JP7432568B2 - Information processing device, information processing method, and program - Google Patents

Description

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

When a paper document such as an invoice is sent from a supplier, the delivery destination receives the paper document, visually confirms the contents of the paper document, and checks the delivery destination's core information. Create data for input into the system. If there is anything unclear about the paper document, we will contact you, and if there is a mistake, we will correct the data to be input into the core system mentioned above.
After inputting the paper document data, the management department at the delivery destination outputs, for example, a payment guide from the core system. Thereafter, payment instructions are promptly provided to the supplier.

The work of creating data to be input into a core system from the contents of paper documents requires a large amount of labor costs. Therefore, in Patent Document 1 listed below, characters included in an image are converted into text data using optical character recognition to create the above-mentioned data.

Japanese Patent Application Publication No. 10-97606

In the above-mentioned conventional technology, characters included in an image are converted into text data using optical character recognition, but character recognition is not always performed accurately, and erroneously recognized characters may , it was necessary to manually correct each item one by one.
In addition, to check whether a misrecognition has occurred, for example, check the paper document by comparing it with the above-mentioned payment guide, or check by checking the paper document in one hand while looking at the screen of the above-mentioned core system. This work was being done.

The present invention has been made in view of the above situation, and an object of the present invention is to provide an information processing device, an information processing method, and a program that can improve the efficiency of correction work for character recognition results. .

To achieve the above object, an information processing device according to one embodiment of the present invention includes:
An information processing device that enables an operator to modify character text generated by converting at least one image character included in an image using optical character recognition, the information processing device comprising:
a first display means for displaying the image character and the character text in a comparatively visible state on a display unit;
When the operator determines that the character text displayed on the display unit requires the correction, the operator receives the necessary correction from the input unit and replaces the character text with the corrected character text. A first modification means;
Equipped with.

Further, an information processing method according to one embodiment of the present invention is a method corresponding to the above-described information processing apparatus according to one embodiment of the present invention.

Further, a program according to one embodiment of the present invention is a program corresponding to the above-described information processing apparatus according to one embodiment of the present invention.

According to the present invention, it is possible to improve the efficiency of correction work for character recognition results.

FIG. 2 is a diagram showing an overview of this service provided by the information processing device of the present invention in the information processing system. FIG. 2 is a diagram illustrating an example of displaying image characters and character text on a display unit in the information processing apparatus of FIG. 1 and then modifying the image characters. FIG. 1 is a block diagram showing an example of a system configuration regarding an information processing system. FIG. 4 is a block diagram showing the hardware configuration of the information processing device shown in FIG. 3. FIG. 4 is a functional block diagram showing an example of the functional configuration of the information processing device in FIG. 3. FIG. 4 is a flowchart illustrating an example of a processing operation of the information processing apparatus of FIG. 3. FIG. It is a figure showing an example of the state where image characters and character text are displayed on a display part. FIG. 8 is a diagram illustrating an example when trying to make a correction from the state shown in FIG. 7; 9 is a diagram illustrating an example when trying to make a correction from the state shown in FIG. 7 or 8. FIG. FIG. 9 is a diagram showing an example of a case where correction is attempted from any one of the states of FIGS. 7 to 9. FIG. FIG. 6 is a diagram illustrating an example of a state in which data correction candidates for assisting correction are displayed on the display unit.

<About the overview of this service>
FIG. 1 is a diagram showing an overview of this service provided by an information processing device 1 of the present invention in an information processing system.

In FIG. 1, the purpose of this service is to provide an environment in which it is easier to appropriately correct character recognition results during character recognition using an information processing device 1. In other words, the purpose is to provide an environment in which the operator 2 can efficiently modify character recognition results during character recognition using the information processing device 1.

In the present embodiment shown in FIG. 1, an example will be described in which a supplier 7 sends an invoice to a delivery destination (numerals omitted) (the invoice is just one example). Although only one supplier 7 is shown in the figure, there are actually a plurality of suppliers 7. Regarding such a plurality of suppliers 7, it is assumed that the delivery destination (reference numeral omitted) manages and identifies each of them using, for example, an ID or the like.

The supplier 7 in FIG. 1 has, for example, an information processing system 4 that is its own core system. The information processing system 4 on the side of the supplier 7 creates an invoice for the delivery destination. The invoice is different for each supplier 7, and is created in one of three patterns as shown in (1) to (3) in FIG. 1, for example, and sent to the supplier side.

The first pattern (1) on the supplier 7 side is to send the invoice file and data together. Note that the file in (1) refers to an electronic file in which information is fixed in a form that can be printed like paper, and the fixed information can be exchanged. In other words, it refers to an electronic file that replaces paper (so-called PDF, etc.). Furthermore, the data in (1) is, for example, text data extracted from the file in (1).

The second pattern (2) is for sending only the above-mentioned files. The third pattern (3) is for sending a paper document. The paper document here is a printed version of the original bill. The printed original will be mailed to the delivery address.

