JPH1145252A - Information retrieval device and computer readable recording medium for recording program for having computer function as the same device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To attain improvement of convenience of a retrieval processing by making it possible to retrieve necessary information in real time during edition of a document. SOLUTION: The device is equipped with a client 100 for specifying an arbitrary range of a document prepared in advance, analyzing a structure of a character string within the specified range, generating a retrieval condition by using the character string within the specified range and outputting it and a retrieval server 103 for inputting the retrieval condition from the client 100, performing a retrieval processing by using a transposition file 102 and retrieving a document concerned in a document DB101.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information retrieval apparatus capable of retrieving necessary information in real time while editing a document, and to improve the convenience of retrieval processing, and to function a computer as the apparatus. The present invention relates to a computer-readable recording medium that stores a program for causing a computer to execute the program.

[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] As one technique for facilitating retrieval, a query (Quu) using a natural language usually used by humans is used.
ery) can be input. 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.

[0006] The present invention has been made in view of the above, and an object of the present invention is to make it possible to search for necessary information in real time while editing a document, thereby improving the convenience of search processing. .

[0007]

According to a first aspect of the present invention, there is provided an information retrieving apparatus for performing a retrieving process for retrieving information based on a retrieval condition for retrieving arbitrary information. In the information search device provided with, a range specifying means for specifying an arbitrary range of the document displayed on the screen, an analyzing means for analyzing a structure of a character string in the range specified by the range specifying means, A search condition generating unit that generates the search condition using the character string in the specified range based on the analysis result, wherein the search unit inputs the search condition generated by the search condition generating unit. Then, the search process is executed.

According to a second aspect of the present invention, in the information search apparatus according to the first aspect, the range designating means can designate a plurality of ranges of the document.

According to a third aspect of the present invention, there is provided the information retrieval apparatus according to the second aspect, further comprising a weight specifying means for specifying a positive or negative weight for the plurality of ranges. is there.

According to a fourth aspect of the present invention, there is provided an information retrieval apparatus as set forth in any one of the first to third aspects.
Further, the search result by the search means is input, arbitrary information is selected from the input search result, and weight specifying means for specifying a positive weight or a negative weight for the selected information, Weighting means for weighting the corresponding information with a positive weight or a negative weight based on the designation of the weight inputted through the interface.

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 information retrieval apparatus according to any one of the first to fourth aspects is recorded. is there.

[0012]

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram showing an embodiment of an information retrieval 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 an information retrieval apparatus according to a first embodiment. The information search device shown in FIG. 1 generates a transposed file 102 from a plurality of clients 100 that output search conditions for searching for a desired document, a document DB (database) 101, and performs a vector space search. A search engine 103 (e.g., CLARIT of CLARITECH) capable of inputting search conditions from the client 100 and searching for a corresponding document using the transposed file 102 based on the input search conditions; A network 104 connects the client 100, the search server 103, and the like.

Referring to FIG. 1, a document DB 101 stores a plurality of documents (information) created by the client 100 or the like.
Any type of document, such as a structured document such as SGML or HTML, may be used. In the first embodiment, the document in the document DB 101 is set as a search target. However, the search target is not limited to the document in the document DB 101.

The transposed file 102 defines the relationship between a plurality of documents in the document DB 101 and a plurality of index terms extracted from each of the plurality of documents by a method described later. An important vocabulary is indicated using a vector expression, and a corresponding document can be searched using the index word.

More specifically, one document is divided into sub-documents consisting of a plurality of sentences in advance, and the noun phrases serving as the index words are extracted from the sub-documents. Statistical information such as an appearance frequency and 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. Then, a vector expression of the document is generated based on the vector expression of the converted sub-document. The transposition file 102 stores the document in the document DB 101 thus vectorized.

Each index word can be weighted according to the degree of importance in the corresponding document. Also, the vector expression of the document may be generated based on the vector expression of the sub-document when performing an actual search.

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
Is an input device 207 such as a mouse that designates an arbitrary range in a document being edited by an application program such as a word processor or spreadsheet software, and designates the start of a search as a query 200 using a character string in the designated range.
And the query 200, and the entered query 200
Of the transposed file 102 using the dictionary 202 storing part-of-speech information and the grammar dictionary 203 for analyzing the dependency of each word. The system includes a natural language processing module 201 that generates a search condition 206 including a noun phrase 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 search.

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
00, the document set 303 generated by the natural language processing module 300 is input, each sub-document in the input document set 303 is converted into a vector expression, and the vector of the document is converted based on the vector expression of the sub-document. A database build component 304 for generating an expression and registering it in the transposed file 102;
Is input, and for each of the noun phrases constituting the input search condition 206, the appearance frequency in the query 200, the document DB 10
1 and a query build component 305 for generating a query document 306 in which the search condition 206 is converted into a vector expression using the obtained statistical information, and a query build component 305 Query Document 3
06, the vector of each document in the transposed file 102 is compared with the vector of the query document 306, a score corresponding to the degree of similarity with the query document 306 is given to each document, and a predetermined threshold is set. And a search engine 307 that outputs, as a search result, a document list 308 to which a score exceeding the score is given.

