Information processing device, information processing system, and information processing program

Abstract

To provide an information processing device, an information processing system, and an information processing program that enable users to easily identify a character to be confirmed among recognized characters, compared to a case where character information that is commonly recognized by reading multiple forms is displayed regardless of the number of character recognition results.SOLUTION: A recognition result totaling unit 56 totals recognition results of a character recognized over a plurality of forms. A recognition result list display unit 58 displays a list of character images, character information, certainty levels, etc. recognized over the plurality of forms. Further, an aggregated result of the recognition results is also displayed so that they can be selected in descending order of the aggregated result. In addition, while the list display is performed for each item, different items are displayed so that they can be easily extracted and selected.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing system, and an information processing program. [Background technology]

[0002] Patent Document 1 proposes a recognition result correction device for a character recognition device that improves the efficiency of correction work when a large number of forms are input. In detail, the recognition result correction device inputs a plurality of forms including one or more recognition items as image data. Characters in each recognition item in each form of the input image are recognized, and the recognition results and likelihood information of the characters included in each recognition item are stored in a result storage means for each form in association with these recognition items. At least one of the minimum value and the average value of the likelihood information of each character stored in the result storage means is calculated as a representative value of each recognition item in each of the forms, and the priority order for correcting the recognition results of each recognition item in the form is considered as the priority order of the sort key, and the order of forms to be corrected is determined by sorting the representative values ​​of the recognition items.

[0003] Patent Document 2 proposes an information processing device that reduces the burden on the worker compared to when the worker searches for all corrections in the recognition result for the information entered in the entry area. In detail, the information processing device accepts an extraction area image that represents an extraction area including a entry area in which information is entered by handwriting by a person entering information, and when an instruction to correct the recognition result for the information entered in the entry area represented in the extraction area image is given, displays another extraction area image similar to the extraction area image.

[0004] Patent Document 3 proposes a data entry system that enables efficient data entry work while viewing an image of a form. This data entry system includes an arrangement condition storage unit that stores conditions for rearranging a plurality of character input boxes, an extraction unit that extracts character entry fields corresponding to the plurality of character input boxes from an image, a rearrangement unit that changes the order defined in the definition information according to the conditions, and a display control unit that displays on a screen the plurality of character input boxes whose order has been rearranged and an extracted image of the character entry field corresponding to the character input box into which characters are to be input, at approximately the same time. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent 429977 [Patent Document 2] JP 2020-046734 A [Patent Document 3] JP 2009-211746 A Summary of the Invention [Problem to be solved by the invention]

[0006] By displaying character information for each commonly recognized character after scanning multiple documents, it is possible to check the character information all at once. However, there is a risk that characters that are not actually common may be displayed all at once due to misreading. When characters that are not actually common are displayed together, it is difficult to distinguish between common and non-common characters, and it is difficult to identify the character that should be checked. For example, when checking the character "1" as the scanning result, if characters that are not actually common, such as "1," "2," and "3," are displayed together, it is difficult to identify the character "1" that should be checked.

[0007] Therefore, an object of the present invention is to provide an information processing device, an information processing system, and an information processing program that can make it easier for a user to identify characters that should be confirmed among the recognized characters, compared to when character information that is commonly recognized by reading multiple documents and displaying it regardless of the number of character recognition results. [Means for solving the problem]

[0008] In order to achieve the above object, an information processing device according to a first aspect includes a processor, and the processor displays character information recognized by reading a plurality of forms, in order of the number of pieces of character information recognized as common characters, in descending order or descending order. and receiving an instruction to select a character for which the reading result is to be confirmed, and displaying a character image for the selected character and the character information of the character recognition result, including related characters having a similarity equal to or higher than a predetermined level among the character recognition results, and displaying the character images and character information of the related characters whose total number ratio is equal to or lower than a predetermined threshold value on a screen displaying the character image corresponding to the selected character and the character information of the character recognition result, thereby presenting the possibility of erroneous recognition. The process is performed.

[0012] In addition, the information processing device according to the fifth aspect is 1 In the information processing device according to the aspect, the processor further performs processing to display a screen on which the character image and the character information for the selected character and the character image and the character information below the threshold can be viewed together.

[0013] Also, 3 The information processing system according to the embodiment is a first embodiment Or in the second aspect The information processing device includes a client terminal having such an information processing device and a display unit, the client terminal displaying the character information on the display unit in ascending or descending order of the number of pieces of character information by processing of the information processing device.

