new document created by the client 100 or the like is registered in the document DB 101 (S401), the search server 103 starts processing for inputting this document and registering it in the transposition file 102 (S40).
2).

In the search server 103, the natural language processing module 300 performs a process of analyzing the document input in step S402 (S403). Specifically, the input document is a word processing document, a structured document such as HTML, etc.
A process is performed to determine the format of the document. Thereafter, syntax analysis such as morphological analysis and dependency is performed by using the dictionary 301 and the grammar dictionary 302 to divide the document into a plurality of sub-documents, and to perform processing such as extracting a noun phrase from the divided sub-documents.

The sub-documents classified in step S403 are composed of an arbitrary number of sentences.
For example, a plurality of sentences may be set as sub-documents in advance, or sentences in paragraph units may be set as sub-documents. In the first embodiment, since this sub-document is to be searched, how to compose the sub-document, that is, how to divide sentences, can be set / changed according to the user's preference.

Then, the natural language processing module 300
Is based on the result of the processing in step S403.
A noun phrase list is generated for each sub-document, and a document set 303 including the generated noun phrase list is generated (S404).

After that, the database build component 304 performs a process of inputting the document set 303 generated by the natural language processing module 300 and registering it in the transposed file 102 (S405).

Specifically, the document set 303
Transpose file 102 for each noun phrase of subdocument in
The statistical information such as the frequency of occurrence in the sub-document and the distribution in the entire document DB 101 is obtained as an index term, and the sub-document is converted into a vector expression using the obtained statistical information for each noun phrase. This process is performed for all sub-documents in the document set 303 and registered in the transposed file 102.

(2) Sub-document Search Processing Next, sub-document search processing will be described. FIG. 5 is a flowchart showing a sub-document search process. The user specifies an arbitrary range using the input device 207 of the client 100 in a document currently being edited by a word processor or the like (S501), and specifies execution of a search process using the character string in the specified range as the query 200. (S502).

FIG. 6A shows a state in which the range of the query 200 is specified in step S501.
FIG. 6B is an explanatory diagram illustrating a state in which execution of a search process is specified. As shown in FIG. 6A, the user uses the mouse or the like as the input device 207 to
An arbitrary range 601 in 00 is specified. Query 200
The range 601 is, as shown in FIG. 6, a document associated with all documents, an entire page, an embed, an object, a document being edited, a URL, in addition to a unit of paragraph.
And so on. Also, the range 601
Can specify more than one range, not just one. If a plurality of ranges are specified, the specified ranges are treated as one query 200. Further, when specifying the range 601 serving as the query 200, the user can specify a positive weight for the range 601 in which important items desired to be reflected in the search results are described. A range 601 in which unnecessary items that are not desired to be reflected in the search result are described can be designated for performing negative weighting.

Then, as shown in FIG. 6B, the user clicks the right button of the mouse as the input device 207 to open the menu 602 and selects "search" to specify the execution of the search process. I do. Here, FIG.
As shown in (b), the menu 602 is opened to specify the execution of the search processing. However, an icon for specifying the execution of the search processing may be prepared.

Returning to FIG. 5, when execution of the search processing is designated in step S502, the natural language processing module 201
Inputs the character string in the designated range 601 as the query 200, and analyzes the input query 200 (S503). Specifically, syntax analysis processing such as morphological analysis and dependency is performed using the dictionary 202 and the grammar dictionary 203.

The natural language processing module 201 executes the query 20 based on the analysis result in step S503.
A search condition is generated from 0 (S504). That is, the natural language module 201 extracts a noun phrase corresponding to the index word in the transposed file 102 from the character string in the designated range 601 and generates a search condition 206 including the noun phrase.

As described above, the search condition 206 is generated from the query 200, and the generated search condition 206
Is output from the client 100 to the search server 103. Further, as described above, when a weight is specified for the selected range 601, the weight specification information is also output to the search server 103.

