JPH03131971A - document search device - Google Patents

Abstract

PURPOSE:To shorten the time required for retrieval by setting up document accuracy to '0' when the calculated result of sub-document probability for a certain sub-retrieval condition expression becomes '0'. CONSTITUTION:Document accuracy indicating relation between the keyword group of respective documents in a document information data base 7 and a keyword in a retrieval condition expression specified by a user is calculated by a document probability calculating part 12. The document accuracy of the sub-retrieval condition expression is calculated at first, and then the product of the sub-document accuracy results of all sub-retrieval condition expressions is found out as document accuracy. When a certain sub-document accuracy is '0' even if the other sub-document accuracy has a value other than '0', the final document accuracy becomes '0' without fail. When the sub-document accuracy of a certain sub-retrieval condition expression is '0' in the case of finding out the document accuracy of a certain document, the document accuracy consisting of the product of sub-document accuracy results can be set up to '0' without calculating the residual sub-document accuracy in the document concerned.

Description

DETAILED DESCRIPTION OF THE INVENTION Field of Industrial Application The present invention relates to a document retrieval device, and particularly to a document retrieval device, which can generate a group of keywords that are close to the sense of the user during a search, and furthermore, the closer the search results are to the user's search request, the more the search results are searchable. The present invention relates to a flexible and high-speed document retrieval device that can be ordered by evaluation values having large values.

2. Description of the Related Art In conventional document retrieval devices, when registering a document, a registration operator has to select keywords deemed appropriate, classify them appropriately using a thesaurus, and update the thesaurus as keywords are added or deleted, which is quite a complicated task. Furthermore, in order to search for documents that generally satisfy the search conditions specified by the user during a search, it is necessary to reconsider the search conditions and perform the search again.

In order to solve these problems, we use keyword connections, which are related information between keywords, and introduce an evaluation value called document accuracy, which has a larger value when searching for documents, as the closer it is to the user's search request. A document retrieval device that allows a user to flexibly search for documents that meet their requirements has been proposed by the present applicant in Japanese Patent Application No. 8291/1983. Furthermore, a system with a learning function that changes the weight of each keyword connection based on the user's judgment and instructions and reflects that judgment in the search results at the next search was proposed in Japanese Patent Application No. 197988. ing. Furthermore, we have improved the document accuracy so that it can be calculated for search expressions in which multiple keywords are combined using any combination of AND, logical OR, and negation operators as document search conditions for users. Devices with a learning function have also been proposed.

Problems to be Solved by the Invention However, in the content of proposals using such keyword connections, the amount of calculation for document accuracy is relatively large, so it takes a long processing time.

Means for Solving the Problems Keyword extraction means for extracting keywords from the registered document when registering a registered document and its bibliographic information in a document database; and an inverter that indicates the relationship between the registered document and the keyword. an inverted file management means for creating and changing a keyword file; and a keyword connection table management means for creating and changing a keyword connection table that describes related information between the keywords; The document accuracy is defined as a value indicating the strength of the relationship between the keywords included in the expression and the keyword group of the registered documents in each file, and the document accuracy is calculated using the keyword connection table, the inverted file, and a predetermined method. a document accuracy calculation means for calculating;
A document sorting/display management means that outputs search result documents in the order of the calculated document accuracy, and a user who interactively determines whether the document accuracy given to each document in the search results is appropriate. A document selection means is provided which has a learning management means for changing the weight of a keyword connection according to a predetermined method when instructed to select a document that matches the search condition expression, and a document selection means for selecting a document that matches the search condition expression, When any of the calculation results of the sub-document probabilities defined by the document probabilities for the combined sub-search condition expressions becomes O, the calculation of the remaining sub-document probabilities for the fully open search condition expressions is stopped and the document certainty is set to O. I decided to do so.

When calculating the working document certainty, it is necessary to calculate the subdocument certainty for all documents as many times as there are subsearch condition expressions.
When the accuracy of a certain subdocument is O, even if the accuracy of other subdocuments is not O, the final document accuracy is always O. Therefore, when calculating the document accuracy, the document accuracy can be set to O when the calculation result of the sub-document accuracy for a certain sub-search condition expression becomes O, and there is no need to calculate the remaining sub-document accuracy for that document. It can speed up the calculation of document accuracy. As a result, the time required for a search is shortened, and the search can be performed efficiently.