[0014] Also, 4 The information processing program according to this embodiment causes a computer to execute a process of displaying character information recognized by reading a plurality of documents in order of the number of character information recognized as common characters or the number of character information recognized as common characters. Effect of the Invention

[0015] According to the first aspect, it is possible to provide an information processing device that allows a user to easily identify a character to be confirmed among the recognized characters, compared to a case where character information commonly recognized by reading a plurality of documents is displayed regardless of the number of character recognition results. The character to be checked can be identified and checked for the presence or absence of misrecognition, and the presence or absence of misrecognition can be checked including characters similar to the character to be checked, and for the character identified as the character to be checked, a character image that is highly likely to be misrecognized and character information can be checked together. do.

[0019] No. 2 According to this aspect, character images and character information that are likely to be misrecognized can be checked more efficiently than when the character image and character information for the selected character and the character image and character information that are likely to be misrecognized are displayed and checked separately.

[0020] No. 3 According to this aspect, an information processing system can be provided that makes it easier for a user to identify which characters among the recognized characters should be confirmed, compared to when multiple documents are read and commonly recognized character information is displayed regardless of the number of character recognition results.

[0021] No. 4 According to the aspect, it is possible to provide an information processing program that allows a user to easily identify a character to be confirmed among the recognized characters, compared to a case where character information commonly recognized by reading a plurality of documents is displayed regardless of the number of character recognition results. The character to be checked can be identified and checked for the presence or absence of misrecognition, and the presence or absence of misrecognition can be checked including characters similar to the character to be checked, and for the character identified as the character to be checked, a character image that is highly likely to be misrecognized and character information can be checked together. do. [Brief description of the drawings]

[0022] [Figure 1] 1 is a diagram showing a schematic configuration of a form system according to an embodiment of the present invention; [Diagram 2] FIG. 1 is a diagram illustrating an example of a specific configuration of a form system according to an embodiment of the present invention. [Diagram 3] FIG. 2 is a block diagram showing the configuration of the main electrical systems of the cloud server and the PC according to the embodiment. [Figure 4] 2 is a functional block diagram showing the functional configuration of each part in the form system according to the embodiment. FIG. [Diagram 5] 10 is a flowchart showing an example of the flow of processing performed on a cloud server in the form system according to the present embodiment. [Figure 6] FIG. 13 is a diagram showing an example of a confirmation and correction screen for the reading result of a single digit number. [Figure 7] In this example, "List view" is selected, and "None" is selected for "Check box" as the type of text information. [Figure 8] In this example, "List view" is selected, and "Fuji Hanako" in "Other" is selected as the type of character information. [Figure 9] 11 is a functional block diagram showing a modified example of the functional configuration of each unit in the form system according to the embodiment. FIG. [Figure 10] 11 is a diagram showing an example of a specific display when related items are extracted and presented in the form system according to the present embodiment. FIG. [Figure 11] FIG. 13 is a diagram showing an example of a screen for collectively checking. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] An example of an embodiment of the present invention will be described in detail below with reference to the drawings. In this embodiment, an example in which a form system is applied will be described as an example of an information processing system. Fig. 1 is a diagram showing a schematic configuration of a form system 10 according to this embodiment.

[0024] 1, the form system 10 includes an information processing device 20, a client terminal 40, and an input device 60. These devices are connected to a communication line such as a network (not shown) and can communicate with each other via the communication line. As an example of this communication line, the Internet, a LAN (Local Area Network), a WAN (Wide Area Network), etc. are applied.

[0025] The information processing device 20 performs OCR (Optical Character Recognition) processing on image data of multiple documents including forms input through the input device 60, and manages a series of processing flows for outputting the results of the OCR processing to a predetermined output destination. The specific configuration and operation of the information processing device 20 will be described later.

[0026] The client terminal 40 transmits various instructions related to the OCR process to the information processing device 20. The various instructions include, for example, an instruction to start reading information of image data, an instruction to display the result of reading information of image data, and the like. The client terminal 40 also displays various information such as the result of the OCR process performed by the information processing device 20 in response to the various received instructions, and notifications related to the OCR process. For example, the client terminal 40 is a general-purpose computer device such as a server computer or a personal computer (PC). Although only one client terminal 40 is illustrated in FIG. 1, this is not limiting, and multiple client terminals 40 may be prepared and, for example, each client terminal 40 may be used for different processes.

