JP2022039640A - Business form processing apparatus, business form processing program and business form processing method - Google Patents

Abstract

To provide a business form processing apparatus, a business form processing program and a business form processing method that can reduce cost which is required to correct a character erroneously recognized when character recognition of a business form is performed using an OCR.SOLUTION: According to the present embodiment, in a business form processing apparatus comprising a control section, the control section comprises: setting means that sets, for each reading area, text data set to a master existing under management of a business system associated with the reading area, for reading candidate list data for holding the text data supposed to be described on the reading area of a business form for each reading area; reading means that reads text data for each reading area by performing character recognition processing being accompanied by reference of the reading candidate list data after setting by the setting means on the basis of image data of the business form; and title-collecting means that acquires text data which is similar to the text data read by the reading means and which is set to the master, for each reading area.SELECTED DRAWING: Figure 1

Description

The present invention relates to a form processing device, a form processing program, and a form processing method.

There is a technology called OCR (Optical Character Recognition) that extracts character data from image data. Further, a technique has been developed in which paper such as a form is scanned by a multifunction device or the like, converted into image data, and then characters are extracted from the image data by OCR and transmitted to a business system.

The general process of importing the characters of the form into the business system using OCR is performed according to the following flow. (1) Set master data such as a reading area and a reading candidate list for each form. Here, the reading candidate list is a list of characters extracted by OCR. (2) Scan the received documents (forms) with a multifunction device or the like. (3) With reference to the master data, OCR is executed on the image data obtained by scanning the document. (4) The characters extracted by OCR are converted into text data. (5) Humans correct errors contained in the text data converted from characters.

Japanese Unexamined Patent Publication No. 2020-087112

However, initial / operational costs may hinder the introduction of OCR for the process of reading text data from forms. Specifically, when introducing OCR, it is necessary to set master data for each form reading area. Further, during the operation of OCR, it is necessary for a human to correct an error contained in the text data converted from the characters extracted by OCR.

Further, in the character recognition engine of OCR, a technique of recognizing character data from image data by using a machine learning model has been developed. Since the accuracy of character recognition by the character recognition engine using the machine learning model is determined by the training data set, it is appropriate to use the machine learning model properly according to the type of character to be recognized (for example, hiragana, katakana, kanji, numbers, alphabet). Is. For example, in order to prevent erroneous character recognition of similar characters such as "L" and "", a machine learning model is created by separating the learning data set for English and the learning data set for Japanese. Is generated, and the machine learning model is used properly according to the type of character recognized.

However, when improving the reading accuracy of similar characters, the setting of master data becomes complicated. Specifically, it is preferable to create a machine learning model for each type of character that recognizes characters, but since it takes time to learn the machine learning model, it is not possible to learn the machine learning model for all types of characters. It is not realistic, and machine learning models are often created for each language such as Japanese and English, but in this case, it is difficult to identify similar characters such as "L" and "", so the reading candidate list is displayed. It should be used to avoid misrecognition of similar characters. For example, when performing character recognition in a telephone number field, reading candidate list: "TEL.-0123456789: can be used to improve the reading accuracy of similar characters. However, character recognition such as a product name can be performed. When doing so, it is difficult to specify which read candidate list to use, so the read candidate list is often not available.

Further, even if a mechanism such as a reading candidate list is used for character recognition, if the characters in the image data read by the scanner are rubbed or tilted, a character recognition error occurs. OCR vendors allow the content of character recognition errors to be corrected from a dedicated screen, but when the cost of finding and correcting characters that are mistakenly recognized becomes high, the introduction of OCR for the conversion process of forms to text data is introduced. It is difficult to obtain merits, and there is a demand for a mechanism for registering the character information of a form in a business system using OCR without correcting the characters recognized by mistake as much as possible.

The present invention has been made in view of the above, and is a form processing device and a form processing that can reduce the cost required for correction of characters erroneously recognized when character recognition of a form is performed using OCR. The purpose is to provide a program and a form processing method.