Thereafter, the query build component 305 of the search server 103 inputs the search condition 206 from the client 100, and for each noun phrase constituting the input search condition 206, the appearance frequency in the query 200, the entire document DB 101 Is obtained, and a query document 306 is generated by converting the search condition 206 into a vector expression using the obtained statistical information (S505). When the weighting is specified, the query document 306 is generated by adding a positive weight or a negative weight to the corresponding noun phrase.

The search engine 307 inputs the query document 306 generated by the query build component 305, compares the vector of the sub-document in the transposed file 102 with the vector of the query document 306, and 306
The sub-document list 308 is generated by assigning a score according to the degree of similarity to each sub-document, selecting a sub-document to which a score exceeding a predetermined threshold is given (S506).

The score according to the degree of similarity expresses the degree of similarity between each sub-document and the query document 306 based on the cosine distance.
It is similar to 06. Then, a score threshold is set in the search engine 307 in advance, and a sub-document given a score exceeding this threshold is set as a search result.

After that, the search engine 307 outputs the generated sub-document list 308 to the client 100 as a search result, and the sub-document list 3
08 is displayed on the screen of the client 100 (S50).
7).

FIG. 7 is an explanatory diagram showing an example of the sub-document list 308. Sub-document list 30
8 shows a ranking of scores according to the degree of similarity to the query document 306, a subdocument ID for specifying which subdocument in the document, and a document name of the document including the subdocument.

The user of the client 100 can display a sub-document of a document in the document DB 101 on the screen by selecting an arbitrary sub-document from the sub-document list 308 displayed on the screen.

The document search apparatus according to the first embodiment selects one document in advance (the document may be searched as a search target), searches a sub-document of the selected document, and searches for a desired document in the document. Can also be used to find the description.

The document ranking can be generated by using the sub-document list 308 shown in FIG. As a result, even when there are a plurality of documents including a plurality of topics, it is possible to create a ranking of documents related to a specific topic, and to easily obtain a document including a specific description.

Further, the sub-document list 30 which is a search result obtained by the document search apparatus according to the first embodiment described above.
In step 8, the results of the sub-documents that the user considers appropriate or unsuitable as the search results can be fed back to the search server 103. That is, the user can specify a positive weight, for example, “+” for a sub-document that is deemed appropriate as a search result, and a negative weight, for example, “A” for a sub-document deemed inappropriate as a search result. -"Can be specified. As a result, if the input weight is a positive specification, the weight of the corresponding sub-document in the transposed file 102 is strengthened, and if the input weight is a negative specification, the weight of the sub-document is weakened. Can be

As described above, according to the document search apparatus of the first embodiment, the search target is not the entire document but the sub-document of the document, and the description in the document directly related to the search condition can be obtained as the search result. Since it is possible to search for necessary information in real time while editing a document, it is possible to improve the convenience of search processing.
Therefore, quotes, annotations, and the like related to descriptions in the document can be obtained by searching. Further, since it is not necessary to search for a necessary part in the document, it is possible to improve work efficiency. Further, when performing a search using the vector space method, it is possible to reliably search not only a topic having a high relevance to a search condition but also a document including a plurality of other topics.

[Second Embodiment] Next, a document search apparatus according to a second embodiment will be described. The document search device according to the second embodiment uses the document search device according to the first embodiment to support creation of a quote or an annotation. In addition,
The configuration of the document search device and the process of generating the transposed file 102 are the same as those in the first embodiment, and thus description thereof is omitted here.

FIG. 8 is a flowchart showing a process of creating a quote or an annotation by using a search of a sub-document. Steps similar to those in FIG. 5 are denoted by the same step numbers and detailed description is omitted. .

The user uses the input device 207 of the client 100 to select an arbitrary range 6 in which a quote or an annotation is required in the document 600 currently being edited by a word processor or the like.
01 (S801: see FIG. 6A). For the specified range 601, word units, sentence units,
It can be specified according to the user's preference, such as paragraph units.