[0027] The input device 60 inputs image data to be subjected to OCR processing to the information processing device 20. Examples of the input device 60 include a general-purpose computer device such as a server computer or a PC, and an image forming device having a scanning function, a printer function, a FAX function, etc. In addition to the input device 60, image data may also be input to the information processing device 20 from the client terminal 40.

[0028] Next, an overview of the form system 10 will be described.

[0029] The form system 10 is a system in which an information processing device 20 performs OCR processing on image data input via an input device 60, and outputs the results of the OCR processing to a predetermined output destination.

[0030] In the OCR process, the information processing device 20 manages various processes, including (1) business design and operation verification, (2) data input, (3) data reading, (4) form discrimination, confirmation and correction, (5) reading result confirmation and correction, (6) business check, (7) data output, and (8) return. In this embodiment, the OCR process refers not only to the process of simply reading characters and symbols from image data, but also to post-processing such as character correction.

[0031] As an example of the management of various processes, (1) business design and operation verification, (2) data input, (3) data reading, (6) business check, and (7) data output processes are each automatically executed by the information processing device 20. Also, as an example of the management of various processes, (4) document discrimination, confirmation, and correction, and (5) reading result confirmation and correction processes are each accepted by input by the user via the client terminal 40. Also, as an example of the management of various processes, (8) return process may be automatically executed by the information processing device 20 or may be accepted by input by the user via the client terminal 40.

[0032] In the (1) business design and operation verification process, job rules are created that include read definition settings, output settings, and business check settings. In the read definition settings, as an example, a read range is set, which is the range in which image data information is read in the process of "(3) data reading". More specifically, as an example, a definition may be set such that the item value, which is the value, is read from near the right of the item extracted as the key. In the output settings, as an example, a file format and output destination of the output data output in the process of "(7) data output". In the business check settings, as an example, a format, such as the required input items and the number of characters that can be entered, in the form to be detected in the process of "(6) business check" are set.

[0033] In the process of (2) data input, image data is accepted as input from the input device 60. The accepted input image data is registered as a job, which is an execution unit of the process of "(3) data reading."

[0034] (3) In the data reading process, the information of the image data in the job is read using a job rule for the job to be executed, selected by the user from the job rules created in the process of "(1) Business Design and Operation Verification." As an example, in this process, the form included in the image data in the job is identified (hereinafter referred to as "form identification") and characters and symbols within the reading range are read.

[0035] In the (4) form identification, confirmation, and correction process, the image data in the job is divided into records that indicate the forms included in the job based on the results of the form identification performed in the "(3) Data Reading" process. After that, in this process, the divided records are displayed, and the user can confirm and correct the form identification.

[0036] In the process of (5) checking and correcting the read result, the read result of the characters and symbols within the read range performed in the process of "(3) data reading" is displayed, and the user can check and correct the read result.

[0037] In the (6) task check process, errors in each preceding process are detected by the task check setting included in the job rule for the job selected by the user from among the job rules created in the process of "(1) Task design and operation verification." The detection results may be presented to the user.

[0038] (7) In the data output process, output data is created using the output settings included in the job rules for the job selected by the user from the job rules created in the process of "(1) Business design and operational verification," and the created output data is output to a predetermined output destination.

[0039] In the (8) return process, the process executed in the OCR process is returned to the process one or more steps before. As an example, the return is instructed by the user from the client terminal 40 during the execution of various processes such as "(4) Document discrimination, confirmation, and correction" and "(5) Read result confirmation and correction." Also, as an example, the return is instructed from the client terminal 40 of the administrator depending on the result of the check by the administrator performed between the processes of "(6) Business check" and "(7) Data output."

[0040] In the above OCR processing, the process of "(1) business design and operation verification" is executed before the processes after "(3) data reading" are performed, i.e., before the form system 10 is put into operation. Furthermore, the process of "(1) business design and operation verification" may be executed during the operation of the form system 10, when the processes after "(3) data reading" are being performed. As an example, the job rules created in the process of "(1) business design and operation verification" before the operation of the form system 10 can be appropriately modified according to the results of the process of "(5) checking and correcting the reading results" during the operation of the form system 10.

[0041] Next, a specific configuration example of the form system 10 according to this embodiment will be described. Fig. 2 is a diagram showing an example of a specific configuration of the form system 10 according to this embodiment.