Example An embodiment of the present invention will be described based on the drawings.

First, the document retrieval device of the present invention is premised on the use of the concept of keyword connection, similar to the previously proposed method described above. In addition, we have introduced the concept of evaluation value called document accuracy, which has a larger value for each document as it is closer to the user's search request, and when searching for a document, the user can search for documents that satisfy the user's request based on the degree of document accuracy. This allows for flexible selection. A keyword connection is a description of a relationship between keywords.

Specifically, in the keyword connection of this embodiment, the magnitude of the relationship is in the range from O to 1, where O indicates that there is no relationship between the keywords, and a value of 0 or more indicates that there is a relationship, and in particular, l indicates the magnitude of the relationship. is the maximum.

Related information between the i-th keyword and the third keyword (hereinafter referred to as "weight") can be expressed in WIJ.

Under such a premise, the document retrieval device of the present invention
It is configured as shown in the figure. First, when the keyword extraction unit 1 inputs the registered document 2, it extracts keywords from the document, and the keywords and the registered document 2 are sent to the document information management unit 3,
It is output to the keyword connection table management section 4 and the inverted file management section 5. The document information management unit 3 stores keywords and bibliographic information 6 in a file 7, and converts the information into a database in a form that can be used at the time of searching. The keyword connection table management unit 4 creates a keyword connection table that describes related information between keywords and stores it in a file 8. Furthermore, if there is a request from the learning management section 9, the weight of the keyword connection is changed. The inverted file management section 5 creates an inverted file indicating the relationship between keywords and registered documents, and stores it in file IO.

The document selection section 11 includes the learning management section 9 and the document accuracy calculation section 1.
2, a request processing section 13, a document sorting section 14, and a display management section 15. First, the document accuracy calculation unit 12 uses the necessary information in the keyword connection table stored in the file 8 to calculate the document accuracy for each document based on the search condition expression consisting of keywords transferred from the request processing unit 13. Calculate. This calculation method will be described later. Document sorting section 1
4 sorts all documents stored in the file 7 in descending order of document accuracy calculated by the document accuracy calculation unit 12 and transfers the sorted documents to the display management unit 15. The request processing unit 13 transfers the search condition expression input by the user from the keyboard 16 to the document certainty calculation unit 12.

Further, when displaying search results on the display 17, a display instruction input by the user is transferred to the display management section 15.

Furthermore, if there is an instruction from the user, information regarding learning of keyword connections is transferred to the learning management section 9. The learning management unit 9 performs keyword connection learning according to the user's instructions given from the request processing unit 13. That is, the learning management section 9 calculates the amount of change in each weight of the keyword connection, but the actual change in the weight value is performed by giving an instruction to the keyword/connection table management section 4. The learning method will be described later. The display management section 15 displays the search results on the display 17 according to the user's instructions given from the request processing section 13.

The purpose of the document search process is to search and display appropriate documents according to the user's request, and document selection processing for this purpose is performed by the document selection unit 11.

Here, the search conditions are determined by specifying keywords and setting conditions for other bibliographic information.

First, it is determined whether condition settings other than keywords for each document are satisfied. If the conditions are met,
The document accuracy of the document is calculated as described below. If the conditions are not met, the document accuracy of the document is not calculated and the value is set to zero.

Keywords are specified using a search condition expression consisting of keywords that express the information the user wants to obtain. A search condition expression is a keyword or multiple keywords.
They are combined using D (logical product), OR (logical sum), and NOT (negation). A combination of multiple keywords is used when a single keyword expressing the information the user is trying to obtain does not exist in the document management device.

Next, the search condition expression, document accuracy calculation method, and keyword connection learning method included in the previously proposed contents will be individually explained.