In this embodiment, the files and data in (1) are transmitted to the data conversion system 5 via a predetermined network N (see FIG. 3). Further, the file (2) is also sent to the data conversion system 5. On the other hand, the original in (3) is sent directly to the delivery destination without being sent to the data conversion system 5.

The data conversion system 5 is, for example, a system that is constructed separately from the information processing device 1 that provides this service, and is capable of providing at least a service that automatically creates forms. The data conversion system 5 creates form data (form file) that can be used in the information processing system 3 of the delivery destination. Although a detailed explanation will be omitted, in the case of (1) above, for example, form data is created together with data in which text data is separated by commas (so-called CSV). In the case of (2) above, for example, the data conversion device 6 is used to create form data (form file) and other data (other files). In the case of (2) as well, the data conversion device 6 is used to create data in which text data is separated by commas as in the case of (1).

Note that the data of the form created by the data conversion system 5 is transmitted to a BPO center (BPO: Business Process Outsourcing) of the delivery destination, and is imported into the information processing device 1. Although the installation of a BPO center is optional, in this embodiment, since there are many suppliers 7, a BPO center is installed in order to improve efficiency at the delivery destination.
If a BPO center is not installed, the information processing device 1 is, for example, one component of the information processing system 3 at the delivery destination.

The data conversion device 6 includes, for example, a scanner, an OCR device (OCR: Optical Character Recognition), an image storage section, a text storage section, and the like. A scanner is an optical reading device that optically reads a paper medium original such as a document and converts it into image data. An OCR device generates text data by recognizing characters included in an image generated by a scanner and converting the characters as an image (image characters) into character codes (character text). The data conversion device 6 having such a configuration is capable of outputting image characters (characters as images) included in an image and character text (character code) generated by converting the image characters. Has a function.
The data conversion device 6 is configured to be able to create form data using character text.

In this embodiment, the data converting device 6 is also provided at the BPO center of the delivery destination in order to cope with the case (3). The original invoice mailed to the delivery destination is converted into image characters or text by the scanner or OCR device of the data conversion device 6. In addition, form data is also created. Note that the data conversion device 6 does not necessarily recognize characters accurately, and it becomes necessary to check and correct characters that are erroneously recognized. Therefore, the information processing device 1 is configured so that the above-mentioned confirmation and correction can be performed efficiently (so that the purpose of the above-mentioned service can be realized).

In addition to the above-mentioned BPO center, the supplier also has an organization such as a management department. This management section has an information processing system 3 which is a core system. In the information processing system 3 managed by the management department, a payment guide, for example, is automatically created and output based on data output from the information processing device 1 of the BPO center. Thereafter, the management department carries out payment guidance procedures. Note that data matching is performed between the information processing system 3 and the information processing device 1 as appropriate.

The information processing device 1 is configured to allow the operator 2 to correct any characters that have been erroneously recognized based on the operator's judgment.

For example, content as shown in FIG. 2 is displayed on the display screen 16a of the display unit 16 (see FIG. 4) of the information processing device 1.
FIG. 2 is a diagram illustrating an example of displaying image characters and character text on the display unit 16 (display screen 16a) in the information processing device 1 of FIG. 1 and then modifying the image characters and text.

In FIG. 2, the display screen 16a is provided with a first display area 16b and a second display area 16c. In the first display area 16b, image characters and character texts are displayed vertically arranged. The display screen 16a is displayed in such a manner that the operator 2 can check whether or not there are any erroneously recognized characters, and if there are any erroneously recognized characters, the operator 2 can correct them. On the other hand, in the second display area 16c, a part of the form F created including the character text in the first display area 16b is displayed.
Note that, although a detailed explanation will be omitted, it is also possible to display the contents of the first display area 16b on a full screen, or to display the form F on a second display area 16c on a full screen.

First, the display contents of the first display area 16b will be explained.
In the first display area 16b, for example, data that has been converted into data by the scanner or OCR device of the data conversion device 6 and transmitted to the information processing device 1 is displayed.

In FIG. 2, for example, an example is shown in which the item "field name" is input in the item filter setting field 16d. In this example, items related to the field names of form F are displayed in the first display area 16b. Specifically, items related to the field name are displayed in a plurality of vertically arranged item columns 16e. For example, the item "Issuance date" is displayed as a field name in the top item column 16e. Below this, the item "Claim Number" is displayed. Also, below this, "Billing Name", "Billing Address", "Billing Telephone Number", "Total", "Product Name", "Details Number", "Billing Product Number", "Quantity" , "unit price" items are displayed in order. It is assumed that these items are displayed with reference to a dictionary used for form recognition (this is an example). It is assumed that the above-mentioned input is performed using the input unit 17 used by the operator 2.

