JPH08221558A - Method and device for filing document - Google Patents

Abstract

PURPOSE: To simultaneously input plural documents with a simple configuration and operation by displaying document image data and coded data respectively corresponding to plural documents on a display part, performing post-correction as needed and simultaneously registering the document image data and the coded data on a data base later. CONSTITUTION: A document partitioning means 3 compares series of image data corresponding to plural kinds of documents with the document image pattern of a document item defining means 13 and partitions them as the document image data corresponding to one document. A document discriminating means 4 compares the document image data with the document image pattern defined by the document item defining means 13 and discriminates the kind of the document. A data base registration item extracting 5 segments the image data and a character recognizing means 6 recognizes the character pattern of image data, turns it to a character code and sends it to a batch display means 7. A correcting means 8 reponds to the correcting operation to the information displayed on a display part 14, transmits it to the batch display means 7 and reflects the data with the displayed contents on the display part 14.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a document filing method and apparatus, and is particularly applicable to a document filing system for registering and retrieving document image information when inputting and registering document image information.

[0002]

2. Description of the Related Art Conventionally, in a document filing system for registering and retrieving document image information, various methods have been proposed for easily inputting registration items in a database used for retrieving document image information. As a document filing system capable of inputting registration items to a database used for searching such document image information, there is one disclosed in, for example, Japanese Patent Laid-Open No. 4-77885. This is to search for image data such as a business card read by a scanner by character recognition by a character recognition means and determining an item, and registering it in a database using the character data and the item type of the character data. Is.

FIG. 8 is a display showing a correction operation in this document filing system. In the figure, C1 is a cursor for the character data currently designated, C2 is a selection display of the recognition candidate list for the character data designated by the cursor C1, and C3 is a selection display of the item name list designated by the cursor C1. Show. The cursor C1 is moved to the position of the character data to be corrected, the correct character is selected by C2, the correct item name is selected by C3, and the correction is performed. After such post-correction is sequentially performed, the read image data and the recognized character data are registered in the database.

[0004]

However, the display and correction operations in the document filing system described above display a list of item names for one document, and after correcting them, display a list of items for another document and make corrections. Since it is repeatedly performed, it is necessary to perform a complicated operation of updating and correcting the display of the screen each time in order to correct all the documents, and there is a problem that the work efficiency of the correction work is poor. In the document filing system described above,
It handles only documents that have a limited number of items in a limited format, such as business cards and slips, and there is no convenience to input and modify multiple documents of multiple types at once. It was still insufficient in terms of user convenience.

The present invention has been made in order to solve the above-mentioned problems, and it is possible to collectively input a plurality of types of a plurality of documents with a simple configuration and operation, and the work load on the user in the correction work. It is an object of the present invention to provide a document filing method and apparatus that can reduce the number of problems and improve the usability.

[0006]

According to the document filing method of the present invention, a series of image data obtained by collectively reading a plurality of types of a plurality of documents from an image reading apparatus is associated with the plurality of read documents. A document image data input process that is input as image data, a pattern recognition process that pattern-recognizes and encodes the document image data that was input in the document image data input process, and generates coded data. A first display step for collectively displaying the document image data and the coded data to be displayed on the display unit, and the necessity of post-correction of the coded data is determined based on the display result of the first display step. A correction process for post-correcting the coded data based on the determination result, and a second display process for displaying the coded data corrected by the correction process on the display unit. , In which and a database registration processing step of registering in a database in bulk document image data and the coded data displayed on the display unit.

Further, in the document filing method according to the next invention, the document image data input process includes a document dividing process of comparing a series of image data with predefined fixed document information and dividing the read image into a plurality of read documents. , A document discrimination process of comparing a plurality of documents segmented by the document segmentation process with standard document information to discriminate the type of the document, and transmitting the document image data.

In the document filing method according to the next invention, the document image data input process further includes database registration item values for registering the document in the database for each document type in addition to the standard document information. A document item definition step in which a database registration item area indicating a position is defined in advance, and a database registration item extraction step for extracting image data of the database registration item area corresponding to the document type from the document image data corresponding to the document. The image data of the database registration item area extracted in the database registration item extraction process is coded in the pattern recognition process, the coded database registration item value is given, and the document image data is sent to the database in the database registration processing step. It is to register.

In the document filing method according to the next invention, the first and second display steps include document image data of a plurality of types of a plurality of documents and encoded database registration item values, and document and database registration items. Displayed collectively in an arrayed table format, the correction process is to correct the database registration item value coded corresponding to the document in the document and database registration item table.

In the document filing method according to the next invention, the display and operation of the first and second display steps are switched according to the type of document.

In the document filing method according to the next invention, for a plurality of documents of different types, a first display mode in which documents of the same type are collectively displayed and a document of different types are mixed and displayed simultaneously. The second display mode to be performed is switched according to a user's request.

In the document filing method according to the next invention, the second display mode is a fixed display mode in which the display position of the database registration item value which is different for each document type is fixed and displayed, and a second display mode is set for each document type. The display position of different database registration item values is switched to the left-justified display mode in accordance with the user's request.

In the document filing method according to the next invention, the correction process is coded as an image data display area for constantly enlarging and displaying the document image data corresponding to the database registration item value in the document to be corrected. A pattern data display area for constantly enlarging and displaying pattern data of database registration item values is provided.

In the document filing method according to the next invention, the correction process includes the document image data of the entire page including the database registration item value in the document to be corrected and the coded pattern data of the database registration item value. And a fixed display area for always displaying and at a designated display magnification.