[0042] As shown in FIG. 2, the form system 10 illustrates an example in which an image forming device 12 is used as an example of an input device 60, a cloud server 14 is used as an example of an information processing device 20, and a PC 16 is used as an example of a client terminal 40.

[0043] In the form system 10, the image forming device 12, the cloud server 14, and the PC 16 are each connected via a communication line 18. The image forming device 12, the cloud server 14, and the PC 16 are each capable of transmitting and receiving various data to and from each other via the communication line 18.

[0044] Next, a description will be given of the main configuration of the electrical system of the cloud server 14 and the PC 16 according to this embodiment. Fig. 3 is a block diagram showing the main configuration of the electrical system of the cloud server 14 and the PC 16 according to this embodiment. Note that since the cloud server 14 and the PC 16 are basically configured as general computers, the cloud server 14 will be described as a representative and a description of the PC 16 will be omitted.

[0045] As shown in FIG. 3, the cloud server 14 according to the present embodiment includes a CPU 14A, a ROM 14B, a RAM 14C, a HDD 14D, a keyboard 14E, a display 14F, and a communication line interface (I / F) unit 14G. The CPU 14A controls the overall operation of the cloud server 14. The ROM 14B stores various control programs and various parameters in advance. The RAM 14C is used as a work area when the CPU 14A executes various programs. The HDD 14D stores various data and application programs. The keyboard 14E is used to input various information. The display 14F is used to display various information. The communication line interface unit 14G is connected to the communication line 18 and transmits and receives various data to and from other devices connected to the communication line 18. The above-mentioned units of the cloud server 14 are electrically connected to each other by a system bus 14H. Note that, in the cloud server 14 according to the present embodiment, an example in which the cloud server 14 includes the HDD 14D will be described, but the present embodiment is not limited to this, and the cloud server 14 may include other non-volatile storage units such as a flash memory.

[0046] With the above configuration, cloud server 14 according to the present embodiment executes, by CPU 14A, access to ROM 14B, RAM 14C, and HDD 14D, acquisition of various data via keyboard 14E, and display of various information on display 14F. Cloud server 14 also executes, by CPU 14A, control of transmission and reception of communication data via communication line interface unit 14G.

[0047] In this embodiment, the CPU 14A performs a process of displaying character information in descending order of the number of pieces of character information recognized as common characters among the character information read and recognized from each of a plurality of forms. In detail, the CPU 14A performs a process of rearranging the character information in descending order of the number of pieces of character information recognized as common characters among the character information read and recognized from each of a plurality of forms, and displaying the rearranged character information on the PC 16. Note that in this embodiment, an example of displaying in descending order will be described as an example.

[0048] Next, a functional configuration of the form system 10 according to this embodiment configured as described above will be described. Fig. 4 is a functional block diagram showing the functional configuration of each unit in the form system 10 according to this embodiment.

[0049] The form system 10 has the functions of an image reading unit 50, a recognition processing unit 52, a result storage unit 54, a recognition result tallying unit 56, a recognition result list display unit 58, a correction unit 62, and a result output unit 64. Each function is realized by executing a program. In this embodiment, the image reading unit 50 is described as a function of the image forming device 12, and the recognition processing unit 52, the result storage unit 54, the recognition result tallying unit 56, the recognition result list display unit 58, the correction unit 62, and the result output unit 64 are described as functions of the cloud server 14. The recognition processing unit 52, the result storage unit 54, the recognition result tallying unit 56, the recognition result list display unit 58, the correction unit 62, and the result output unit 64 may not be functions of a single cloud server 14, but may be functions shared by multiple servers.

[0050] The image reading unit 50 digitizes the input document and generates image data representing the read image. Note that non-standard forms may be automatically recognized. For example, image data representing an image of a form read by the image forming device 12 is generated.

[0051] The recognition processing unit 52 recognizes characters from image data generated by the image reading unit 50 by OCR processing, and reads the written contents.

[0052] The result storage unit 54 stores the image data of the form and the character recognition results of the OCR process in association with each other. For example, the recognition results such as character information and the degree of certainty of character recognition are stored in the HDD 14D in association with the image data of the character image.

[0053] The recognition result counting unit 56 counts the results of character recognition across multiple forms, for example, by counting the number of occurrences of each piece of character information.

[0054] The recognition result list display unit 58 displays a list of the character images, character information, confidence levels, etc. that have been recognized across multiple forms. It also displays the results of tallying the recognition results together, allowing selection in descending order of the number of tally results. It also extracts different items from the list displayed for each item and displays them for easy selection. By viewing this, it is possible to determine whether the character images and character information are correct. For example, it is possible to check for mistakes by searching for items displayed in the same row.