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 information retrieval apparatus 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 information search device according to the first embodiment can be configured by a computer.

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

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 receives the document set 303 generated by the natural language processing module 300, generates a vector representation of the document, and registers it in the transposed file 102 (S405).

More 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 processing is performed for all the sub-documents in the document set 303, and based on the converted sub-document vector expression, a vector expression of the document is generated and registered in the transposed file 102.

(2) Document Search Process Next, the document search process will be described. FIG. 5 is a flowchart showing the document search process. The user specifies an arbitrary range using the input device 207 of the client 100 in the document currently being edited by a word processor or the like (S501), and queries the character string in the specified range for the query 20.
The execution of the search process to be set to 0 is specified (S502).

FIG. 6A shows a state in which a range to be a 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 queries 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.

After that, 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 each document in the transposed file 102 with the vector of the query document 306, and A score corresponding to the degree of similarity is given to each document (S506).

The score according to the similarity is obtained by expressing the similarity between each document and the query document 306 based on the cosine distance. A document having a higher score is more similar to the query document 306. It represents that it is. Also, the weight specified by the user is
It is used in this search processing and is reflected in the score value.

The search engine 307 selects a document to which a score exceeding the threshold is assigned based on a preset score threshold, and generates a document list 308 based on the selected document to perform search. The result is output (S507). Note that the document list 308 is arranged in order from the document having the highest similarity to the query document 306, that is, the score.

Thereafter, the document list 308 output from the search engine 307 is displayed on the screen of the client 100. By selecting an arbitrary document from the document list 308 displayed on the screen, the user of the client 100 can display the corresponding document in the document DB 101 on the screen. Then, the user can copy necessary descriptions from this document to the document being edited.
Therefore, when it is desired to insert a quotation or a comment in a document being edited, the information search device of the first embodiment can be conveniently used.

When the client 100 inputs the document list 308, the client 100 can activate the application program and display the documents listed in the document list 308 on the screen. That is, the client 100
Selects an application program (application program used when creating the corresponding document) in the document list 308 that is compatible with the format of the document, and displays the relevant document on the screen using the selected application program.

FIG. 7 is an explanatory diagram showing a state in which the retrieved document is displayed by activating the application program. 7, reference numeral 700 denotes a floating button. The floating button 700 includes a next document button 701 for displaying a next document, a previous document button 702 for displaying a previous document, and execution of the above-described search processing. Is provided with a search execution button 703 for designating.

Since the document list 308 output from the search engine 103 is arranged in order from the document most similar to the character string in the range specified by the user as the query 200, when the next document button 701 is clicked with a mouse or the like. Thus, a document having the second highest similarity to the currently displayed document can be displayed. On the other hand, if the previous document button 702 is clicked with a mouse or the like, a document having a higher similarity than the currently displayed document can be displayed.

The floating button 7 shown in FIG.
By specifying an arbitrary range in the document with “00” displayed and clicking the search execution button 703, the above-described search processing and the display processing of the document by the application program are automatically executed.

As described above, according to the information search apparatus of the first embodiment, an arbitrary range 601 of the document being edited is selected,
Since the search process can be performed using the selected range 601 as the query 200, the trouble of starting the search software and newly inputting the query 200 can be omitted, and the convenience of the search process can be improved. . Further, when it is desired to search for and refer to a matter related to the document being edited, a reference document can be easily obtained simply by specifying a corresponding range in the document and specifying execution of a search process. Further, since the document displayed on the screen can be directly used as the query 200, the search operation can be performed intuitively and easily.

The result of the search as described with reference to FIG. 5 can be used as a further search target, and an arbitrary range in the document 600 can be specified to narrow down the search result.

Further, the search process can be performed while increasing the range 601 serving as the query 200 while dragging the document 600 with a mouse or the like. That is, the query 200 may be changed while referring to the search result, and the search result for the changed query 200 may be obtained in real time.

Further, in the first embodiment, the search by the vector space method has been described as an example. However, by using the result of analyzing the query 200 to express the search condition 206 by AND or OR, the Boolean search can also be performed. It can be carried out.

[Second Embodiment] In the document list 308 which is a search result obtained by the information search apparatus of the first embodiment described above, for a document which the user considers appropriate or unsuitable as the search result, The result can be fed back to the search server 103. This process is defined as relevance feedback.

FIG. 8 is an explanatory diagram for explaining the relevance feedback. FIG. 8 shows the client 100 and the search server 103 shown in FIGS. 2 and 3, respectively.
Are collectively shown in one figure.