In the document filing method according to the next invention, the display of the document image data of the entire page in the fixed display area is performed by changing the area on the document image data corresponding to the database registration item value to be corrected. An area or a color is displayed in a frame, and the area on the document image data corresponding to the database registration item value to be corrected is moved to the minimum necessary to fit in the display area.

Further, in the document filing method according to the next invention, when the user corrects the correction process to be a document type different from the document type discriminated by the document discrimination process, the document type is corrected. Only the document is reprocessed according to the processing procedure corresponding to the document type defined by the document item definition process.

Further, in the document filing method according to the next invention, the database registration processing step includes a keyword extraction step of cutting out a word from coded data obtained by encoding the entire document by the character recognition step and extracting it as a keyword. When a keyword is designated as a registration item, the keyword extracted in the keyword extraction process is added and registered in the database.

Further, in the document filing method according to the next invention, the area for extracting the keyword from the database registration item value is limited, and the keyword is extracted from the coded data in which only the designated area is coded by the character recognition process. Then, the extracted keywords are added and registered in the database.

Further, in the document filing method according to the next invention, a keyword extraction range designating step for designating a keyword extraction range according to the content of the document is provided, and the entire document is encoded by the character recognition process. The keyword is extracted from the specified extraction range, the extracted keyword is added and registered in the database.

Further, a document filing apparatus according to the next invention inputs a series of image data obtained by collectively reading a plurality of types of a plurality of documents from an image reading device as document image data corresponding to the plurality of read documents. Document image data inputting means, pattern recognition means for pattern-recognizing and coding the document image data input by the document image data inputting means, and generating coded data, and document image data respectively corresponding to a plurality of documents. And a display means for collectively displaying the coded data on the display unit, and whether or not the coded data needs to be corrected later based on the display result on the display unit, and the coded data is corrected after the determination result. The correction means to be supplied to the display means and the document image data and the coded data displayed on the display section are collectively registered in the database. Is intended and a database registration processing means.

Further, in the document filing apparatus according to the next invention, the document image data input means compares the series of image data with predefined standard document information, and divides the read image into a plurality of read documents. A document discriminating unit that discriminates the type of the document by comparing the plurality of documents segmented by the document segmenting unit with the standard document information and sends the document image data.

In the document filing apparatus according to the next invention, the document image data input means further describes the database registration item value when registering the document in the database for each type of document in addition to the fixed document information. A document item definition means for predefining a database registration item area indicating a position, and a database registration item extraction means for extracting image data of a database registration item area corresponding to a document type from document image data corresponding to the document. The image data of the database registration item area extracted by the database registration item extraction means is coded by the pattern recognition means, the coded database registration item value is given, and the document image data is transferred to the database by the database registration processing means. It is to register.

In the document filing device according to the next invention, the display means collectively displays the document image data of a plurality of types of a plurality of documents and the encoded database registration item value in a table format in which the documents and the database registration items are arranged. The correction means is for correcting the database registration item value coded corresponding to the document in the table of documents and database registration items.

[0024]

A series of image data obtained by collectively reading a plurality of types of a plurality of documents from the image reading device is input as document image data corresponding to each of the plurality of read documents,
The document image data is pattern-recognized to generate coded data, and the document image data and coded data corresponding to each of a plurality of documents are collectively displayed on the display unit, and the coded data is post-corrected as necessary. Then, the document image data and the coded data displayed on the display unit are collectively registered in the database. As a result, a plurality of types of documents can be collectively input with a simple configuration and operation, and the work burden on the user in the correction work can be reduced and usability can be improved.

Further, a series of image data is compared with pre-defined standard document information to be divided into a plurality of read documents, and the plurality of sectioned documents are compared with the standard document information to determine the type of document. Determine. Thus, it is possible to reliably input a plurality of documents into a plurality of types at once with a simple configuration and operation.

Further, image data of the database registration item area corresponding to the type of the document is extracted from the document image data corresponding to the document, the image data of the database registration item area is coded in the pattern recognition process, and the coding is performed. The document image data is registered in the database by adding the database registration item value. This makes it possible to reliably input a plurality of documents of a plurality of types at once with a simple configuration and operation.

Further, the document image data of a plurality of kinds of a plurality of documents and the coded database registration item values are collectively displayed in a table format in which the documents and the database registration items are arranged, and a table of the documents and the database registration items is displayed. Correct the database entry value coded for the document. As a result, the work burden on the user in the correction work can be reduced and usability can be improved.

In the first and second display steps, the display and operation are switched according to the type of document. As a result, the user can easily recognize the type of the document, and the work burden on the user in the correction work can be reduced and the usability can be improved.

Further, for a plurality of documents of different types,
A first display mode in which documents of the same type are collectively displayed and a second display mode in which documents of different types are mixed and displayed simultaneously
The display mode of and is switched according to the user's request.
With this, if the user selects the first display mode,
You can compare the contents of multiple documents of the same type, and if you select the second display mode, you can compare the contents of different documents.
By selecting these as necessary, the work load on the user in the correction work can be reduced and usability can be improved.

The second display mode includes a fixed display mode in which the display position of the database registration item value that differs for each type of document is fixed and displayed, and a display position of the database registration item value that differs for each type of document. Switches between left-justified display mode, which displays left-justified, according to the user's request.
Therefore, if the user selects the fixed display mode, it is possible to easily recognize the presence or absence of database registration items for each document type, and if the left-justified display mode is selected, more database registration items can be registered in the same document. Can be displayed and recognized, and these can be selected as necessary, whereby the work load on the user in the correction work can be reduced and usability can be improved.