[0055] If the character recognition result is incorrect, the correction unit 62 accepts the correct result and updates the information stored in the result storage unit 54. After updating the confirmation status, it is possible to re-sort the results by the number of unconfirmed cases.

[0056] The result output unit 64 outputs a series of processing results including the correction result by the correction unit 62. The output data also includes an input form to a core business system, such as CSV (Comma Separated Value), and the like.

[0057] Next, specific processing performed in the form system 10 according to this embodiment will be described. Fig. 5 is a flow chart showing an example of the flow of processing performed in the cloud server 14 in the form system 10 according to this embodiment. Note that the processing in Fig. 5 starts when, for example, the PC 16 issues an instruction to start reading information of image data.

[0058] In step 100, the CPU 14A obtains image data obtained by reading the form, and proceeds to step 102. That is, image data generated by the image reading unit 50 reading the form is obtained. For example, image data generated by reading each page of the form is obtained.

[0059] In step 102, the CPU 14A performs character recognition processing, and the process proceeds to step 104. That is, the recognition processing unit 52 recognizes characters by OCR processing from the image data generated by reading an image with the image reading unit 50, and converts the handwritten character image or the printed character image into character information by reading the written contents.

[0060] In step 104, the CPU 14A tallies the character recognition results for each type, and the process proceeds to step 106. That is, the recognition result tallying unit 56 tallies the recognition results of characters recognized across multiple forms. Specifically, the total number of character images is calculated for each type of character information, such as checkboxes, one-character numbers, one-character alphabet, and free-writing character strings including Japanese.

[0061] In step 106, the CPU 14A performs counting for each recognition result for each type range, and proceeds to step 108. Specifically, the recognition result counting unit 56 calculates the total number of character images for each piece of character information.

[0062] In step 108, the CPU 14A acquires a narrowing down setting, and the process proceeds to step 110. For example, a narrowing down setting based on an attribute that does not depend on the recognition result, such as a processing date designated by a user operation, is acquired.

[0063] In step 110, the CPU 14A extracts the relevant items and proceeds to step 112. The relevant items are extracted by filtering the relevant items from the tabulation results in accordance with the selection made by the user operation. For example, filtering is performed by date and time, and items related to today's jobs are extracted.

[0064] In step 112, the CPU 14A determines the display order in descending order of the number of items, and proceeds to step 114. In this embodiment, the recognition result list display unit 58 rearranges the data group after filtering in descending order of the total number of free-writing character strings including Japanese.

[0065] In step 114, the CPU 14A displays a predetermined confirmation and correction screen for the reading result, and then proceeds to step 116. That is, the recognition result list display unit 58 displays a list of the character images, character information, and confidence levels recognized across multiple forms on the display 16F of the PC 16, and also displays the tabulated results of the recognition results, in descending order of frequency. By viewing this, it is possible to determine whether the character images and character information are correct.

[0066] In step 116, CPU 14A accepts a confirmation operation and proceeds to step 118. For example, recognition result list display unit 58 accepts an instruction to select a character to be confirmed from PC 16 and displays a character image for the selected character and character information of the character recognition result, and correction unit 62 accepts a confirmation result as to whether or not the character recognition result is correct.

[0067] In step 118, the CPU 14A judges whether or not to update the display. For example, the judgement is made by judging whether or not an operation to update the display has been performed. If the judgement is affirmative, the process proceeds to step 120, whereas if another operation such as an end instruction has been performed, the judgement is negative and the process proceeds to step 122.

[0068] In step 120, the CPU 14A updates the counted result and returns to step 110 to repeat the above-mentioned processing.

[0069] In step 122, the CPU 14A judges whether or not the process is to be ended. This judges whether or not an operation instructing the end has been performed. If the judgement is negative, the process returns to step 118 to repeat the above-mentioned process, and if the judgement is positive, the process of this example is ended.

[0070] Here, an example of a display screen for checking the character recognition result will be specifically described. Fig. 6 is a diagram showing an example of a confirmation and correction screen for the reading result of a single digit number.

[0071] 6 shows an example in which "Report View" and "List View" can be selected, and "List View" is selected. "Report View" is a display mode in which the character recognition results are displayed in the format of the scanned document, and "List View" is a display mode in which the character recognition results are filtered by items selected by the user from the scanned document and displayed in a list.