As described in the first embodiment, the result of performing search processing by search engine 307 in response to query 200 as a search request from a user is document list 308.
Is output in the form The user selects an arbitrary document from the document list 308 as an evaluation of the search result, and inputs an instruction for giving a positive weight or a negative weight to the selected document via the input device 207.

That is, the user can specify a positive weight, for example, “+” for a document that is considered to be appropriate as a search result, and a negative weight, for example, for a document that is not appropriate for the search result. "-" Can be specified.

The weight specified by the user is input to the database build component 304 via the input device 207. The database build component 304 strengthens the weight of the corresponding document in the transposed file 102 when the input weight is a positive specification, and increases the weight of the document when the input weight is a negative specification. A process for weakening the weight is performed.

Based on the user's evaluation, the transposed file 1
The result of changing the weight of the document in 02 is reflected in the search processing from the next time. In this way, by performing the suitability feedback process of feeding back the evaluation of the user's search result, the evaluation of the user's search result can be reflected in the next search process, and the search process is repeated. Each time, more appropriate search results can be obtained.

The relevance feedback processing described in the second embodiment is not limited to the information search apparatus described in the first embodiment, that is, the information search apparatus in which a specified range in a document is used as a query 200. Needless to say, the present invention is also applicable to an information search device of a type in which a user directly inputs 200.

Further, the information retrieval apparatus 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.

[0055]

As described above, according to the information retrieval apparatus of the present invention (claim 1), a range designating means for designating an arbitrary range of a document prepared in advance, and a range designated by the range designating means. Analyzing means for analyzing the structure of the character string of the character string, and search condition generating means for generating a search condition using a character string in a specified range based on the analysis result by the analyzing means. In order to input the search condition generated by the condition generating means and execute the search processing, an arbitrary range of the document being edited by a word processor or the like can be designated, and the search processing can be executed using the specified range as a query.
Therefore, since information related to the document being edited can be searched in real time, the convenience of the search process can be improved.

Further, the information retrieval apparatus of the present invention (Claim 2)
According to the information retrieval apparatus of the first aspect, the range specifying means can specify a plurality of ranges of the document, so that the user can perform the search process under desired conditions.

An information retrieval apparatus according to the present invention (claim 3)
According to the information retrieval apparatus according to the second aspect, since the information retrieval apparatus further includes a weight specifying unit that specifies a positive or negative weight for a plurality of ranges, a search result desired by a user can be easily obtained. it can.

Further, the information retrieval apparatus of the present invention (Claim 4)
According to the information search device according to any one of claims 1 to 3, further, a search result by the search means is input, and arbitrary information is selected from the input search result.
Weighting means for designating a positive weight or a negative weight for the selected information, and performing a positive weighting or a negative weighting on the corresponding information based on the designation of the weight inputted through the weighting means. Weighting means, the evaluation of the user's search result can be reflected in the search processing from the next time, and a more appropriate search result can be obtained every time the search processing is repeated. .

Furthermore, 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 information search device according to any one of claims 1 to 4 Was recorded,
By causing a computer to execute the recorded program, it is possible to obtain an information retrieval apparatus capable of designating an arbitrary range of a document being edited by a word processor or the like and executing a search process using the designated range as a query.
Therefore, it is possible to improve the convenience of the search processing when searching for information related to the document being edited.

[Brief description of the drawings]

FIG. 1 is a system configuration diagram of an information 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 information search device according to the first embodiment;

FIG. 5 is a flowchart showing a document search process in the information search device of 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 a state in which a searched document is displayed by activating an application program in the information search device according to the first embodiment;

FIG. 8 is an explanatory diagram illustrating relevance feedback in the information 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 Document list 600 Document 601 Range 602 Menu 700 Floating button 701 Next document button 702 Previous document button 703 Search execution button

Claims (5)

[Claims] 1. An information search apparatus having a search means for performing search processing of corresponding information based on a search condition for searching for any information, an arbitrary range of a document displayed on a screen is designated. Range specifying means; analyzing means for analyzing the structure of the character string in the range specified by the range specifying means; and the search condition using the character string in the specified range based on the analysis result by the analyzing means. And a search condition generating means for generating the search condition, wherein the search means inputs the search condition generated by the search condition generating means and executes the search processing. 2. The information retrieval apparatus according to claim 1, wherein said range designating means is capable of designating a plurality of ranges of said document. 3. The information retrieval apparatus according to claim 2, further comprising a weight specifying unit for specifying a positive or negative weight for the plurality of ranges. 4. A weight specifying means for inputting a search result by the search means, selecting arbitrary information from the input search result, and specifying a positive weight or a negative weight for the selected information; 4. Weighting means for weighting the corresponding information with a positive weight or a negative weight based on the weight designation input through the weight designation means. The information retrieval device described in (1). 5. A computer-readable recording medium having recorded thereon a program for causing a computer to function as each unit of the information search device according to any one of claims 1 to 4.