Further, in the correction process, the document image data corresponding to the database registration item value in the document to be corrected is always enlarged and displayed in the image data display area, and the database registration item value coded in the pattern data display area is displayed. The pattern data of is always enlarged. This allows
It is possible to recognize the enlarged pattern data of the correction target and the document image data thereof by comparison, and reduce the work burden on the user in the correction work and improve the usability.

In the correction process, the document image data of the entire page including the database registration item value in the document to be corrected and the coded database registration item value pattern data are displayed in the fixed display area. , Always display at the specified display magnification. As a result, the pattern data to be corrected displayed at the designated display magnification can be recognized in comparison with the document image data, and the work load on the user in the correction work can be reduced and the usability can be improved.

The display of the document image data of the entire page in the fixed display area is performed by enclosing the area on the document image data corresponding to the database registration item value to be corrected with a frame or displaying a color, The area on the document image data corresponding to the database registration item value to be corrected is moved to the minimum necessary to fit in the display area. As a result, the document image data corresponding to the correction target database registration item value can be surely recognized, and the work burden on the user in the correction work can be reduced and the usability can be improved.

When the user corrects the correction process so that the document type is different from the document type determined by the document determination process, only the document with the corrected document type is defined by the document item definition process. Reprocess according to the processing procedure corresponding to the document type. As a result, even if a document is erroneously discriminated, the document can be easily corrected, and a plurality of documents of a plurality of types can be surely input at once.

In the keyword extraction process of the database registration process, words are cut out from the encoded data obtained by encoding the entire document by the character recognition process and extracted as keywords, and when the keywords are designated as registration items in the database, Add the extracted keyword and register it in the database. As a result, the keyword can be easily extracted and registered in the database, and the usability for the user can be improved.

Further, the area in which the keyword is extracted from the database registration item value is limited, only the specified area is encoded by the character recognition process, the keyword is extracted, and the extracted keyword is assigned. Register in the database. Thereby, the database registration item value can be easily extracted as a keyword and registered in the database, and the usability for the user can be improved.

Further, in the keyword extraction range specification step, the range for extracting the keyword is specified according to the content of the document, and the keyword is extracted from the specified extraction range in the coded data obtained by encoding the entire document by the character recognition step. It is extracted, and the extracted keyword is added and registered in the database. As a result, effective keywords can be extracted and registered in the database, and the usability for the user can be improved.

Further, the document image data inputting means inputs a series of image data obtained by collectively reading a plurality of plural kinds of documents from the image reading device as corresponding document image data, and the pattern recognizing means recognizes the pattern. To generate the encoded data by the display means, and collectively display the document image data and the encoded data corresponding to each of a plurality of documents on the display section, and the correction means, if necessary, based on the display result of the display section. The document image data and the coded data displayed on the display unit by the database registration unit are collectively registered in the database after being corrected and supplied to the display unit. As a result, a plurality of types of documents can be collectively input with a simple configuration and operation, and the work burden on the user in the correction work can be reduced and usability can be improved.

Further, in the document image data inputting means, the document dividing means compares the series of image data with the predefined fixed form document information and divides it into a plurality of read documents,
The plurality of documents divided by the document discriminating means are compared with the standard document information to discriminate the type of the document, and the document image data is transmitted. As a result, it is possible to reliably input a plurality of documents in a plurality of types at once with a simple configuration and operation.

Further, in the document image data input means, in addition to the standard document information by the document item definition means, a database registration item area indicating the position where the database registration item value is described is previously defined for each document type, and the database registration is performed. The image data in the database registration item area is extracted from the document image data corresponding to the document by the item extracting means, the database registration item value encoded by the pattern recognizing means is added, and the document image data is registered in the database. This makes it possible to reliably input a plurality of documents of a plurality of types at once with a simple configuration and operation.

Further, the display means collectively displays the document image data of a plurality of types of a plurality of documents and the coded database registration item values in the form of a table in which the documents and the database registration items are arranged. Modify the database entry value coded for the document in the Documents and Database Entries table. As a result, the work burden on the user in the correction work can be reduced and usability can be improved.

[0042]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described in detail below with reference to the drawings.

Example 1. FIG. 1 shows the overall configuration of a document filing system according to the present invention installed on a personal computer or workstation.
Is a control unit which is a CPU (Central Processing Unit) and controls the operation of the entire system. The control unit 1 includes a document reading unit 2, a document dividing unit 3, a document discriminating unit 4, a database registration item extracting unit 5, a character recognizing unit 6, a collective displaying unit 7, a correcting unit 8, a keyword extracting unit 9, and a database registering unit. 10 and the storage unit 11 are instructed to control and data is transmitted and received.

The document reading means 2 is a software driver that operates corresponding to the document reading unit 12 which is an optical image reading device having a sheet feeder. As a result, a plurality of documents of a plurality of types are placed on the document reading unit 12, and image data obtained by collectively scanning are input to the document filing system. Document classification means 3
Compares a series of image data corresponding to a plurality of types of documents input through the document reading unit 2 with a document image pattern defined in advance in the document item defining unit 13 using a pattern matching method or the like. , The top page of a document is recognized and classified as document image data corresponding to one document. The document image data obtained as a result is again read by the document discrimination means 4 in the document item definition means 13
The document type is determined by comparison with the document image pattern defined in.