[0072] In the example of FIG. 6, the total number of items is 300, and the number of unconfirmed items is 200, and the unconfirmed items are filtered and displayed. In addition, the total number of character images is displayed for each type of character information, and the total number for each type of character information is displayed. In addition, in the example of FIG. 6, as shown by the type of character information being "single digit number," the most common "single digit number" is "2" with 150 occurrences, followed by "0" with 21 occurrences, and other "single digit numbers" with 0 occurrences, and the character information is displayed in descending order of the total number of pieces of character information. In this way, by displaying the character information in descending order of the total number of pieces, it becomes easier for the user to identify the recognized characters that should be confirmed.

[0073] In the example of Figure 6, "2" of "single digit number" is selected, and the record ID of "2", item name, scanned image, confirmation result, certainty, and confirmation status are displayed. The example of Figure 6 shows an example where the second-lowest certainty is judged to be "low" and the others to be "high." The screen is updated by checking the confirmation and operating "temporarily save."

[0074] FIG. 7 shows an example in which "List View" is selected and "None" is selected for "Check Box" as the type of text information.

[0075] In the example of Fig. 7, similar to Fig. 6, the total number of items is 300, and the number of unconfirmed items is 200, and the items are filtered and displayed by the unconfirmed items. Also, the total number of character images is displayed for each type of character information, and the total number for each type of character information is displayed. Also, in the example of Fig. 7, the most common type of "single digit number" in the type of character information is "2" with 150 cases, followed by "0" with 21 cases, and other "single digit numbers" with 0 cases, and the character information is displayed in descending order of the total number of characters.

[0076] In addition, in the example of Fig. 7, "None" is selected for the "Check box", and the record ID, item name, scanned image, confirmation result, certainty, and whether or not confirmation was performed for the "None" "Check box" are displayed. In the example of Fig. 7, a check mark is added to "Confirm" for items with a certainty of "High".

[0077] FIG. 8 shows an example in which "List View" is selected and "Fuji Hanako" in "Other" is selected as the type of character information.

[0078] In the example of Fig. 8, the total number of items is 165, and the number of unconfirmed items is 124, and all items are filtered and displayed. In addition, the total number of character images is displayed for each type of character information, and the total number for each type of character information is displayed. In addition, as shown in the example of Fig. 8, for the type of character information "Other," out of 120 items in "All Text," "Fuji Hanako" is the most common with 20 items, followed by "Child" with 10 items, "0123-45-678" with 10 items, etc., and the characters are displayed in descending order of the total number of characters.

[0079] In the example of Fig. 8, "Fuji Hanako" is selected, and the record ID, item name, scanned image, confirmation result, certainty, and whether or not confirmation was performed for "Fuji Hanako" are displayed. In the example of Fig. 8, a check mark is added to "Confirm" for items with a certainty of "High".

[0080] In this manner, in this embodiment, the character information of the read results is displayed in descending order of the number of words read, so that the greater the number of words read, the higher the accuracy of the results displayed all at once, and the user can check the read results all at once starting with those with the highest accuracy, thereby efficiently carrying out the checking process.

[0081] As shown in Fig. 9, the functional configuration of the form system 10 shown in Fig. 4 may further include the functions of a list condition setting unit 68 and a related item extraction unit 66. Fig. 9 is a functional block diagram showing a modified example of the functional configuration of each unit in the form system 10 according to this embodiment.

[0082] In this case, the list condition setting unit 68 specifies the display order not only in order of the number of pieces of character information but also in order of the number of pieces of character information, the order of the number of pieces of character information set by the administrator, etc. As an example of the order set by the administrator, for example, the order of character codes assigned to characters may be applied.

[0083] The related item extraction unit 66 also presents character images and character information as related recognition results according to the similarity of the extracted characters. The related items are those related to the extracted image with a similarity equal to or higher than a predetermined similarity. For example, the related items are those related to the extracted image when the certainty of character recognition is equal to or higher than a predetermined threshold value. Among these, those whose total number ratio between the related items is equal to a predetermined ratio are presented as those with a high possibility of erroneous recognition. For example, those that are ranked as second or subsequent candidates by measuring the certainty or average certainty for the image recognition result are presented as related items. For example, for a group of recognized images determined to be "Saitama", the certainty is "Saitama": 90%, "Saio": 70%, "Saitama": 65%, and "Saitama-kuni": 55%. Although "Saio": 70% is the second candidate, an image in which "Saio" is the first candidate is considered as a related item. Then, the image group in which "Saio" is the first candidate as a related item is presented as an error of "Saitama". In this case, items with a ratio of the total number between related items below a preset threshold (e.g., 5%) are presented as being highly likely to be misrecognized. For example, if there are 300 items (e.g., "Saitama") and there are 10 related items "Saio" and 5 related items "Saitama", then both of these total numbers are below 5% of the 300 items for "Saitama", and therefore "Saitama" and "Saitama" are presented as being highly likely to be misrecognized.