An image character field 16f and a text character field 16g are provided to the right of the plurality of item fields 16e. The image character field 16f and the text character field 16g are arranged vertically so that they can be compared. The image character field 16f and the text character field 16g are arranged in such a way that the image characters (described later) displayed in the image character field 16f and the text characters displayed in the text character field 16g can be visually recognized at a glance. be done.

The image character column 16f is provided for displaying image characters included in the image (provided for displaying the image). Further, the text character column 16g is provided to display the character text generated by converting the image characters (provided to display the value corresponding to the image).

“2021/04/15” is displayed in the form of image characters in the image character field 16f located to the right of the field name “Date of Issue” in the top item field 16e. In addition, “2021/04/15” is displayed in the text character field 16g in the form of text characters.

"1000476" is displayed as an image character in the image character field 16f located to the right of the field name "call number" in the item field 16e. Further, "1000476" is displayed in the text character column 16g as text characters.

In the image character field 16f to the right of the field name "Billing party name" in the item field 16e, "XXXX Solution Co., Ltd." is displayed in the form of image characters. In addition, in the text character field 16g, "XXXX Solution Co., Ltd." is displayed as text characters. ).

In addition, the image characters to the right of "Billing Address", "Billing Phone Number", "Total", "Product Name", "Details Number", "Billing Product Number", "Quantity", and "Unit Price" Descriptions regarding the image characters in the field 16f and the text characters in the text character field 16g will be omitted here.

A check box 16h is provided to the right of the image character field 16f and the text character field 16g. This check box 16h is provided to check whether the item is "confirmed" or not. The checkbox 16h is provided in the form of a small square.

The image character field 16f is displayed in color based on the accuracy of optical character recognition. Accuracy is based on the degree to which text with the same content has been modified in the past, for example, in the position corresponding to the field name "Billing Address" or in the position corresponding to "Billing Phone Number". This is a calculated index. The accuracy is set such that the greater the number of corrections, the smaller the value, and conversely, the smaller the number of corrections, the larger the accuracy value. An example of calculation is to calculate the reciprocal of the ratio of the number of times corrections have been made as the accuracy, using the number of character texts stored in the storage unit 18 so far as a parameter.

In this embodiment, if the text belongs to a category with high accuracy, the image text field 16f is displayed in a blue color. Furthermore, if the accuracy belongs to the medium classification, the image character field 16f is displayed in a yellowish color. Furthermore, if the text belongs to a category with low accuracy, the image text field 16f is displayed in a reddish color.

For example, in this embodiment, the image text field 16f at the position corresponding to the field name "Billing Address" is displayed in red (the number of corrections is large). Further, the image character column 16f at the position corresponding to the field name "Billing Telephone Number" is displayed in blue (because it is a number, the characters are easy to recognize and the number of corrections is small). In addition, the image text field 16f at the position corresponding to the field name "Billing Product Number" is displayed in purple (reddish-purple) (the number of corrections has been relatively large).

As described above, since the image character field 16f is displayed in color depending on the accuracy, the operator 2 compares the image characters in the image character field 16f and the text characters in the text character field 16g, paying attention to the color display. You can check by doing so. Note that since the image character field 16f and the text character field 16g are arranged vertically, it is very easy to compare the image characters and the text characters (the arrangement is just an example; for example, the left and right arrangement is ).

Regarding the display of accuracy in color, in this embodiment, if the checkbox (code omitted) on the left side of the accuracy display mark 16i is unchecked, the accuracy is displayed in the same white color as the text character field 16g, for example. Note that between the check box and the accuracy display mark 16i, "Display accuracy in color" is displayed (this display is an example).

In FIG. 2, the value in the text field 16g for the field name "Product Name" is being corrected (corrected at the position of the cursor C), and at this time, the "Product Name" in the form F in the second display area 16c is A certain item column 16j is displayed in an enlarged manner. The item field 16j corresponding to the value being modified is displayed as a highlight HL1. In this embodiment, it is possible not only to make corrections in the text character field 16g, but also to make corrections (value corrections) in the item field 16j displayed in the highlight HL1.

The operator 2 can modify the value in the text character field 16g and the value in the item field 16j using an input section 17, which will be described later. Corrections are made by inputting replacement of character text with corrected character text.

As mentioned above, the outline of this service has been explained with reference to FIGS. 1 and 2. Since this service uses the information processing device 1, the operator 2 can correct the character recognition results during character recognition. It can be done efficiently.

<About the system configuration of the information processing system>
FIG. 3 is a block diagram showing an example of a system configuration regarding the overall information processing system.

The information processing system is connected to a predetermined network N such as the Internet. This network N includes an information processing system 4 on the supplier 7 side (see FIG. 1), a data processing system 5 interposed between the information processing system 4 on the supplier 7 side and the information processing device 1, and The information processing system 3 on the destination side is also connected. A data conversion device 6 including a scanner, an OCR device, etc. is connected to the information processing device 1 . Although not shown in FIG. 3, the data conversion device 6 is also provided in the data conversion system 5.