In practice, in this embodiment, at the beginning of the document, FIG.
A plurality of documents of a plurality of types are collectively read and input with the head identification page PH shown in FIG. On the top identification page PH, the top page mark HM of a rectangular area that is filled in advance is displayed.
And a document type mark SM composed of a plurality of rectangular areas each of which is designated by the user by filling in the document type. Therefore, in the document item definition means 13, a document image pattern corresponding to the first page mark HM and a document image pattern having a document type mark SM corresponding to the type of document are defined in advance. As a result, the document classifying unit 3 and the document discriminating unit 4 can classify the input image data for each document by a simple pattern matching method, and determine the document type.

When the above-mentioned head identification page PH (FIG. 2) is used, instead of the pattern matching method, the presence or absence of a filled rectangular area is detected to divide the document and determine the document type. However, in this case, the processing of the document classification means 3 and the document discrimination means 4 can be further reduced. Further, without using the head identification page PH, the head document image pattern is previously defined and stored in the storage unit 11 for a plurality of types of documents to be input, and pattern matching is performed using this document image pattern. The document may be divided and the type of the document may be determined at the same time. In this case, the user may place only the document on the document reading device 12 and read the document, which improves the usability in inputting the document.

In the document item definition means 13, in addition to the document image patterns of a plurality of types used for the above-described document division and document type discrimination, the item name of the database registration item corresponding to each document type and its The description position in the document corresponding to the item name is defined as the database registration item area. Database registration item extraction means 6
Cuts out the image data of the contents of the database registration item area according to the document type from the document image data judged by the document judging means 4. In the case of this embodiment, the database registration item area is defined by the numerical value of the coordinate information of the area as a description position in the document, and the document image data within the range of this coordinate information is cut out as the image data of the database registration item area. . Note that this database registration area may also be defined as a document image pattern, and in this case, the image data of the database registration item area can be cut out using the pattern matching method as described above.

The character recognition means 6 recognizes the character pattern of the image data of the database registration item area extracted by the database registration item extraction means 5 by the character recognition method and character-codes it. Is sent to the collective display means 7. The pattern for recognizing characters is characters, alphanumeric characters, symbols, patterns and the like. The collective display means 7 arranges documents and database registration items vertically and horizontally, and arranges image data of database registration items of a plurality of types of plural documents and character string data obtained by character encoding the data in two lines. And collectively display them on the display unit 14.
At the same time, the document image data of the corresponding page of the document in which the database registration item to be edited by the correction means 8 is displayed on the image data viewer, which is a fixed display area, and a frame is displayed on the corresponding area of the editing target. Various display information is generated and sent to the display unit. The display unit 14 presents the display information generated by the collective display unit 8 to the user, and is composed of a CRT (cathode ray tube) display or the like.

The correction means 8 responds to various correction operations instructed by the user through the operation section 15 on various information displayed on the display section 14 to make desired corrections to the internal data and at the same time. Is transmitted to the collective display means 7 and is reflected on the display content displayed on the display unit 14. In addition to the correction operation of the recognized characters, the user can operate the classification of the document and the correction of the error of the type. In this case, according to the type of the corrected document, the corresponding document image data A desired database registration item extraction area is obtained from the document item definition means 13, reprocessed by the database registration item extraction means 5 and the character recognition means 6 described above, and additionally displayed by the collective display means 7. .
The operation unit 14 is composed of a keyboard and a pointing device such as a mouse for inputting a correction desired by the user to the information displayed on the display unit 14 into the correction unit 10.

The keyword extracting means 9 is the character recognizing means 6
From the character string data of the database registration item coded by and corrected by the correction means 8, a keyword useful for document retrieval is extracted. Further, according to the type of the document, all the words are cut out from the character string data encoded by the character recognizing means 6 for the document image data of the entire document area or the designated document category, for example, the area of the summary or the like. May be extracted as Database registration means 10
Is the database registration item extracted by the database registration item extraction means 5, coded by the character recognition means 6, and corrected by the correction means 8 and the keyword extracted by the keyword extraction means 9 as additional information, and the document discrimination means The document image data determined in 4 is registered in the database of the storage unit 11. The storage unit 14 stores the document image pattern of the document item definition unit 13, the document registered by the database registration unit 13, and the like, and includes a semiconductor storage device, a disk device, or the like.

FIG. 3 shows the flow of the document filing process in the document filing system of this embodiment having such a configuration. A plurality of types of a plurality of documents 20 are placed on the document reading unit 12 and are collectively input through the document reading unit 2, and a series of image data corresponding to the plurality of documents are converted into documents by the document dividing unit 3. Divided into
The document discriminating means 4 discriminates the type of each document. For example, for the document image data 21A determined to be the document A, the definition 22A for the document A obtained from the document item definition means 13 is applied, and the document image data 21A is processed according to the procedure defined therein.

Image data 23 of the database registration item area is cut out from each document image data 21 by the database registration item extracting means 5 according to the definition 22 of the document item defining means 13. The image data 23 of each database registration item area cut out as a result is character coded by the character recognizing means 6, and character string data 24 consisting of database registration item values is created. These are displayed by the collective display / correction interface 25, and are post-corrected if necessary, and the document image data and the character string data are registered in the database 26 built in the storage unit 11.

Batch display / correction interface 25
Will be described in detail. Information for collectively displaying the database registration items of all documents is generated by the collective display means 7 and displayed on the display unit 14, so that the user confirms the information and operates the operation unit 15 as necessary. You can interactively modify. In this case, only one cursor is always displayed on the operation unit 15, and the database registration item at the position where the cursor is displayed becomes the correction target at that time.

In the database registration item to be corrected, the image data and the encoded character string data are enlarged and displayed, whereby the user corrects the encoded character string data while checking the enlarged image data. it can. The image data of the corresponding page of the document that contains the database registration item to be modified is always displayed in the image data viewer, and the database registration item area corresponding to the database registration item is displayed in a frame or the color is reversed. By displaying as, the user can easily recognize the database registration item to be corrected on the image data.