In order to solve the above-mentioned problems and achieve the object, the form processing device according to the present invention is a form processing device including a control unit, and the control unit is expected to be described in a form reading area. For the read candidate list data for holding the text data for each read area, the text data set in the master under the control of the business system, which is associated with the read area, is set for each read area. A reading means for reading text data for each reading area by executing a character recognition process accompanied by reference to the reading candidate list data after setting by the setting means based on the means and the image data of the form, and reading. Each area is provided with a name identification means for acquiring text data set in the master, which is similar to the text data read by the reading means.

Further, the form processing program according to the present invention is for holding text data expected to be described in the form reading area for each reading area to be executed by the control unit of the form processing device including the control unit. Based on the setting step of setting the text data set in the master under the control of the business system, which is associated with the reading area, for each reading area for the reading candidate list data, and the image data of the form. By executing the character recognition process accompanied by the reference of the reading candidate list data after the setting by the setting step, the text data is read in each reading area and the reading step is read in each reading area. It includes a name identification step for acquiring text data set in the master, which is similar to text data.

Further, the form processing method according to the present invention is a reading candidate for holding text data, which is executed by the control unit of the form processing device including the control unit and is expected to be described in the reading area of the form, for each reading area. With respect to the list data, the text data set in the master under the control of the business system, which is associated with the reading area, is set for each reading area. A reading step of reading text data for each reading area by executing a character recognition process accompanied by reference to the reading candidate list data after setting by the setting step, and a reading step of the text data read in the reading step for each reading area. A name identification step for acquiring text data set in the master, which is similar to the above, is included.

INDUSTRIAL APPLICABILITY The present invention has an effect that it is possible to reduce the cost required for correction of characters erroneously recognized when character recognition of a form is performed using OCR.

FIG. 1 is a block diagram showing an example of the configuration of the form processing device according to the present embodiment. FIG. 2 is a diagram showing an example of the data configuration of the OCR reading candidate list setting master stored in the form processing apparatus according to the present embodiment. FIG. 3 is a diagram showing an example of a data structure of a business partner master stored in the form processing device according to the present embodiment. FIG. 4 is a diagram showing an example of the data structure of the OCR layout master stored in the form processing apparatus according to the present embodiment. FIG. 5 is a diagram showing an example of the data structure of the name identification master stored in the form processing apparatus according to the present embodiment. FIG. 6 is a flowchart showing an example of the flow of character recognition processing of a form in the form processing apparatus according to the present embodiment. FIG. 7 is a diagram for explaining an example of a reading candidate list setting process for the OCR layout master in the form processing device according to the present embodiment. FIG. 8 is a diagram showing an example of image data generated by the multifunction device. FIG. 9 is a diagram for explaining an example of character recognition processing in the form processing apparatus according to the present embodiment. FIG. 10 is a diagram for explaining an example of conversion processing into text data in the form processing apparatus according to the present embodiment. FIG. 11 is a diagram for explaining an example of name identification processing in the form processing apparatus according to the present embodiment. FIG. 12 is a diagram for explaining an example of a reading candidate list setting process in the form processing device according to the present embodiment.

Hereinafter, embodiments of a form processing device, a form processing program, and a form processing method according to the present invention will be described in detail with reference to the drawings. The present invention is not limited to the present embodiment.

An example of the configuration of the form processing device according to the present embodiment will be described with reference to FIG. 1 and the like. FIG. 1 is a block diagram showing an example of the configuration of the form processing device according to the present embodiment.

The form processing device 100 is constructed based on a commercially available desktop personal computer. The form processing device 100 is not limited to a device constructed based on a stationary information processing device such as a desktop personal computer, but is not limited to a commercially available notebook personal computer, a PDA (Personal Digital Assistants), a smartphone or a tablet personal computer. It may be constructed based on a portable information processing device such as.

The form processing device 100 includes a control unit 102, a communication interface unit 104, a storage unit 106, and an input / output interface unit 108. Each part of the form processing apparatus 100 is communicably connected via an arbitrary communication path.