<About the hardware configuration of the information processing device 1>
FIG. 4 is a block diagram showing the hardware configuration of the information processing device 1 in the overall information processing system of FIG. 3. As shown in FIG.

The information processing device 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input/output interface 15, and a display unit 16 (output unit). , an input section 17 , a storage section 18 , a communication section 19 , and a drive 20 .

The CPU 11 executes various processes according to programs recorded in the ROM 12 or programs loaded into the RAM 13 from the storage section 18 .
The RAM 13 also appropriately stores data necessary for the CPU 11 to execute various processes.

The CPU 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input/output interface 15 is connected to this bus 14 .
A display section 16 (output section), an input section 17, a storage section 18, a communication section 19, and a drive 20 are connected to the input/output interface 15.

The display unit 16 (output unit) is constituted by a display (screen; in this specification, this screen is referred to as display screen 16a), and displays various images. The input unit 17 is comprised of various hardware such as a mouse and a keyboard, and inputs various information.
The storage unit 18 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), etc., and stores various data.
The communication unit 19 controls communication with other devices (in the case of FIG. 3, the data processing system 5 and the information processing system 3 on the delivery destination side) via a predetermined network N.

The drive 20 is provided as necessary. A removable medium 21 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately installed in the drive 20.
The program read from the removable medium 21 by the drive 20 is installed in the storage unit 18 as necessary. Further, the removable medium 21 can also store various data stored in the storage section 18 in the same manner as the storage section 18.

Regarding the information processing device 1 as described above, it is assumed that various processes described below are realized through cooperation between various hardware and various software.

Note that the information processing device 1 is, for example, a personal computer (PC) or a mobile terminal such as a tablet. In the case of a personal computer (PC), it may be either a so-called desktop computer or a notebook computer.

<About the functional configuration of the information processing device 1>
FIG. 5 is a functional block diagram showing an example of the functional configuration of the information processing device 1 of FIG. 3. As shown in FIG.

In FIG. 5, the information processing device 1 includes the CPU 11, the display section 16, the input section 17, the storage section 18, the communication section 19, and other functions (as described above with reference to FIG. 5). (not shown).

The CPU 11 includes an item data/character data processing section 111, a display processing section 112, a correction processing section 113, an accuracy calculation processing section 114, and a form data processing section 115. In other words, when the CPU 11 of the information processing device 1 operates, it processes the item data/character data processing section 111, the display processing section 112, the correction processing section 113, and the accuracy calculation processing section 114. , and the form data processing unit 115 function.

Among these configurations, the display processing section 112 includes a first display processing section 112a (first display means), a second display processing section 112b (second display means), and a third display processing section 112c (third display means). ). Further, the correction processing section 113 includes a first correction processing section 113a (first correction means) and a second correction processing section 113b (second correction means).

The storage unit 18 includes an item data/character data storage unit 181, a data correction candidate storage unit 182, an accuracy data storage unit 183, and a form data storage unit 184.

The item data/character data processing unit 111 of the CPU 11 executes various processes according to the items input in the item filter setting field 16d. For example, the item data/character data processing unit 111 performs processing related to providing data necessary for the display processing unit 112 to perform a predetermined display, and performs the above-mentioned processing for the item data/character data storage unit 181 of the storage unit 18. Executes processing such as storing the items.

In addition to the above, the item data/character data processing section 111 also executes processing for storing image characters and character texts created by the data conversion device 6 in the item data/character data storage section 181 of the storage section 18 . Note that the image characters and character texts are stored so as to be linked to the data of the form F stored in the form data storage section 184.

The first display processing section 112a of the display processing section 112 executes a process of displaying the image characters and text created by the data converting device 6 on the display section 16 (display screen 16a) in a visually comparable state. Specifically, a process is executed in which image characters are displayed in the image character field 16f and text characters are respectively displayed in the text character field 16g so as to be arranged vertically.

The first display processing unit 112a executes a process of displaying image characters and text in accordance with the specified item (in accordance with the item input in the item filter setting field 16d). The first display processing unit 112a also performs a process of displaying the image characters in a display state based on the accuracy obtained by the accuracy calculation processing unit 114 (for example, color-coded in blue, red, and yellow). Execute.

When the character text displayed on the display unit 16 (display screen 16a) needs to be corrected, the second display processing unit 112b provides a data correction candidate 16l (see FIG. 11) for assisting in the necessary correction. (described later) on the display screen 16a. Note that the correction processing unit 113 functions to correct the character text using the data correction candidate 16l.

The third display processing section 112c executes a process of displaying the form F on the display section 16 (display screen 16a). Specifically, when the operator 2 places the pointer P on the character text displayed in the first display area 16b and clicks the mouse button (designates the character text), the character text is included. A process of displaying the form F at the location in the second display area 16c is executed. In addition to the above, the third display processing unit 112c also performs highlight display processing (highlight HL1, highlight HL2).