If the size of the image data of the corresponding page is too large to fit in the image data viewer, the scroll is performed within the minimum necessary range in order to display the area corresponding to the database registration item to be corrected. When modifying the coded character string data of database registration items, if the selected character has two or more character recognition candidates, a list of them can be displayed and replaced with the character selected by the user. However, if there is no correct character in the list of character recognition candidates, enter the correct character from the keyboard or the like by using Kana-Kanji conversion or the like.

Here, the display of the collective display / correction interface 25 for correction displayed on the display unit 14 is shown in FIG. This is configured on the basis of the collective display data generated by the collective display means 7. The modifying means 8 interprets the modification instruction input from the operation unit 15 to make the modification, and then the result is collectively displayed by the collective display means 7. To the display unit 14, and by repeating this process thereafter, the user corrects each database registration item of each document as necessary.
In the case of this embodiment, in the display frame of the display unit 14, in addition to the main display area for displaying documents and database registration items in a tabular format, the display areas for the image data viewer 30 and the character string data viewer 31 described above are provided. It is distributed.

In the main display area, the document type label 32 is a label showing the type of the document, showing the result of the discrimination by the document discriminating means 4, and the data displayed in the same line is the database registration item of the same document. Indicates that there is.
Further, the database registration item label 33 is a label showing a database registration item for searching a document, and shows a result extracted by the database registration item extracting means 5. Data indicated in the same digit is the same database of each document. Indicates that it is a registered item. The cells corresponding to each document are the image data cell 34 and the character string data cell 35.
It is composed of two stages.

Of these, the image data cell 34 shows the image data of the area of the database registration item of the document image data in the document. The image data displayed at this time is reduced by the necessary minimum so that the display fits within the image data cell 34. The character string data cell 35 is
The character string data obtained by encoding the image data in the area corresponding to the database registration item of the document image data in the document by the character recognition means 6 is shown. This character string data cell 3
On the above 5, the character string data can be corrected. Also, at some point, only one of the character string data cells
The image data cell 34 that owns the
The character string data cell 35 is called a current cell and is a correction target at that time.

The image data viewer 30 is a fixed display area for displaying the image data of the page corresponding to the document corresponding to the current cell. A frame 37 is displayed in the area corresponding to the current cell in the image data of the image data viewer 30. If the frame 37 is outside the display area, the image of the display portion is moved by the minimum necessary amount, and the frame 37 is displayed within the image data viewer to the maximum extent. The character string data viewer 31 is a fixed display area for displaying the character string data of the current cell, and has a normal editor function. A cursor 38 is always displayed on the character string data viewer 31, and the character string data can be corrected.

As a modification of the character string data, the cursor 36 on the current cell or the character string data viewer 31 is used.
Alternatively, when one character corresponding to 38 is modified, a recognition candidate selection screen showing a list of recognition candidate characters is popped up and displayed as shown in FIG. In this figure, the image data 40 for one character to be corrected is displayed and
The recognition candidate characters 41 are displayed one by one with the type such as kanji, hiragana, katakana, and alphanumeric characters. Therefore, the user selects a character to be modified and selected by moving a pointing device such as a mouse or a cursor. If the correction is not necessary, the display of end 42 is instructed and input.

As a result, the recognition candidate selection screen is closed, and the characters in the corresponding character string data are corrected at the positions of the cursors 38 and 36 on the character string data viewer 31 and the current cell. When the character desired to be corrected is not displayed in the recognition candidate selection screen, the user can correct the character corresponding to the cursors 36 and 38 or the character string including the character by using the interface of a usual editor. Actually, when one of the cursor 38 on the character string data viewer 31 and the cursor 36 on the current cell moves, the other cursor moves so as to always keep the same position on the character string data. When the correction is made in either the character string data viewer 31 or the current cell, the other character string data is always corrected.

According to this structure, the database registration item area to be extracted is defined for each type of document, and the image data of a plurality of types of plural documents collectively read based on this definition are collectively determined. By extracting necessary database registration items and encoding them by the character recognizing means into character string data, it is possible to efficiently input the database registration items to be used for searching the document image. Furthermore, by collectively displaying the image data of the database registration item and the encoded character string data for a plurality of documents of a plurality of types and making corrections, the work load on the user at the time of the correction operation can be reduced.

Example 2. In the collective display correction interface of the first embodiment described above, the image data viewer 30 and the character string data viewer 31 are displayed in addition to the display of the document and database registration items. As shown in FIG. 6, only characters and database registration items are displayed in a table format. In this case, the display of the current cell in which the cursor 36 exists is always enlarged and displayed, and when the cursor 36 moves to another cell, the display of the cell of the movement source is returned to the normal size and the display of the cell of the movement destination is displayed. Enlarge and display.

By doing so, in addition to the effect similar to that of the first embodiment, if the display area is the same as that of the first embodiment, the database registration items corresponding to more documents can be displayed. , It is possible to further reduce the work burden on the user when performing the correction operation. When displaying database registration items corresponding to the same number of documents as in the first embodiment, the image data viewer 30 and the character string data viewer 3 are displayed.
Since 1 is not displayed, the display area can be reduced,
The display screen of the display unit 14 can be effectively used.