The communication interface unit 104 connects the form processing device 100 to the network 300 so as to be communicable via a communication device such as a router and a wired or wireless communication line such as a dedicated line. The communication interface unit 104 has a function of communicating data with another device via a communication line. Here, the network 300 has a function of connecting the form processing device 100 and the server 200 so as to be communicable with each other, and is, for example, the Internet, a LAN (Local Area Network), or the like. The data stored in the storage unit 106 may be stored in the server 200, for example.

An input device 112 and an output device 114 are connected to the input / output interface unit 108. As the output device 114, a speaker or a printer can be used in addition to a monitor (including a home television). In addition to the keyboard, mouse, and microphone, the input device 112 can use a monitor that realizes a pointing device function in cooperation with the mouse. In the following, the output device 114 may be referred to as a monitor 114, and the input device 112 may be referred to as a keyboard 112 or a mouse 112.

Various databases, tables, files, and the like are stored in the storage unit 106. In the storage unit 106, a computer program for giving an instruction to a CPU (Central Processing Unit) in cooperation with an OS (Operating System) to perform various processes is recorded. As the storage unit 106, for example, a memory device such as a RAM (Random Access Memory) / ROM (Read Only Memory), a fixed disk device such as a hard disk, a flexible disk, an optical disk, or the like can be used.

In the present embodiment, the storage unit 106 stores the OCR reading candidate list setting master 106a, the business partner master 106c, the OCR layout master 106b, the name identification mapping master 106d, and the like.

FIG. 2 is a diagram showing an example of the data configuration of the OCR reading candidate list setting master stored in the form processing apparatus according to the present embodiment. As shown in FIG. 2, the OCR reading candidate list setting master 106a (an example of reading candidate list data) has an ID (hereinafter referred to as a screen ID) of a reading area for executing character recognition processing by OCR in the reading area of a form. , The EQ, which is the order of the target columns expected to be described in the reading area, the target table for storing the target columns, and the name of the target columns are stored in association with each other.

FIG. 3 is a diagram showing an example of a data structure of a business partner master stored in the form processing device according to the present embodiment. As shown in FIG. 3, the business partner master 106c is an example of a master (target table) under the control of a business system, and includes a business partner CD which is a business partner code and a target column (an example of text data). , Are associated and stored.

FIG. 4 is a diagram showing an example of the data structure of the OCR layout master stored in the form processing apparatus according to the present embodiment. As shown in FIG. 4, the OCR layout master 106b is an example of reading candidate list data that stores a target column that is expected to be described in the reading area of a form for each reading area, and includes a screen ID, a SEQ, and a screen ID. An area name that is the name of the reading area, a reading candidate list setting master used FLG that indicates whether or not to set a reading candidate list (for example, an assumed alphabet or number) for the reading area, and the reading candidate list. The reading candidate list ID, which is the ID of the above, and the reading candidate list set for the reading area are stored in association with each other.

FIG. 5 is a diagram showing an example of the data structure of the name identification master stored in the form processing apparatus according to the present embodiment. As shown in FIG. 5, the name identification mapping master 106d has a screen ID, a SEQ, a master table name which is a name of a target table to be referred to when executing OCR, a business partner CD of a business partner, and execution of OCR. The master column names 1 and 2 which are the names of the target columns referred to in the above, the transaction table name which is the name of the text data table read by OCR, and the transaction column name 1 which is the name of the text data read by OCR. , 2 and are stored in association with each other.

Returning to FIG. 1, the control unit 102 is a CPU or the like that collectively controls the form processing device 100. The control unit 102 has an internal memory for storing a control program such as an OS, a program that defines various processing procedures, required data, and the like, and performs various information processing based on these stored programs. Execute.

The control unit 102 is functionally conceptually provided with a setting unit 102a, a reading unit 102b, a name identification unit 102c, and the like.

The setting unit 102a displays the reading candidate list set in the customer master 106c specified via the OCR reading candidate list setting master 106a, which is associated with the reading area of the form, for the OCR layout master 106b. This is an example of a setting unit that is set for each reading area. Thereby, the reading candidate list can be set for the OCR layout master 106b by using the target column set in the target table such as the business partner master 106c registered in the business system. As a result, the optimum reading candidate list for each customer can be set in the OCR layout master 106b. Further, since the erroneous recognition of characters by the character recognition processing of the form using OCR is reduced, it is possible to reduce the cost required for correcting the erroneously recognized characters by the character recognition processing of the form using OCR.