A. Search Condition Expression The search condition expression that the document search device of this embodiment accepts as input is one in which keywords are combined using AND (logical product), OR (logical sum), and NOT (negation) operators. be. As a result, for example, "a document without keyword A"
Searches such as "documents containing both keywords A and B" can be performed. A search condition expression in which keywords are arbitrarily combined with AND, OR, NOT is a search condition expression that combines keywords with OR, NO.
It is possible to convert the sub-search condition expressions connected by T into the product standard form in the form of AND. This conversion is performed by the request processing unit 13. The search condition expression for the product standard form is Query = S
Q(1)*・・−* S Q(N) ---(1
). Here, II*II represents AND and is N22. Further, 5Q(h) represents a sub-search condition expression % expression % (2) consisting of only OR and NOT. Here, "K Q + °' is the q1th keyword, II 11 is 0R1rr 1 ++ is NO
represents T, and n≧0, m≧1, and n+m≧1. Let the set of keywords without negation be Q+(h) and the set of keywords with negation be Qih), then Q+(h) = (Kq, , --, Kq, 1Q
(h)”= (Kqfl++ , −・−・・・K
qn+, ). However, it is assumed that there are no keywords included in Q+(h) and Q-(h) at the same time. This check is performed by the request processing unit 13, and if there are keywords included at the same time, this fact is displayed on the display 17 to alert the user.

B0 Document accuracy calculation method Document accuracy is defined as a numerical value indicating the strength of the relationship between the keyword group of each document in the document database and the keyword in the search condition formula specified by the user. Calculated in section 12.

Document accuracy is determined by the following two steps.

a. Calculate the document accuracy for the sub-search condition expression (this is called sub-document accuracy).

b. Calculate the product of the sub-document accuracy for the full-open search conditional expression and use it as the document accuracy.

Document accuracy is calculated for all documents, appropriate documents are selected by threshold processing, etc. according to the user's specifications, and search results are obtained.

The above two steps will be explained. First, the first step is to calculate the subdocument probability for the subsearch condition expression.
If the 6th sub-document accuracy of the i-th document is ri(h), this is performed according to the following equation (3).

・・・・・・・・・・・・・・・・・・・・・(3) However, when A1 is the set of keywords indexed to the i-th document, RjJ and sIJ are Next (4)
Calculated using equation (5).

However, Wjk indicates the degree of association between the fifth keyword and the second keyword (keyword connection weight).

If Q+(h) or Q-(h) is an empty set (φ),
The following equations (6) and (7) are used instead of equation (3).

As a second step, after calculating all sub-document probabilities for N sub-search condition expressions, document probabilities are calculated using equation (8).

C. Keyword connection learning method Keyword connection learning is performed by the learning management section 9. As the keyword connection learning method, for example, the learning method described in Japanese Patent Application No. 1-132696 proposed by the present applicant is used.

That is, the user's judgment regarding the search result during learning is assigned ``ri'' if the answer is correct, ``O'' if the answer is incorrect, and an ambiguous judgment is expressed as a real value between [0, 1]. Letting L be the evaluation value representing the user's judgment regarding the document accuracy X, the evaluation function is defined as follows.

e(X) =-(t-X)''...
・・・・・・・・・・・・・・・(9) In one learning session, the document that is currently being focused on (here, the i-th document)
, the value e(
All weights of keyword connections are changed to reduce ri). That is, Wmn 4- g(Wmn + aΔWmn)
...--(IQ). Here, a is a learning coefficient of a positive real number, and g is a normalization function so that the value of the keyword connection after change falls within the range [0, l].

・・・・・・・・・・・・・・・・・・・・・・・・(
11) Using the steepest descent method, the variation ΔWmn can be calculated as shown in equation (12).

・・・・・・・・・・・・・・・・・・(12) Here, from equation (8), therefore, ・・・・・・・・・・・・・・・・・・・・・・・・(
14) In the calculation formula (14) for calculating the change ΔWmn, i (h)/a Wmn is expressed as (I5) to (
17) Calculated by Eq.

Therefore, △Wmn==O except for the combination of (m+n) where rnc:Query and E A
There are only combinations of (m, n) that are EQery and nEAi.

In order to calculate ΔWmn, it is necessary to be able to calculate the partial differential of ri(h) with respect to Wmn. Here, Q” (
Based on the assumption that there are no keywords included in h) and Q-(h) at the same time, the partial differential of ri(h) with respect to Wmn can be calculated in the following three cases.