Example 3. In the batch display / correction interface of the above-described first and second embodiments, a plurality of documents of a plurality of types are collectively displayed in the order of being read collectively. However, in this embodiment, only data of the same document type is displayed. All of the multiple documents of multiple types that are collectively read by performing the correction work with them as one unit and correcting the document of another type when the correction of one document type is completed. Make corrections. Further, the position where each document is displayed may be rearranged based on the type of document. By doing so, in addition to achieving the same effects as those of the above-described first and second embodiments, when comparing with the first and second embodiments, the displayed documents of the same type are compared. Since the correction operation can be performed, the work burden of the correction operation on the user can be further reduced.

Example 4. In the collective display / correction interface of the above-described first to third embodiments, a blank is displayed for an item in which there is no value of a database registration item of each document and a cell at that position does not exist. In the embodiment, as shown in FIG. 7, there is no value of the database registration item of each document, and the cells at the position are not displayed, and the cells are displayed on the left. In this case, the item name displayed on the database registration item label 33 becomes the database registration item name corresponding to the document corresponding to the current cell, and every time the current cell is moved, the database registration item corresponding to the destination document is registered. The item name displayed on the label 33 is changed. By doing so, in addition to achieving the same effects as those of the above-described first to third embodiments, compared with the first to third embodiments, the database registration items corresponding to the document to be corrected can be changed. By increasing the display amount, it is possible to further reduce the work load of the user during the correction operation.

Example 5. In the image data viewer 30 in the collective display correction interface of the first embodiment, the case where the displayed image data includes the moved database registration item area in accordance with the movement of the current cell has been described. In this embodiment, the display area of the image data is moved using a pointing device such as a mouse,
By designating any one point in the database registration item area in the image data, the cursor 36 of the document and database registration item table is moved. Further, the image data viewer 30 may be provided with an operation display for switching to the display of another sheet of document image data. By doing so, in addition to achieving the same effect as that of the first embodiment, the user can visually perform a correction operation while looking at the display of the image data viewer 30. The work load can be further reduced.

[0068]

As described above, according to the present invention, a series of image data obtained by collectively reading a plurality of documents of a plurality of types from an image reading apparatus is used as document image data corresponding to the read plurality of documents. Input the document image data, generate the coded data by pattern recognition, and display the document image data and the coded data corresponding to each of the multiple documents at once on the display unit, and if necessary, the coded data. By post-correcting and registering the document image data and the coded data displayed on the display unit in the database in a batch, a plurality of types of a plurality of documents can be input in a batch with a simple configuration and operation, It is possible to realize a document filing method that can reduce the work burden on the user in correction work and improve usability.

According to the next invention, a series of image data is compared with pre-defined standard document information, divided into a plurality of read documents, and the plurality of divided documents are compared with the standard document information. By discriminating the type of the document, it is possible to realize a document filing method capable of surely inputting a plurality of documents into a plurality of types with a simple configuration and operation.

According to the next invention, the image data of the database registration item area corresponding to the type of the document is extracted from the document image data corresponding to the document, and the image data of the database registration item area is subjected to the pattern recognition process. Document filing that allows you to input multiple documents of multiple types in a batch with a simple configuration and operation by encoding and adding the encoded database registration item value and registering the document image data in the database The method can be realized.

According to the next invention, the document image data of a plurality of types of a plurality of documents and the coded database registration item values are collectively displayed in a table format in which the documents and the database registration items are arranged. By correcting the database registration item value coded corresponding to the document in the database registration item table, it is possible to realize the document filing method that can reduce the work burden on the user in the correction work and improve the usability.

According to the next invention, the display and the operation are switched according to the document type in the first and second display steps, so that the user can easily recognize the document type. Therefore, it is possible to realize a document filing method that can reduce the work load on the user in the correction work and improve the usability.

Further, according to the next invention, for a plurality of documents of different types, a first display mode for collectively displaying documents of the same type and a second display mode for simultaneously displaying documents of different types are mixed. By switching the display mode of the above according to the user's request, if the user selects the first display mode, the contents of a plurality of documents of the same type can be compared and the second display can be displayed. If the mode is selected, the contents of different documents can be compared with each other, and these can be selected as needed, thus realizing a document filing method that can reduce the work burden on the user in the correction work and improve the usability.

According to the next invention, the second display mode is the fixed display mode in which the display position of the database registration item value that is different for each type of document is fixed and displayed, and the database display that is different for each type of document is performed. By switching the left-justified display mode in which the display position of item values is left-justified according to the user's request, if the user selects the fixed display mode, database registration for each document type will be performed. The presence or absence of items can be easily recognized, and if the left-justified display mode is selected, more database registered items can be displayed and recognized in the same document, and these can be selected as needed, thus making it possible to correct It is possible to realize a document filing method that can reduce the user's work load and improve usability.

According to the next invention, in the correction process, the document image data corresponding to the database registration item value in the document to be corrected is always displayed in the image data display area in an enlarged manner and the code is displayed in the pattern data display area. Since the pattern data of the converted database registration item values is always enlarged, it is possible to recognize the enlarged pattern data of the correction target and its document image data in contrast, and to reduce the work burden on the user in the correction work. It is possible to realize a document filing method that can reduce the number and improve the usability.

According to the next invention, in the correction process, the document image data of the entire page including the database registration item value in the document to be corrected and the coded database registration item are displayed in the fixed display area. By constantly displaying the value pattern data at the specified display magnification, the pattern data to be corrected displayed at the specified display magnification and its document image data can be recognized by comparison, and the user in the correction work It is possible to realize a document filing method that can reduce the work load of and improve the usability.