However, if it is known in advance that the characters read by the reading unit 102b, which will be described later, are numbers and specific characters, such as a telephone number, the input device 112 manually inputs the characters to the OCR layout master 106b. It is possible to set the reading candidate list, and it is not always necessary to set the reading candidate list for the OCR layout master 106b by using the OCR reading candidate list setting master 106a.

The reading unit 102b executes character recognition processing (OCR) with reference to the OCR layout master 106b after the setting unit 102a has set the reading candidate list based on the image data of the form read by a multifunction device or the like (not shown). This is an example of a reading unit that reads text data for each reading area.

The name identification unit 102c is an example of a name identification unit that acquires a reading candidate list set in the business partner master, which is similar to the text data read by the reading unit 102b, for each reading area of the form. As a result, even if a character is erroneously recognized by the character recognition process by the reading unit 102b, a list of reading candidates such as names registered in the business system similar to the text data of the character erroneously recognized by the name identification process. Can be obtained. As a result, it is possible to reduce the cost required for correcting the erroneously recognized characters by the character recognition process of the form using OCR.

FIG. 6 is a flowchart showing an example of the flow of character recognition processing of a form in the form processing apparatus according to the present embodiment. Next, an example of the flow of the character recognition processing of the form in the form processing apparatus 100 according to the present embodiment will be described with reference to FIG.

First, the setting unit 102a sets a reading candidate list associated with each reading area of the form in the business partner master 106c for each reading area in the OCR layout master 106b (step S601).

FIG. 7 is a diagram for explaining an example of a reading candidate list setting process for the OCR layout master in the form processing device according to the present embodiment. For example, as shown in FIG. 7, the setting unit 102a associates the OCR layout master 106b with the screen ID, SEQ, and area name for each reading area of the form, and coordinates information and reading of the reading area. Set the candidate list.

Returning to FIG. 6, next, the form is read by a multifunction device or the like (not shown), and the image data of the form is generated (step S602). FIG. 8 is a diagram showing an example of image data generated by the multifunction device. As shown in FIG. 8, the multifunction device reads the form and generates image data of the form.

The reading unit 102b refers to the OCR layout master 106b after the reading candidate list is set by the setting unit 102a, executes character recognition processing on the image data of the form (step S603), and recognizes the characters by the character recognition processing. Is converted into text data (step S604).

FIG. 9 is a diagram for explaining an example of character recognition processing in the form processing apparatus according to the present embodiment. FIG. 10 is a diagram for explaining an example of conversion processing into text data in the form processing apparatus according to the present embodiment. For example, the reading unit 102b executes character recognition processing on the image data shown in FIG. 8 according to the coordinate information of the reading area (Consignee name) associated with the screen ID: 1 and the reading candidate list in the OCR layout master 106b. Then, the characters shown in FIG. 9 are read. Further, as shown in FIG. 10, the reading unit 102b converts the read characters into text data (for example, "KINOSHITA TRADING GOMPANY").

Returning to FIG. 6, next, the name identification unit 102c executes a name identification process for acquiring a reading candidate list similar to the text data converted by the reading unit 102b from the reading candidate list set in the business partner master 106c. (Step S605).

FIG. 11 is a diagram for explaining an example of name identification processing in the form processing apparatus according to the present embodiment. For example, the name identification unit 102c executes name identification processing on text data having an error as shown in FIG. 10 (for example, "KINOSHITA TRADING GOMPANY"). Specifically, since the area name: Consignee name represents a business partner, the name identification unit 102c, as shown in FIG. 11, is referred to from the business partner master 106c as a reading candidate list similar to the text data shown in FIG. Acquire the English customer official name 1: "KINOSHITA TRADING COMPANY" associated with the customer CD: 11001000.