Then, the specified range 601 is added to the query 2
When the execution of the search process is set to 00 (S50)
2), a query 200 analysis process (S503), a search condition 206 generation process (S504), a query document 306 generation process (S505), and a subdocument search process by the query document 306 (S506) are performed. The sub-document list 308 as a search result is displayed on the screen of the client 100 (S507).

Each sub-document in the sub-document list 308 displayed on the screen in step S507 is a candidate for a quote or an annotation. After confirming the content of the sub-document as necessary, the user of the client 100 selects a desired sub-document from the sub-document list 308 and specifies a position where the sub-document is to be inserted into the document 600 being edited. (S802).

When the sub-document is selected and the insertion position is specified in step S802, a process of inserting the selected sub-document into the specified insertion position is performed (S803). Thereafter, the user can perform processing such as processing the inserted sub-document as necessary.

In step S802, a menu for designating how to use the searched sub-document may be displayed. Specifically, as a method of using sub-documents,
Ability to specify quotes, headnotes, footnotes, etc. using menus and icons. If a quote is selected, the sub-document is inserted as a quote after the range 601 specified in step S801. When a headnote or footnote is selected, a process is performed such that a subdocument is inserted as a comment at a predetermined location, and a number or the like that associates the designated range 601 with the comment is attached to both. To

In the second embodiment, the description has been given of the support for creating a quotation or an annotation. For example, when a description of a word or a matter is described, the sub-document is used as a query 200 using the word or the matter. You can also search and use the searched sub-documents as their descriptive text.

As described above, according to the document search apparatus of the second embodiment, the search target is a sub-document of the document, and the description in the document directly related to the search condition can be obtained as the search result. Search results can be used as quotes and annotations. Also, an arbitrary range 601 of the document being edited displayed on the screen is searched for by the query 20.
Since it can be set to 0 and the execution of the search can be designated on the spot, a sub-document that can be a quote or an annotation can be searched in real time during editing.

The document search device described in the first and second embodiments is realized by executing a prepared program on a computer or a workstation. This program is recorded on a computer-readable recording medium such as a hard disk, a floppy disk, a CD-ROM, an MO, and a DVD, and is executed by being read from the recording medium by the computer. This program can be distributed via the recording medium or via a network.

[0059]

As described above, according to the document retrieval apparatus of the present invention (claim 1), each sentence constituting a document is divided into a group consisting of an arbitrary number of sentences or sentences for each paragraph. Storage means for defining a divided group as a sub-document, converting a prepared document into a vector representation in units of sub-documents, and storing the document, and a range specifying means for specifying an arbitrary range of the document displayed on the screen Analysis means for analyzing the structure of a character string in a range specified by the range specification means; and search condition generation for generating a search condition using the character string in the specified range based on an analysis result by the analysis means. Means, a conversion means for converting the search condition generated by the search condition generation means into a vector expression, and a conversion method based on the vector expression of the search condition input from the conversion means. Since having a search means for searching said sub-document corresponding from said storage means,
Necessary information can be searched in real time while editing the document, and the convenience of the search process can be improved. Also, because you do n’t have to find the right place in the document,
Work efficiency can be improved. Further, when performing a search using the vector space method, it is possible to reliably search not only a topic having a high relevance to a search condition but also a document including a plurality of other topics.

Further, the document search device of the present invention (Claim 2)
According to the document search apparatus according to claim 1, the search means obtains a similarity between the vector expression of the search condition and the vector expression of the sub-document, and determines the sub-similarity exceeding the predetermined threshold. Since a document is selected and a list in which the selected sub-documents are arranged according to the similarity is output as a search result, a desired sub-document can be easily selected.

Further, the document search device of the present invention (claim 3)
3. The document retrieval apparatus according to claim 1, further comprising: designation means for designating a method of dividing sentences constituting the document, and a method of dividing the sentence designated via the designation means. Generating the sub-document from the document based on the document, wherein the storing means converts the sub-document generated by the generating means into a vector expression and stores the vector. Sub-documents can be searched.