According to the next invention, the document image data of the entire page is displayed in the fixed display area by enclosing the area on the document image data corresponding to the database registration item value to be corrected with a frame. Alternatively, by displaying the color and moving the area on the document image data corresponding to the correction target database registration item value to the minimum necessary to fit in the display area, the document image corresponding to the correction target database registration item value It is possible to realize a document filing method that can reliably recognize data, reduce the work load on the user in the correction work, and improve usability.

Further, according to the following invention, when the user corrects the correction process so that it becomes a document type different from the document type discriminated by the document discrimination process, only the document whose document type has been corrected is documented. By reprocessing according to the processing procedure corresponding to the type of document defined by the item definition process, even if a document is misidentified, it can be easily corrected, and multiple documents of multiple types can be reliably collected. A document filing method that can be input can be realized.

According to the next invention, in the keyword extraction step of the database registration processing step, a word is cut out from the coded data obtained by encoding the entire document by the character recognition step and extracted as a keyword, and the keyword is registered as a database registration item. When is designated, the extracted keyword is added and registered in the database, whereby the keyword can be easily extracted and registered in the database, and a document filing method that can improve the usability for the user can be realized.

According to the next invention, the area for extracting the keyword from the database registration item value is limited, and the keyword is extracted from the encoded data in which only the designated area is encoded by the character recognition process. By adding the extracted keyword and registering it in the database, the database registration item value can be easily extracted as a keyword and registered in the database, and a document filing method that can improve the usability for the user can be realized.

According to the next invention, in the keyword extraction range designating process, the range for extracting the keyword is designated according to the document content, and the entire document is designated by the character recognition process. By extracting a keyword from the extraction range, adding the extracted keyword and registering it in the database, a valid keyword can be extracted and registered in the database, and a document filing method that can improve the usability of the user can be realized. .

According to the next invention, the document image data inputting means inputs a series of image data obtained by collectively reading a plurality of plural kinds of documents from the image reading device as the corresponding document image data, and the pattern The recognition means performs pattern recognition to generate coded data, the display means collectively displays the document image data and the coded data corresponding to a plurality of documents on the display unit, and the correction unit displays the display result on the display unit. Based on the need, the data is corrected and supplied to the display means, and the database registration means collectively registers the document image data and the coded data displayed on the display section in the database, thereby simplifying the configuration and operation. A document filing device that can input multiple documents of multiple types at the same time, reduce the work burden on the user in correction work, and improve usability. It can be realized.

According to the next invention, in the document image data inputting means, the document dividing means compares the series of image data with the predefined fixed form document information, divides the read document into a plurality of documents, and discriminates the document. By comparing multiple documents divided by means with standard document information to determine the document type and sending it as document image data, this makes it possible to ensure multiple documents for multiple types with a simple configuration and operation. It is possible to realize a document filing device capable of inputting all at once.

According to the next invention, in the document image data input means, the document item definition means further includes a database registration item area indicating the position where the database registration item value is described for each document type in addition to the standard document information. Predefined,
The image data in the database registration item area is extracted from the document image data corresponding to the document by the database registration item extraction means, the database registration item value encoded by the pattern recognition means is added, and the document image data is registered in the database. As a result, it is possible to realize a document filing device that can surely input a plurality of types of a plurality of documents collectively with a simple configuration and operation.

According to the next invention, the display means collectively displays the document image data of a plurality of types of a plurality of documents and the coded database registration item values in a table format in which the documents and the database registration items are arranged. In the correction means, the database registration item value coded in correspondence with the document in the table of documents and database registration items is corrected, so that the work burden on the user in the correction work can be reduced and the usability can be improved. A document filing device can be realized.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of a first embodiment of a document filing system according to the present invention.

FIG. 2 is a schematic diagram showing a head identification page used in batch input of the document filing system of FIG.

FIG. 3 is a schematic diagram illustrating a processing flow of the document filing system in FIG.

FIG. 4 is a schematic diagram illustrating collective display and correction operations in the document filing system of FIG.

5 is a schematic diagram showing a recognition candidate selection screen in the collective display and correction operation of FIG.

FIG. 6 is a schematic diagram illustrating collective display and correction operations of a second embodiment of the document filing system according to the present invention.

FIG. 7 is a schematic diagram illustrating collective display and correction operations of a fourth embodiment of the document filing system according to the present invention.

FIG. 8 is a schematic diagram illustrating display and correction operations in a conventional document filing system.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 control part 2 document reading means 3 document classification means 4 document discrimination means 5 database registration item extraction means 6 character recognition means 7 batch display means 8 correction means 9 keyword extraction means 10 database registration means 11 storage section 12 document reading section 13 document items Definition means 14 Display unit 15 Operation unit 20 Document 21 Document image data 22 Definition 23 Database registration item area image data 24 Character string data 25 Batch display correction interface 26 Database 30 Image data viewer 31 Character string data viewer 32 Document type label 33 Database Registration item label 34 Image data cell 35 Character data cell 36 Cursor 37 Frame 38 Cursor 40 Image data for one character 41 Character of recognition candidate 42 End display

 ─────────────────────────────────────────────────── ─── Continued Front Page (72) Inventor Yuzo Maruta 5-1-1 Ofuna, Kamakura-shi Personal Information Equipment Development Laboratory, Mitsubishi Electric Corporation

Claims (18)