Next, an example of the reading candidate list setting process in the form processing device 100 according to the present embodiment will be described with reference to FIG. 12. FIG. 12 is a diagram for explaining an example of a reading candidate list setting process in the form processing device according to the present embodiment.

First, the setting unit 102a is associated with the screen ID of the reading area for executing the character recognition processing in the reading area of the form for executing the setting (automatic addition) processing of the reading candidate list in the OCR reading candidate list setting master 106a. Identify the target table (eg, Account Master 106c) and target columns (eg, English Account Official Name 1 and English Account Address 1). Next, in the specified customer master 106c, the setting unit 102a has an English business partner official name 1 (for example, "KINOSHITA TRADING COMPANY", "KINOSHITA TRADING COMPANY TK") and English associated with the business partner CD of the business partner. Select the business partner address 1 (for example, "8-8-2, MAMIZUKA,", "1-8-2, HARUMI, CHUO-KU, TOKYO JAPAN"). Then, as shown in FIG. 12, the setting unit 102a sets the selected English business partner official name 1 and English business partner address 1 to the reading candidate list associated with the screen ID: 1 in the OCR layout master 106b. Set (add).

Next, an example of name identification processing by the form processing device 100 according to the present embodiment will be described.

First, in the name identification mapping master 106d, the name identification unit 102c uses the master table name, the master column CD, and the master column names 1 and 2 associated with the screen ID of the reading area for executing the name identification process, and the business partner master 106c. Select English business partner name 1 and English business partner address 1 as master data from. Further, the name identification unit 102c uses the transaction table name associated with the screen ID and the transaction column names 1 and 2 in the name identification master to read OCR acceptance data (that is, characters read by character recognition by the reading unit 102b). From the text data), select the English business partner name 1 and the English business partner address 1 as the text data for executing the name identification process.

Next, the name identification unit 102c has master column names 1 and 2 (English business partner name 1 and English business partner address 1) selected from the business partner master 106c and transaction column names 1 and 2 (English) selected from the OCR acceptance data. Compare with the business partner name 1 and the English business partner address 1). Further, the name identification unit 102c uses, for example, the Levenshtein distance or the like to select the master column names 1 and 2 from the business partner master 106c, and the master column names 1 and 2 most similar to the transaction column names 1 and 2. Identify the master column CD (ie, the trading partner CD) associated with. Then, the name identification unit 102c acquires the English business partner name 1 and the English business partner address 1 associated with the specified master column CD from the business partner master 106c.

As described above, according to the form processing device 100 according to the present embodiment, even if a character is erroneously recognized by the character recognition process by the reading unit 102b, it is similar to the text data of the character erroneously recognized by the name identification process. It is possible to acquire a list of reading candidates such as names registered in the business system. As a result, it is possible to reduce the cost required for correcting the erroneously recognized characters by the character recognition process of the form using OCR.

In addition to the above-described embodiments, the present invention may be implemented in various different embodiments within the scope of the technical ideas described in the claims.

For example, of each of the processes described in the embodiments, all or part of the processes described as being automatically performed may be manually performed, or all of the processes described as being performed manually. Alternatively, a part can be automatically performed by a known method.

In addition, processing procedures, control procedures, specific names, information including parameters such as registration data and search conditions for each processing, screen examples, and database configurations shown in this specification and drawings are not specified unless otherwise specified. Can be changed arbitrarily.

Further, with respect to the form processing device 100, each component shown in the figure is a functional concept and does not necessarily have to be physically configured as shown in the figure.

For example, with respect to the processing functions included in the form processing device 100, particularly each processing function performed by the control unit, even if all or any part thereof is realized by the CPU and a program interpreted and executed by the CPU. Well, it may be realized as hardware by wired logic. The program is recorded on a non-temporary computer-readable recording medium including a programmed instruction for causing the information processing apparatus to execute the processing described in the present embodiment, and the form processing apparatus is required. Read mechanically to 100. That is, a computer program for giving instructions to the CPU in cooperation with the OS and performing various processes is recorded in a storage unit such as a ROM or an HDD (Hard Disk Drive). This computer program is executed by being loaded into RAM, and cooperates with the CPU to form a control unit.