A document search device according to the present invention (claim 4)
According to this, in the document search device according to any one of claims 1 to 3, further, a selection unit for selecting a desired sub-document based on a search result by the search unit is displayed on a screen. The search result is used as a citation or an annotation because it has a designating means for designating an arbitrary place of the document and an inserting means for inserting the sub-document selected by the selecting means at the place designated by the designating means. Can be. In addition, since any range of the document being edited displayed on the screen can be specified as a query and execution of the search can be specified on the spot, sub-documents that can be quoted or commentary in real time during editing can be specified. Can be obtained by searching.

Further, according to a computer-readable recording medium of the present invention (claim 5), a program for causing a computer to function as each means of the document search device according to any one of claims 1 to 4 Was recorded,
By executing this program on a computer, it is possible to search for necessary information in real time while editing a document, to search for a necessary portion in the document, and further, to edit a document including a plurality of topics. A document search device capable of reliably searching for a document can also be realized.

[Brief description of the drawings]

FIG. 1 is a system configuration diagram of a document search device according to a first embodiment.

FIG. 2 is a schematic block diagram illustrating processing of a client illustrated in FIG. 1;

FIG. 3 is a schematic block diagram illustrating processing of a search server illustrated in FIG. 1;

FIG. 4 is a flowchart illustrating a process of generating an inverted file in the document search device according to the first embodiment;

FIG. 5 is a flowchart showing a sub-document search process in the document search device according to the first embodiment.

FIG. 6 is a diagram illustrating the information retrieval apparatus according to the first embodiment;
Shows the state of specifying the range to be a query, (b)
FIG. 8 is an explanatory diagram illustrating a state in which execution of a search process is specified;

FIG. 7 is an explanatory diagram showing an example of a sub-document list in the document search device according to the first embodiment.

FIG. 8 is a flowchart showing a process of creating a quote or an annotation using a search of a sub-document in the document search device according to the second embodiment.

[Explanation of symbols]

 Reference Signs List 100 client 101 document DB 102 transposed file 103 search server 104 network 200 query 201, 300 natural language processing module 202, 301 dictionary 203, 302 grammar dictionary 206 search condition 207 input device 303 document set 304 database build component 305 query / query Build component 306 Query document 307 Search engine 308 Sub-document list 600 Document 601 Range (query) 602 Menu

Claims (5)

[Claims] 1. A document search apparatus for performing search processing using a vector space method, wherein each sentence constituting a document is divided into a group consisting of an arbitrary number of sentences or sentences for each paragraph, and the divided groups are divided into groups. A storage unit that defines a sub-document, converts a prepared document into a vector expression in units of the sub-document, and stores the converted document; a range specification unit that specifies an arbitrary range of the document displayed on the screen; Analyzing means for analyzing the structure of the character string in the range specified by the means, and search condition generating means for generating a search condition using the character string in the specified range, based on the analysis result by the analyzing means, Conversion means for converting the search condition generated by the search condition generation means into a vector expression; And a search means for searching the storage means for the corresponding sub-document based on a document expression. 2. The search means calculates a similarity between the vector expression of the search condition and the vector expression of the sub-document, selects a sub-document whose calculated similarity exceeds a predetermined threshold, and selects the selected sub-document. 2. The document search apparatus according to claim 1, wherein a list in which are arranged according to the similarity is output as a search result. 3. A designation means for designating a method of classifying sentences constituting the document, and the sub-document from the document based on the sentence classification method designated via the designating means. 3. The document search device according to claim 1, further comprising: a generation unit configured to generate the document, wherein the storage unit converts the subdocument generated by the generation unit into a vector expression and stores the vector expression. 4. 4. A selecting unit for selecting a desired sub-document based on a search result by the searching unit; a specifying unit for specifying an arbitrary place of the document displayed on the screen; The document search apparatus according to any one of claims 1 to 3, further comprising: an insertion unit that inserts a sub-document selected by the selection unit into a designated location. 5. A computer-readable recording medium on which a program for causing a computer to function as each unit of the document search device according to claim 1 is recorded.