In addition to the above-described processing of the first display processing section 112a to the third display processing section 112c, the display processing section 112 displays the first display area 16b in full screen, or displays the form F in the second display area 16c, for example. It also performs processing such as full screen display. The display processing unit 112 also executes display processing of checking or unchecking the small square checkbox 16h in the first display area 16b. The display processing unit 112 executes various processes related to display.

The first correction processing unit 113a of the correction processing unit 113 performs an operation to determine that a misrecognition has occurred in the character text displayed on the display unit 16 (display screen 16a) and that the portion (character) where the misrecognition has occurred needs to be corrected. When the operator 2 makes a judgment, the necessary correction is received from the input unit 17 and a process of replacing the character text with the corrected character text is executed. Note that the replacement of the character text with the corrected character text is performed not only on the display screen 16a but also in the item data/character data storage section 181 and the form data storage section 184 of the storage section 18. .

In addition to the above, the first correction processing unit 113a also executes processing for accepting necessary corrections based on selected data correction candidates selected from the data correction candidates 16l (described later with reference to FIG. 11).

When the operator 2 determines that the character text specified in the form F is to be corrected, the second correction processing unit 113b receives the necessary correction from the input unit 17 and converts the specified character text into corrected characters. Executes the process of replacing it with text. Note that designation here means, for example, pointing the pointer P and clicking a mouse button to designate a character text. The replacement of the specified character text with the corrected character text is performed not only on the display screen 16a but also in the item data/character data storage section 181 and the form data storage section 184 of the storage section 18. .

The modification processing section 113, which includes the first modification processing section 113a and the second modification processing section 113b, executes various processing related to modification.

The accuracy calculation processing unit 114 executes processing for calculating accuracy used when displaying in color by the first display processing unit 112a. Alternatively, the first display processing unit 112a executes processing that allows the first display processing unit 112a to utilize the preset accuracy. As described above, the accuracy is an index calculated based on the extent to which text with the same content has been modified in the past. The accuracy is set such that the greater the number of corrections, the smaller the value, and conversely, the smaller the number of corrections, the larger the accuracy value.

Note that the accuracy calculation processing section 114 may be included in the functional block of the first display processing section 112a, instead of being a functional block as shown in FIG.

The form data processing unit 115 executes various processes regarding the data of the form F created by the data conversion device 6. For example, the form data processing unit 115 executes processing such as storing the data of the form F in the form data storage unit 184 of the storage unit 18.

The item data/character data storage unit 181 of the storage unit 18 is provided as a storage area for storing the above-mentioned items, image characters, character texts, etc. created by the data conversion device 6.

The data modification candidate storage unit 182 is provided as a storage area for storing data regarding the data modification candidates 16l (described later with reference to FIG. 11).
The accuracy data storage unit 183 is provided as a storage area for storing data regarding accuracy.
The form data storage unit 184 is provided as a storage area for storing the data of the form F created by the data conversion device 6.

<About the processing operation of the information processing device 1>
FIG. 6 is a flowchart illustrating an example of the processing operation of the information processing device 1 of FIG. 3 (an example related to the correction work of character recognition results).

As the operation of the information processing device 1, in step S1, image characters are accurately placed in the image character field 16f so that they are aligned vertically according to the specified item (according to the item input in the item filter setting field 16d). text characters are displayed in the text character field 16g. When the display of image characters and character text is completed, the process moves to step S2.

In step S2, a check mark is placed in each check box 16h, and it is determined whether "all have been confirmed" or not. That is, when the operator 2 compares the image characters and text characters displayed vertically and determines that there is no misrecognition, or after the operator 2 has made the necessary corrections when there is a misrecognition. , put a check mark in the check box 16h to determine whether it is marked as "confirmed" or not. If it is determined that "everything has been confirmed" (Yes in step S2), the operation ends; if it is determined that there is a checkbox 16h with no check mark (No in step S2), the process proceeds to step S3. do.

In step S3, since there is a check box 16h without a check mark, the operator 2 is asked to determine whether or not correction is necessary. There are various ways to make this determination, but one example is to display a popup to the operator 2 asking whether or not correction is necessary (not shown). If no correction is necessary based on the input by the operator 2 (No in step S3), the process moves to step S4, for example. On the other hand, if correction is required based on the input by the operator 2 (Yes in step S3), the process moves to step S5.

In step S4, a check mark is placed in the check box 16h to make it "all confirmed", and the process moves to step S2. The operation then ends by moving to step S2.

In step S5, the character text of the item requiring correction is corrected, and the process moves to step S6.

In step S6, a check mark is placed in the check box 16h of the corrected item to make it "confirmed", and the process moves to step S2. By moving to step S2 and repeating the operation, the operation is finally completed.

<About the display example of the display screen 16a>
FIG. 7 is a diagram showing an example of a state in which image characters and character text are displayed on the display unit 16 (display screen 16a).
Further, FIG. 8 is a diagram showing an example of when trying to make a correction from the state shown in FIG. 7, and FIG. 9 is a diagram showing an example when trying to make a correction from the state shown in FIG. 7 or 8. .
Further, FIG. 10 is a diagram illustrating an example of a case where correction is attempted from the state of any one of FIGS. 7 to 9.
Further, FIG. 11 is a diagram showing an example of a state in which data correction candidates 16l for assisting correction are displayed on the display unit 16 (display screen 16a).

In FIG. 7, an example is shown in which the item "field name" is input into the item filter setting column 16d via the input unit 17 (the display is different from the example in FIG. 2). In the first display area 16b, "product name", "amount", and "remarks" are repeatedly displayed in a plurality of vertically arranged item fields 16e. Further, image characters are displayed in the image character field 16f in accordance with the "product name", and text characters are displayed in the text character field 16g. Further, image characters are displayed in the image character field 16f in accordance with the "amount", and text characters are displayed in the text character field 16g. In addition, image characters are displayed in the image character field 16f in accordance with "remarks", and text characters are displayed in the text character field 16g.
Note that since the operator 2 has not yet determined whether or not correction is necessary, it is assumed that there is no check mark in the check box 16h.
Looking at the display colors of the image character field 16f in FIG. 7, it can be seen that not all of the display colors are highly accurate.

When you move the pointer P to "Product Name" in the item field 16e or to the text field 16g on the right side and click the mouse button, "Product Name" appears in the second display area 16c, as shown in FIG. The form F of the part related to is displayed. If correction is necessary, it can be done from the text field 16g in the first display area 16b or the highlighted item field 16j (highlight HL1) in the second display area 16c.

In FIG. 9, when the pointer P is aligned with "Amount" in the item field 16e or the text character field 16g on the right side and the mouse button is clicked, the second display area 16c displays a section related to "Amount". Form F is displayed. If correction is necessary, it can be done from the text field 16g in the first display area 16b or the highlighted item field 16k (highlight HL2) in the second display area 16c.

In FIG. 10, an example is shown in which the item "product name" is input to the item filter setting field 16d via the input unit 17. In the first display area 16b, "product name" is repeatedly displayed in a plurality of vertically arranged item fields 16e. Further, image characters are displayed in the image character field 16f in accordance with the "product name", and text characters are displayed in the text character field 16g. It is assumed that a check mark has been placed in the check box 16h in advance in a location that is not displayed in the image character field 16f and the text character field 16g. In the second display area 16c, a portion of the form F related to the "product name" is displayed.

What can be seen from FIG. 10 is that if, for example, "product name" is input into the item filter setting field 16d via the input unit 17, the operator 2 can confirm and modify the "product name". In other words, you can narrow down your search by "product name" and check and make corrections.

Although illustration is omitted, for example, if "Billing address" is input into the item filter setting field 16d via the input section 17, "Billing address" can be displayed, and "Billing address" can be displayed. The operator 2 can confirm and correct the information. Similarly, if the "quantity" is input, the "quantity" can be displayed, and the "quantity" can be confirmed and corrected.

Here, an example will be given using FIG.
In FIG. 10, one document (for example, a bill) is targeted. Assuming that this one document has three pages and "product name" spans each page, if "product name" is entered in the item filter setting field 16d via the input section 17, the three pages will be displayed. It is possible to display the "product name" across products. Then, the operator 2 can perform confirmation and correction all at once.

In addition, although not particularly shown in the figure, for example, if the target is three documents, each of which has three pages, and there is a "product name" across each page, " If the "product name" is input through the input unit 17, the "product name" can be displayed across a total of nine pages of three documents. Then, the operator 2 can perform confirmation and correction all at once.

Regarding the modification in the explanation of FIGS. 7 to 10, for example, data modification candidates 16l as shown in FIG. By performing the correction, it is possible to improve the efficiency of the correction work for the character recognition results.
<About effects>
As described above with reference to FIGS. 3 to 11, according to this service, it is possible to improve the efficiency of correction work. In other words, using the information processing device 1, the operator 2 can efficiently correct the character recognition results during character recognition.

<Summary>
Although one embodiment of the information processing device 1 of the present invention in an information processing system has been described above, the present invention is not limited to the above-described embodiment. Furthermore, the effects described in this embodiment are merely a list of the most preferred effects resulting from the present invention, and the effects of the present invention are not limited to those described in this embodiment.

The hardware configuration shown in FIG. 4 is merely an example for achieving the object of the present invention, and is not particularly limited. Further, the functional configuration shown in FIG. 5 is also merely an example, and is not particularly limited. That is, it is sufficient that the information processing device 1 is equipped with a function that can execute the above-mentioned series of processes as a whole, and what kind of functional blocks are used to realize this function is not particularly limited to the example shown in FIG. 5. shall be taken as a thing.

Further, the location of the functional blocks is not particularly limited to that shown in FIG. 5, and may be any location. For example, it is assumed that the functional blocks of the information processing device 1 may be transferred to the information processing system 3 or the like at the delivery destination as appropriate. Further, one functional block may be configured by a single piece of hardware, a single piece of software, or a combination thereof.

Further, for example, when a series of processes is executed by software, a program constituting the software is installed in a computer or the like from a network or a recording medium. Further, the computer may be a computer built into dedicated hardware.
The computer may be a computer capable of executing various functions by installing various programs, for example, the information processing device 1, or a general-purpose personal computer or a tablet.

Furthermore, for example, a recording medium containing such a program may not only be composed of a removable medium (not shown) that is distributed separately from the main body of the device in order to provide the program to the user, but also a recording medium that is pre-installed in the main body of the device. It may also consist of a recording medium etc. that is provided to the user in a state in which the

Note that in this specification, the step of writing a program to be recorded on a recording medium is not only a process that is performed chronologically in accordance with the order, but also a process that is not necessarily performed chronologically but in parallel or individually. It also includes the processing to be executed. Furthermore, in this specification, the term system refers to an overall device composed of a plurality of devices, a plurality of means, and the like.

A recording medium containing such a program is not only constituted by the removable medium 21 shown in FIG. 4, which is distributed separately from the main body of the device in order to provide the program to the user, but also can be used by being pre-installed in the main body of the device. It consists of recording media, etc. provided to individuals.
The removable medium 21 is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, a magneto-optical disk, or the like. Optical disks include, for example, CD-ROMs (Compact Disk-Read Only Memory), DVDs (Digital Versatile Disks), and the like. The magneto-optical disk is composed of an MD (Mini-Disk) or the like.
The recording medium provided to the user in a pre-installed state in the main body of the apparatus includes, for example, the ROM 12 in FIG. 4 in which a program is recorded, the hard disk included in the storage unit 18 in FIG. 4, and the like.

In summary, the information processing apparatus to which the present invention is applied only needs to have the following configuration, and can take various embodiments.
That is, an information processing device to which the present invention is applied (for example, information processing device 1 in FIG. 3),
An information processing device that enables an operator (for example, operator 2 in FIG. 3) to modify character text generated by converting at least one image character included in an image using optical character recognition. There it is,
a first display unit (for example, the first display processing unit 112a in FIG. 5) that displays the image character and the character text in a comparatively visible state on a display unit (for example, the display unit 16 in FIG. 5);
When the operator determines that the character text displayed on the display unit requires the correction, the operator receives the necessary correction from the input unit and replaces the character text with the corrected character text. A first correction unit (for example, the first correction processing unit 113a in FIG. 5),
Equipped with.

According to the present invention, the first display means can display the image character and the character text in a comparatively visible state on the display section, and the first correction means receives the modification and converts the modified character from the character text. Since the information can be replaced with text, the operator can efficiently correct the character recognition results during character recognition using the information processing device. Therefore, it is possible to improve the efficiency of the correction work.

Further, the information processing device to which the present invention is applied is
A second display means (for example, the second display processing section in FIG. 5) that displays data modification candidates (for example, data modification candidate 16l in FIG. 11) on the display section to assist in the necessary modification of the character text. 112b),
The first modification means accepts the necessary modification based on a selected data modification candidate selected from the data modification candidates.

According to the present invention, it is possible to perform correction based on a selected data correction candidate selected from data correction candidates. Therefore, the efficiency of correction work can be improved.

Further, the information processing device to which the present invention is applied is
The first display means displays the image character and the character text on the display unit in accordance with a specified item among items related to the image character and the character text.

According to the present invention, when modifying character recognition results, it is possible to designate and narrow down items before modifying them. Therefore, the efficiency of correction work can be improved.

Further, the information processing device to which the present invention is applied is
Further comprising accuracy calculation means (for example, accuracy calculation processing unit 114 in FIG. 5) for calculating the accuracy of the optical character recognition,
The first display means displays at least the image characters on the display section in a display state based on the accuracy.

According to the present invention, image characters can be displayed on the display unit in a display state based on accuracy. This makes it possible to grasp the accuracy of optical character recognition just by looking at the display state. Therefore, the efficiency of correction work can be improved.

Further, the information processing device to which the present invention is applied is
When the operator specifies the character text displayed on the display unit, a form (for example, form F in FIG. 8) including the specified character text is displayed in the display area (for example, the first form in FIG. 8). a third display unit (for example, the third display processing unit 112c in FIG. 5) that displays the display area 16b and the second display area 16c separately on the display unit;
a second correction unit (for example, the second correction processing unit 113b in FIG. 5) that receives the necessary correction to the specified character text in the form and replaces the specified character text with the corrected character text;
It further includes:

According to the present invention, the third display means can divide the display area and display the form on the display section, and the second correction means can accept corrections and replace text text with corrected text text. , an operator can efficiently correct a character recognition result during character recognition using an information processing device. Therefore, it is possible to improve the efficiency of the correction work.

The information processing method to which the present invention is applied is
An information processing method executed by an information processing device that enables an operator to modify character text generated by converting at least one image character included in an image by optical character recognition, the method comprising:
a first display step (for example, step S1 in the flowchart of FIG. 6) of displaying the image character and the character text in a comparatively visible state on a display unit;
When the operator determines that the character text displayed on the display unit requires the correction, the operator receives the necessary correction from the input unit and replaces the character text with the corrected character text. a first modification step (for example, step S6 in the flowchart of FIG. 6);
including.

According to the present invention, since the information processing method is executed by an information processing device, it is possible to improve the efficiency of correction work for character recognition results.

The program to which the present invention is applied is
controlling an information processing device that allows an operator to modify character text generated by converting at least one image character obtained by recognizing characters included in an image by optical character recognition; to the computer,
a first display step (for example, step S1 in the flowchart of FIG. 6) of displaying the image character and the character text in a comparatively visible state on a display unit;
When the operator determines that the character text displayed on the display unit requires the correction, the operator receives the necessary correction from the input unit and replaces the character text with the corrected character text. a first modification step (for example, step S6 in the flowchart of FIG. 6);
Execute control processing including

According to the present invention, since the computer controlling the information processing apparatus executes the above-mentioned control processing, it is possible to improve the efficiency of the correction work of character recognition results.

DESCRIPTION OF SYMBOLS 1... Information processing device, 11... CPU, 112a... 1st display processing part (1st display means), 112b... 2nd display processing part (2nd display means), 112c... Third display processing section (third display means), 113a... first correction processing section (first correction means), 113b... second correction processing section (second correction means), 114... accuracy Calculation processing section, 115... Form data processing section, 18... Storage section, 181... Item data/character data storage section, 182... Data correction candidate storage section, 183... Accuracy data storage Section, 184... form data storage section

Claims (6)

An information processing device that enables an operator to modify character text generated by converting at least one image character included in a target image using optical character recognition, the information processing device comprising:
a first display means for displaying the image character and the character text in a comparatively visible state in a first display area of a display unit;
a first modification unit that accepts a modification made by the operator by operating an input unit to the character text displayed in a first display area of the display unit, and replaces the character text with a corrected character text; ,
When the operator specifies the character text displayed in the first display area of the display unit, a predetermined object including the specified character text is displayed in a second display area different from the first display area of the display unit. a second display means for displaying in the display area;
a second modification that accepts a modification made by the operator to the character text in the predetermined object displayed in the second display area by operating an input unit, and replaces the character text with the corrected character text; means and
An information processing device comprising: further comprising a third display means for displaying data correction candidates on the display unit for assisting the correction to the character text;
The first modification means accepts the modification based on a selected data modification candidate selected from the data modification candidates.
The information processing device according to claim 1. The first display means displays the image character and the character text on the display unit according to a specified item among items related to the image character and the character text.
The information processing device according to claim 1 or 2. Further comprising accuracy calculation means for calculating the accuracy of the optical character recognition,
The first display means displays at least the image characters on the display unit in a display state based on the accuracy.
The information processing device according to any one of claims 1 to 3. An information processing method executed by an information processing device that enables an operator to modify character text generated by converting at least one image character included in a target image by optical character recognition, the method comprising:
a first display step of displaying the image character and the character text in a first display area of a display unit in a visually recognizable state where they can be compared;
a first correction step of accepting a correction made by the operator to the character text displayed in a first display area of the display unit by operating an input unit, and replacing the character text with the corrected character text; ,
When the operator specifies the character text displayed in the first display area of the display unit, a predetermined object including the specified character text is displayed in a second display area different from the first display area of the display unit. a second display step for displaying in the display area;
a second modification that accepts a modification made by the operator to the character text in the predetermined object displayed in the second display area by operating an input unit, and replaces the character text with the corrected character text; step and
information processing methods, including A computer controlling an information processing device that allows an operator to modify character text generated by converting at least one image character included in a target image by optical character recognition;
a first display step of displaying the image character and the character text in a first display area of a display unit in a visually recognizable state where they can be compared;
a first correction step of accepting a correction made by the operator to the character text displayed in a first display area of the display unit by operating an input unit, and replacing the character text with the corrected character text; ,
When the operator specifies the character text displayed in the first display area of the display unit, a predetermined object including the specified character text is displayed in a second display area different from the first display area of the display unit. a second display step for displaying in the display area;
a second modification that accepts a modification made by the operator to the character text in the predetermined object displayed in the second display area by operating an input unit, and replaces the character text with the corrected character text; step and
A program that executes control processing including.

Images