Further, this computer program may be stored in an application program server connected to the form processing device 100 via an arbitrary network, and all or part of the computer program may be downloaded as needed. be.

Further, the program for executing the process described in the present embodiment may be stored in a non-temporary computer-readable recording medium, or may be configured as a program product. Here, the "recording medium" includes a memory card, a USB (Universal Serial Bus) memory, an SD (Secure Digital) card, a flexible disk, a magneto-optical disk, a ROM, an EPROM (Erasable Programmable Read Only Memory), and an EEPROM (registration). Trademarks) (Electrically Erasable and Probe Read Only Memory), CD-ROM (Compact Disk Read Only Memory), MO (Magnet-Optical Disc), MO (Magnet-Optical Disc), DVD (Digital), DVD (Digital) It shall include any "portable physical medium".

Further, the "program" is a data processing method described in any language or description method, regardless of the format such as source code or binary code. The "program" is not necessarily limited to a single program, but is distributed as multiple modules or libraries, or cooperates with a separate program represented by the OS to achieve its function. Including things. It should be noted that well-known configurations and procedures can be used for specific configurations and reading procedures for reading the recording medium in each apparatus shown in the embodiment, installation procedures after reading, and the like.

Various databases and the like stored in the storage unit are memory devices such as RAM and ROM, fixed disk devices such as hard disks, flexible disks, and storage means such as optical disks, and are used for various processes and website provision. Stores programs, tables, databases, files for web pages, etc.

Further, the form processing device 100 may be configured as an information processing device such as a known personal computer or workstation, or may be configured as the information processing device to which an arbitrary peripheral device is connected. Further, the form processing device 100 may be realized by mounting software (including a program or data) that realizes the processing described in the present embodiment on the device.

Furthermore, the specific form of distribution / integration of the device is not limited to that shown in the figure, and all or part of the device may be functionally or physically in any unit according to various additions or functional loads. It can be distributed and integrated. That is, the above-described embodiments may be arbitrarily combined and implemented, or the embodiments may be selectively implemented.

The present invention is particularly useful in the logistics industry.

100 Forms processing device 102 Control unit
102a setting unit
102b reader
102c Name identification unit 104 Communication interface unit 106 Storage unit
106a OCR reading candidate list setting master
106b OCR layout master
106c Account Master
106d Name identification mapping master 108 Input / output interface unit 112 Input device 114 Output device 200 Server 300 Network

Claims (3)

It is a form processing device equipped with a control unit.
The control unit
For the reading candidate list data for holding the text data expected to be described in the reading area of the form for each reading area, it is set in the master under the control of the business system associated with the reading area. Setting means for setting text data for each reading area,
Based on the image data of the form, the reading means for reading the text data for each reading area by executing the character recognition process accompanied by the reference of the reading candidate list data after the setting by the setting means.
For each reading area, a name identification means for acquiring text data set in the master, which is similar to the text data read by the reading means, and
To prepare for
A form processing device characterized by. To be executed by the control unit of a form processing device including a control unit,
For the reading candidate list data for holding the text data expected to be described in the reading area of the form for each reading area, it is set in the master under the control of the business system associated with the reading area. Setting steps to set text data for each reading area,
Based on the image data of the form, the reading step of reading the text data for each reading area by executing the character recognition process accompanied by the reference of the reading candidate list data after the setting by the setting step.
For each reading area, a name identification step for acquiring text data set in the master, which is similar to the text data read in the reading step, and
A form processing program that includes. The control unit of the form processing device including the control unit executes the operation.
For the reading candidate list data for holding the text data expected to be described in the reading area of the form for each reading area, it is set in the master under the control of the business system associated with the reading area. Setting steps to set text data for each reading area,
Based on the image data of the form, the reading step of reading the text data for each reading area by executing the character recognition process accompanied by the reference of the reading candidate list data after the setting by the setting step.
For each reading area, a name identification step for acquiring text data set in the master, which is similar to the text data read in the reading step, and
Form processing method including.

Images