[Claims] 1. A document image data input step of inputting a series of image data obtained by collectively reading a plurality of types of a plurality of documents from an image reading device as document image data corresponding to each of the plurality of read documents, A pattern recognition step of pattern-recognizing and coding the document image data input in the document image data input step to generate coded data, and the document image data and the coded data corresponding to the plurality of documents, respectively. Is displayed on the display unit in a batch, and it is determined whether post-correction of the coded data is necessary based on the display result of the first display process. A correction process for post-correcting the encoded data, a second display process for displaying the coded data corrected by the correction process on the display unit, and a display on the display unit. A document filing method, comprising: a database registration processing step of collectively registering the document image data and the coded data shown in a database. 2. The document image data input process includes a document dividing process of dividing the read image into a plurality of read documents by comparing the series of image data with predefined document information, and the document dividing process. The document filing process according to claim 1, further comprising: a document determination process of comparing the plurality of divided documents with the standard document information to determine a document type and transmitting the document image data. Method. 3. The document image data input step further includes, in addition to the standard document information, database registration indicating a description position of a database registration item value when registering the document in the database for each type of the document. A document item definition process in which item regions are defined in advance, and a database registration item extraction process for extracting the image data in the database registration item region according to the type of the document from the document image data corresponding to the document. The image data of the database registration item area extracted in the database registration item extraction step is coded in the pattern recognition step, the coded database registration item value is added, and the database registration processing step is performed. The document image data is registered in the database, according to claim 2. Document filing method described. 4. The first and second display steps are a table format in which the document image data of the plurality of types of the plurality of documents and the encoded database registration item value are arranged in a document and a database registration item. To display all at once,
4. The document filing method according to claim 3, wherein the correction step is to correct the coded database registration item value corresponding to the document in the table of documents and database registration items. 5. The document filing method according to claim 4, wherein the display and the operation of the first and second display steps are switched according to the type of the document. 6. A plurality of documents of different types,
It is characterized by switching between a first display mode in which the same type of documents are collectively displayed and a second display mode in which the different types of documents are mixed and simultaneously displayed according to a user's request. The document filing method according to claim 5. 7. The second display mode is a fixed display mode in which the display position of the database registration item value that is different for each type of the document is fixed and displayed, and the database registration item that is different for each type of the document. 7. The document filing method according to claim 6, wherein a left-justified display mode in which the display position of the value is displayed left-justified is switched according to a user's request. 8. The correction process includes an image data display area for constantly enlarging and displaying the document image data corresponding to the database registration item value in the document to be corrected, and the coded database registration item. The document filing method according to claim 4, further comprising: a pattern data display area for constantly enlarging and displaying the value pattern data. 9. The correction process includes the document image data of the entire page including the database registration item value in the document to be corrected, and the coded pattern data of the database registration item value. The document filing method according to claim 4, further comprising a fixed display area which is always displayed at a designated display magnification. 10. Displaying the document image data of the entire page in the fixed display area encloses an area on the document image data corresponding to the database registration item value to be corrected with a frame or 10. The document according to claim 9, wherein a color is displayed, and an area on the document image data corresponding to the correction target database registration item value is moved to a minimum necessary amount to fit in the display area. Filing method. 11. When the user corrects the correction process so that the document type is different from the document type determined by the document determination process, only the document with the corrected document type is the document. 5. The document filing method according to claim 4, further comprising reprocessing according to a processing procedure corresponding to the type of the document defined by the item definition process. 12. The database registration processing step includes a keyword extraction step of cutting out a word from the encoded data obtained by encoding the entire document by the character recognition step and extracting the keyword as a keyword, and the keyword registration step is performed as a registration item of the database. If a keyword is specified,
The document filing method according to claim 3, wherein the keyword extracted in the keyword extracting step is added and registered in the database. 13. The area for extracting the keyword from the database registration item value is limited, and the keyword is extracted from the coded data in which only the designated area is encoded by the character recognition process, and the extraction is performed. 13. The document filing method according to claim 12, wherein the keyword is added and registered in the database. 14. A keyword extraction range designating process for designating a range for extracting the keyword according to document contents, and a designated extraction range of the coded data obtained by coding the entire document by the character recognition process. 13. The document filing method according to claim 12, further comprising extracting the keyword, adding the extracted keyword, and registering the keyword in the database. 15. A document image data input means for inputting a series of image data obtained by collectively reading a plurality of types of a plurality of documents from an image reading device as document image data corresponding to the plurality of read documents, respectively. Pattern recognition means for pattern-recognizing and coding the document image data input by the document image data input means to generate coded data, the document image data and the coded data corresponding to the plurality of documents, respectively. Is displayed on the display unit collectively, and it is determined whether or not the post-correction of the coded data is necessary based on the display result of the display unit, and the coded data is post-corrected based on the judgment result. And the correction means to be supplied to the display means, and the document image data and the coded data displayed on the display section are collectively stored in a database. A document filing apparatus comprising: a database registration processing unit for registering. 16. The document image data input means compares the series of image data with predefined standard document information and divides the read image into a plurality of read documents, and the document dividing means. 16. The document filing according to claim 15, further comprising: a document discriminating unit that discriminates a document type by comparing the plurality of divided documents with the standard document information and sends the disc as the document image data. apparatus. 17. The document image data input means further includes database registration indicating a position of a database registration item value when registering the document in the database for each type of the document in addition to the standard document information. Document item definition means for predefining item areas, and database registration item extraction means for extracting the image data of the database registration item area according to the type of the document from the document image data corresponding to the document The image data of the database registration item area extracted by the database registration item extracting means is coded by the pattern recognizing means, the coded database registration item value is given, and the database registration processing means The document image data is registered in the database. 6. The document filing device described in 6. 18. The display means collectively displays the document image data of the plurality of types of the plurality of documents and the encoded database registration item value in a table format in which documents and database registration items are arranged. 18. The document filing apparatus according to claim 17, wherein the correction unit corrects the coded database registration item value corresponding to the document in the table of documents and database registration items.