1. In the case of mfEQ” (h)・・・・・・・・・・・・・・・・・・・・・・・・
・・・(15) In the case of 2゜mEQ-(h)・・・・・・・・・・・・・・・・・・・・・(1(3
In the case of ゜mlQ'' (h) or m1Q-(h) (I5) ~ (
By substituting the result calculated by formula (17) into formula (14), Δ
Although Wmn can be found, equation (14) can be further simplified.

In that case, i; depending on whether it is 0 or not Since the calculation formula is different, Below, we divide into two cases. I will explain.

■.

In case of i+o At this time, all h (l≦h≦N) against Since 1(h)≠0, From equation (8) Since it can be rewritten as Equation (13) is as follows become.

Therefore, ・・・・・・・・・・・・・・・・・・・・・・・・(
20)■.

If i; 0 When i=O, The number of h such that 1(h)=O The calculation formula changes.

If the number of h is 1, then If h is h*, then Equation (13) becomes as follows.

Therefore, ・・・・・・・・・・・・・・・・・・・・・・・・(
When the number of 22h is two or more, equation (13) becomes as follows.

ari=O・・・・・・・・・・・・・・・・・・
・・・・・・(23Wmn Therefore, ΔWmn == O・・・・・・・・・・・・・・・・・・
(24) However, in this embodiment, the calculation of document accuracy using equations (3) to (6) mentioned above is performed at high speed.First, according to the content already proposed, simply (6
), it is necessary to calculate the sub-document probabilities for all documents by the number of sub-search condition expressions. However, according to equation (6), if a certain sub-document certainty is O, the final document certainty will always be 0 even if other sub-document probabilities have values other than O. Therefore, when calculating the document certainty of a certain document, if the subdocument certainty for a certain subsearch condition expression is O, the document certainty may be set to O without calculating the remaining subdocument probabilities for that document. As a result, the amount of calculation required to calculate the document accuracy is reduced, and the calculation speed of the document accuracy can be increased. FIG. 2 is a flowchart showing such document accuracy calculation processing.

Effects of the Invention Since the present invention is configured as described above, when calculating document accuracy, when a certain sub-document accuracy is O, even if other sub-document accuracy is not O, the final document accuracy is always calculated. Therefore, when calculating the document accuracy, when the calculation result of the sub-document accuracy for a certain sub-search condition expression becomes O, the document accuracy is set to O, and the remaining sub-document accuracy calculations for that document can be performed. This eliminates the need for document accuracy calculations, which speeds up the calculation of document accuracy, thereby reducing the time required for searching and making searches more efficient.

[Brief explanation of the drawing]

The drawings show one embodiment of the present invention, with FIG. 1 being a block diagram and FIG. 2 being a flow chart. 1. Keyword extraction means, 2. Registered document, 4 keyword connection table management means, 5. Inverted file management means, 9. Learning management means, 11.
...Document selection means, 12...Document accuracy calculation means, 14
...Sort means, 15...Display management means diagram

Claims (1)

[Claims] A keyword extraction means for extracting keywords from the registered document when registering the registered document and its bibliographic information in a document database, and creating and changing an inverted file indicating the relationship between the registered document and the keyword. An inverted file management means and a keyword connection table management means for creating and changing a keyword connection table that describes related information between the keywords are provided, and the keywords included in the search condition expression input by the user and each Document accuracy calculation means that defines document accuracy as a value indicating the strength of association between a group of keywords of registered documents in a file, and calculates document accuracy using the keyword connection table, the inverted file, and a predetermined method; ,
A document sorting/display management means that outputs search result documents in the order of the calculated document accuracy, and a user who interactively determines whether the document accuracy given to each document in the search results is appropriate. A learning management means changes the weight of a keyword connection according to a predetermined method when an instruction is given, and a document selection means selects documents that match the search condition expression, When any of the calculation results of the sub-document probabilities defined by the document probabilities for the sub-search condition expressions combined with becomes 0, the calculation of the remaining sub-document probabilities for all sub-search condition expressions is stopped and the document certainty is set to 0. A document retrieval device characterized in that: