JPH0962758A - Business form recognition processing system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To correct and input the data on the items that cannot be recognized on a business form with the highest workability in response to the number of those unrecognizable items. SOLUTION: The necessary parts of a large number of business forms 1 are read by a character recognizer, etc., and the recognition results are stored in an additional data file 22 of a storage part 21. On the other hand, the forms 1 that cannot be partly or entirely recognized are directly stored in an image data file 23 in terms of their images. When some of items cannot be concentrically recognized, the corresponding item images of a large number of forms 1 are successively listed up and can be corrected en bloc. If many items have unrecognizable parts, all images of items to be corrected of every form 1 are outputted and the collective input of data is urged.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a form recognition processing system which accepts a form such as a slip, recognizes and reads the characters written in the form, and uses the recognition result for classification and totaling.

[0002]

2. Description of the Related Art For example, in slip processing at supermarkets and convenience stores with stores nationwide, invoice processing for mail order, merchandise delivery and mail delivery processing, a large number of slips are classified, distributed and aggregated. Some work is required. Specifically, a form in which certain items are described is issued, the forms are collected, sorted by destination, and sent to the destination of the form. In the case of a slip or the like, in this case, the work of totaling the amount of money and the like described therein is involved. Such operations typically require large numbers of personnel and are extremely time consuming for processing. Therefore, in general, a large number of specialized personnel have been assigned to the slip processing work.
Further, in order to automate this kind of processing, a system in which a slip itself is eliminated and data is directly input and exchanged using a computer terminal is also widely used.

[0003]

The conventional system as described above has the following problems to be solved. The present inventors have developed a device that recognizes characters on a form and sorts the form into a large number of pockets according to the contents thereof in order to automatically sort a large amount of forms. In such an apparatus, high-speed and reliable recognition of the characters written on the form and smooth correction processing for the unrecognized characters and the ones in which the recognition error occurs are required.

For the unrecognized object or the recognition error, the operator inputs data by using the keyboard while looking at the actual read image. In this case, recognition errors or the like may occur intensively with respect to a specific item on the form. This may occur, for example, when the font of the character written in that portion does not match the font of the character registered in the dictionary for character recognition. In such a case, it is preferable that the operator intensively perform the data correction input process for the item.

In addition, if the entire form is filled with characters that are not easily recognized, it is necessary to correct the data of many items for many forms. In such a case, it may be more efficient to input the data all at once rather than referring to the data in which the recognition error has occurred and correcting the data. Therefore, it is preferable that the data correction input operation can be selected according to the result of character recognition.

[0006]

The present invention adopts the following constitution in order to solve the above problems. <Structure 1> A reading unit that reads an image of a form and recognizes the characters described in each item set on each form, a storage unit that stores the recognition result, and a character recognition unit. Counting the number of items that cannot be recognized, and if the number of items is less than a preset threshold value, a part of displaying an image including at least the unrecognizable items on the output device and urging data correction of the corresponding items. When the correction mode is selected and the number of items is equal to or greater than the preset threshold, the mode selection unit that displays the image of the entire form on the display output unit and selects the entire input mode that prompts data input for all items Prepare

<Explanation> On the form, items to be recognized are set at one or more arbitrary places, and characters including numbers, symbols, etc. are written for each item. Character recognition is performed collectively for each of these items, and as a general rule, even if only some characters in the same item cannot be recognized, the entire item is not recognized. The recognition result is processed as data for classification and aggregation. The threshold value is set on the basis of whether the partial correction work using the recognition result is easy or the entire correction work ignoring the recognition result is easy. The display output unit is a device having a display function including a display and a printer. With this configuration,
The work of correcting the recognition result is made efficient.

<Structure 2> Read the image of the form,
For each item set on each form, a reading unit that recognizes the characters written therein, a storage unit that stores the recognition result, and an image including at least the unrecognizable item are displayed on the display output unit. Then, a mode selection switch for selecting either a partial correction mode for prompting data correction of the corresponding item or an overall input mode for prompting data input for all items by displaying an image of the entire form on the output device. <Description> The mode selection switch is used to forcefully select a mode, not automatically. This is so that the operator can select more efficient work each time.

<Structure 3> In the partial correction mode, the mode selection unit may sequentially display the images of the same item portion of a plurality of forms on the output device as a list. <Explanation> The image of the same item part is not an image of the entire form but a partial image of the item for which data correction is required. Sequential listing means that the same item parts of a plurality of forms are arranged and displayed in the order of data modification. If you enumerate images of the same item part of each form sequentially and make batch corrections for the same item, compared to the case of correcting all the items that need to be corrected for each form and then correcting the next form, The data correction work becomes efficient.

[0010]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to specific examples. <Specific Example 1> FIG. 1 is a schematic explanatory view of a system of the present invention. In the figure, it is assumed that the form 1 is filled with the destination of the form, and in the case of an invoice, data corresponding to various items such as the amount charged. Such a form 1
Is issued by the sender, and the same senders are collectively processed. The reading unit 11 is configured by a well-known device for character recognition processing including a mechanism that reads an image of the form 1 and recognizes the written characters for each item written on the form. In the storage unit 21,
The result recognized by the reading unit 11 is stored.
The result is stored, for example, as an additional data file 22 arranged in order of the serial number of the form 1.

On the other hand, the data that cannot be recognized by the reading unit 11 is transferred to a process in which the operator inputs it again using the keyboard while looking at it. Therefore, if the image cannot be recognized, the read image is stored in the image data file 23 as it is. In this case, the image of the item area that is the target of character recognition is cut out, and an identification number is assigned to each item and stored in the image data file 23. The display output unit 24 is a unit that displays such an image data file 23 so that the operator can make corrections. A display 27 and a printer 28 are provided for the display. In addition, the display 27 and the printer 28
A keyboard 26 and a data processing unit 25 are provided for the purpose of the operator correcting data or inputting new data based on the image displayed in FIG.
The data input from the keyboard 26 is merged with the additional data file 22 by the data processing unit 25, and the data correctly recognized by the operator is added to the corresponding position.

Further, in the present invention, a mode selection unit 31 and a mode selection switch 30 are provided in order to simplify the data input process by the operator. The mode selection unit 31 is a unit that automatically selects a partial correction mode and a general input mode described later. The mode selection switch 30 is composed of a manual switch or the like that allows the operator to forcibly select either the partial correction mode or the entire input mode. Both the mode selection unit 31 and the mode selection switch 30 may be incorporated in one device, or may be incorporated in different devices. The selection signal is supplied to the display output unit 24, and the processing in the partial correction mode or the entire input mode is advanced in a manner described later.

Before giving a more detailed description of the present invention, an outline of a system to which the present invention is applied will be described in advance. FIG. 2 shows a form processing explanatory diagram suitable for the system of the present invention. In this system, the form is processed as a whole in such a procedure. First, the sender A1 has many forms 1
Fill in the address, billing amount, and other items. This form 1 is created for various destinations, and this form A is collectively sent from the source A1 to the sorting center.
The sorting center is equipped with a form classification processing system. Then, first, in step S1, the form 1 is read one by one, and the data is recognized. Then, in step S2, the forms are classified by destination. In this example, the forms created by the sender A1 are sorted in the order of destinations B1, B2, and B3. These forms are finally sent to the destination as they are, but at this time, the billing amount is calculated for each destination. The billing amount is also written on the form and is recognized by the character recognition unit. Therefore, the following procedure is adopted to collect the recognition results and confirm the results.

First, in step S3, the destination B1
Divide the addressed form into 50 sheets. Then, 50 sheets are taken out and the reading results are totaled (step S3).
Step S4). These are automatically executed by the computer, and the subtotal of the charged amount is printed every 50 sheets (step S).
5).

On the other hand, in addition to the 50 sheets, the read character portions are converted into image data. Then, the necessary portion is printed on the paper as it is (step S
6). That is, the billing amount and the like required for tabulating the form are printed side by side on paper as image data. This is totaled by the operator in step S7. The totaling by the operator may be actually performed using the 50 sheets themselves. However, for example, 50 sheets may include data related to privacy such as personal data. In such a case, a portion unnecessary for such totaling is excluded, and only a necessary portion is once printed on a sheet and used for totaling. This enables privacy protection.

Further, the work of collecting a large number of forms at hand and compiling them is relatively complicated and error-prone. Therefore, if only necessary portions of the respective forms are edited and printed so as to be easily aggregated as image data, the processing becomes efficient. Due to these various advantages, in this example, the main part of the read image is once printed on paper, and the totalization is performed by the operator. Then, the totalization result and step S5
In step S8, the result of totaling is compared. If the two match, the result of recognizing and processing the characters of the form and the data conversion is the same as the result calculated by the operator by actually seeing the form, and it can be seen that there is no error in the calculation or recognition result. In this case, move to step S9,
The billing amount for 50 sheets is fixed. On the other hand, if the matching results do not match, the operator compares the read and recognized data with the image, checks the recognition error, etc., and corrects the data.

FIG. 3 is a schematic block diagram of the form classification processing system. As shown in the figure, this system
Is received by the hopper 2, the image of the form is read by the main body 3, the characters written on the form are recognized, and the sorting is performed based on the result. For this sorting, a large number of pockets 4 for storing the forms according to classification are provided.
Further, a console 5 is provided for controlling this device, and a printer 6 is provided for printing out necessary data.
Is provided.

Some functional blocks provided in the main body 3 are shown on the lower side of this figure. As shown in the figure, the main body section 3 is provided with a reading section 11 for recognizing characters by reading the image of the form 1, and a character recognizing section 12.
Further, in this system, a bar code conversion unit 13 and a bar code printing unit 14 are provided in order to convert the result of such character recognition into a bar code and print the bar code in the margin of the form 1. With this device, the characters written on the form 1 can be recognized and the form can be sorted into the corresponding pockets 4 according to the recognition result. However, the number of pockets 4 is specifically 36, for example, and when the form 1 is classified into about 300, the form 1 may be repeated several times.
It is necessary to set to this system and repeat classification and sorting.

In such a case, if character recognition or the like is performed each time, the recognition process may take a long time and a recognition error is likely to occur. Therefore, in the present invention, a bar code that can be surely read and is less likely to cause a reading error is used. Therefore, for the second and subsequent classification / sorting processing, the barcode is read by the barcode reading unit 15 shown in the figure and the result is used. It should be noted that since the result of character recognition is used for the first time sorting and the output of the bar code reading unit is used for the second and subsequent times, both output signals are input to the sorting storage control unit 16. .

FIG. 4 shows an external view of the form. As shown in this figure, the form 1 is, for example, handwritten or typed on the front side of the form 1, together with the address, the amount charged, and other items. This is recognized by the character recognition unit 12. This back surface is, for example, blank. In this case, the information necessary for repeatedly classifying the form is once bar-coded and printed on the back side. Two barcodes 1 shown
In 8, the prefecture code representing the sender and the address thereof, the recipient, etc. are coded and entered.

In addition to the bar code, the additional information printing unit 17 prints a reference number and a batch serial number so that the operator who handles the form can easily confirm the form. The batch serial number is a number that is assigned to each group when the forms are collected into groups of 50 sheets as described above and are to be aggregated. Note that the reason for setting such a unit of aggregation (which is referred to as a batch) to 50 sheets is that the appropriate amount that can be manually checked is approximately 50 sheets if any mistake is discovered.
Therefore, according to the type, shape or contents of the form,
The number of batches may be arbitrarily selected.

In this example, the additional data file is generated based on the serial number printed on the back of the form as described above, and the re-input list is also created in the order of the serial number, and the input process is performed. This allows the data to be easily merged to complete the files arranged in a predetermined order.

FIG. 5 is an explanatory view of a display screen in the whole input mode and the partial input mode selected by the system of the present invention. FIG. 5A is a display screen in the overall input mode. The display screen 35 is displayed on the display 27 shown in FIG. 1, for example. Further, here, there are provided respective unrecognizable item images of the form to be processed, and a data correction input field for correcting and recognizing the recognition error of the item and inputting the corrected data. The hatched portion in the figure is the unrecognizable item image 36, and the portion surrounded by a white frame is the data correction input field 37. That is, if a reading error occurs in these items on the form, the image of each part of these items is cut out and displayed here. Then, on the lower side, data that has been once recognized but is partially unrecognizable is displayed.
In this case, it is preferable that the data correction input field 37 can be freely selected as to whether incorrect data can be displayed and corrected, or only new data can be input. In this mode, all items necessary for data correction for each form are displayed on the display screen 35, and the operator determines the contents of the data one by one.

The whole input mode as described above is suitable when a recognition error occurs in many items of the form. If this method is used, instead of displaying this screen on a display, etc., and printing it on a printer and requesting an outsourcer specialized in this kind of data input, a large number of operators or a large number of operators are arranged for correction processing. It is not necessary to prepare a correction terminal, and the data input cost can be kept low.

A display screen in the partial correction mode is shown in (b). Here, an operation in the case where there is a concentrated recognition error with respect to the same item of many forms is shown. On the display screen 35, the form numbers assigned one by one to the forms subjected to the classification processing and the like are shown. Then, a certain item image 38 and a recognition result 39 are sequentially displayed in a list format so as to correspond to the form number. The display part of the recognition result also serves as a data correction input field. It should be noted that this sequential list may include not only those that have caused a recognition error but also those that have been correctly recognized. Rather, by including the correctly recognized one, it is possible to recognize the relationship of the correct data before and after, which is a reference when the operator directly inputs the data.

Further, as shown in the drawing, when a large number of forms are processed and some of them have recognition errors, the recognition result of each form is sequentially displayed in a list for each item.
By doing this, you can input correct data while referring to other items. In addition, since such a correction can be efficiently performed on a large amount of forms collectively, it can be said that the correction is suitable for internal processing rather than outsourcing processing. Especially when only a part of the form causes a recognition error intensively,
If this is outsourced at the same wages as the data input for the entire form, the cost will be relatively high. Therefore, it is economically advantageous to carry out such work as an internal process.

By the way, one of the whole input mode and the partial correction mode as described above depends on whether there are a small number or a large number of unrecognizable items in the form.
Should be selected. Therefore, in the present invention, the mode selection unit 31 shown in FIG. 1 sets a threshold value in advance such that the number of items is a certain number, for example, the number of items is 2 or 3, and as a result of recognition processing of many forms, unrecognizable items are found. If it is less than this threshold, the partial correction mode is selected, and if it exceeds the threshold, the whole input mode is automatically selected.

Further, it is preferable that such a selection can be made artificially if necessary. Therefore, as another embodiment of the present invention, the mode selection switch 30 is provided so that the operator can understand the state of the unrecognizable item of the form and can select the whole input mode or the partial correction mode. When this selection is made, the display output unit 24 outputs the display screen of the entire input mode or the display screen of the partial correction mode shown in FIG. In each case,
It may be the output of a display or the output to a printer. Especially when performing outsourcing, etc.
In most cases, the output is usually to the printer.

The present invention is not limited to the above embodiments. The form design to be handled, the form classification method, the read content, the read method, etc. may be freely modified and selected.

[Brief description of drawings]

FIG. 1 is a schematic explanatory diagram of a system of the present invention.

FIG. 2 is an explanatory diagram of a form process suitable for the system of the present invention.

FIG. 3 is a schematic block diagram of the system of the present invention.

FIG. 4 is an external view explanatory diagram of a form.

FIG. 5 is an explanatory view of a display screen in each mode according to the present invention.

[Explanation of symbols]

 1 Form 11 Reading Section 21 Storage Section 24 Display Output Section 25 Data Processing Section 27 Display 28 Printer 30 Mode Selection Switch 31 Mode Selection Section

Claims (3)

[Claims] 1. A reading unit that reads an image of a form and recognizes a character described in each item set on each form, a storage unit that stores the recognition result, and the character recognition unit. Count the number of unrecognizable items, and if the number of items is less than a preset threshold value, display an image containing at least the unrecognizable item on the output device and prompt the data correction of the corresponding item. If you select the partial correction mode and the number of items is greater than or equal to the preset threshold, the image of the entire form is displayed on the display output section and the entire input mode that prompts for data input for all items is selected. A form recognition processing system characterized by having a section. 2. A reading unit that reads an image of a form and recognizes a character described in each item set on each form, a storage unit that stores the recognition result, and at least the unrecognizable unit. An image that includes various items is displayed in the output section, and a partial correction mode that prompts you to correct the data for the corresponding item, and an overall input mode that displays an image of the entire form on the output device and prompts you to enter data for all items A form recognition processing system having a mode selection switch for selecting any one of the above. 3. The form recognition processing system according to claim 1, wherein the mode selection unit sequentially displays images of the same item portion of a plurality of forms in a list on the output device in the partial correction mode. .