[0084] FIG. 10 is a diagram showing an example of a specific display when related items are extracted and presented in the form system 10 according to this embodiment.

[0085] In the example of FIG. 10, 230 records of "Kanagawa Prefecture", 200 records of "Saitama Prefecture", 180 records of "Chiba Prefecture", 100 records of "Yokohama City", 3 records of "Saitama Prefecture", and 2 records of "Yokohama City" are recognized, and an example of confirming and correcting the reading result of "Saitama Prefecture" is shown. The record ID of "Prefecture", the scanned image, and the reading result are displayed as the item name. Here, the upper right part of FIG. 10 displays the recognized images determined to be "Saitama" with a certainty level of 90% or more, which is a predetermined threshold value. In addition, the lower part of FIG. 10 displays related items. Here, as related items with a ratio of the total number between related items below a predetermined ratio, three "Saitama Prefecture"s are displayed as possible errors for "Saitama".

[0086] Furthermore, in the example of Fig. 10, when "Check all at once" is operated, a "Check all at once" screen shown in Fig. 11 is displayed. Fig. 11 is a diagram showing an example of a screen for checking all at once. As shown in Fig. 11, by pressing the target recognition result and then pressing the arrow button, the recognition result is moved from "Saitama" to "Saitama", or from "Saitama" to "Saitama". Then, the recognition result associated with the image is updated by pressing the save button.

[0087] In the above embodiment, the number of recognized character information pieces is displayed in descending order, but the present invention is not limited to this. For example, the number of recognized character information pieces may be rearranged and displayed in ascending order. By displaying the characters in descending order and checking and correcting the characters with the fewest number, noise can be removed first and the characters can be checked, which makes it easier for the user to identify the characters to be checked among the recognized characters compared to the case where the characters are displayed regardless of the number of character recognition results. For example, by removing noise first, such as by viewing the characters in descending order and integrating them with others, the user can identify the characters to be checked among the recognized characters. Also, the rearrangement in descending order or descending order may be preset. Also, the characters may be rearranged in the order of character codes previously assigned to the characters, other than the order of ascending order or descending order.

[0088] In addition, in the above embodiment, the CPU has been described as an example of a processor, but the term "processor" refers to a processor in a broad sense, and includes general-purpose processors (e.g., CPUs, etc.) and dedicated processors (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic devices, etc.).

[0089] In addition, the operations of the processor in the above embodiments may be performed not only by one processor, but also by multiple processors located at physically separate locations working together. The order of the operations of the processor is not limited to the order described in the above embodiments, and may be changed as appropriate.

[0090] The processes performed by each part of the form system 10 according to the above embodiment may be processes performed by software, hardware, or a combination of both. The processes performed by each part of the form system 10 may be stored as a program in a storage medium and distributed.

[0091] Furthermore, the present invention is not limited to the above, and it goes without saying that various modifications can be made without departing from the spirit and scope of the present invention. [Explanation of symbols]

[0092] 10 Reporting System 12 Image forming device 14 Client Server 14A CPU 16 PC 18. Communication Lines 20 Information processing device 40 Client terminals 50 Image reading unit 52 Recognition processing section 54 Result storage section 56 Recognition result aggregation unit 58 Recognition result list display area 60 Input Devices 62 Corrections Department 64 Result output section

Claims

1. a processor, the processor comprising: Among the character information recognized by reading each of the plurality of documents, the character information is displayed in order of the number of common characters that are recognized as the character information, and receiving an instruction to select a character for which the reading result is to be confirmed, and displaying, among the character recognition results, a character image for the selected character and the character information of the character recognition results, including related characters having a predetermined similarity or higher; The information processing device also performs processing to integrate and display the character images and character information of the related characters whose total number ratio is below a predetermined threshold on a screen that displays the character image corresponding to the selected character and the character information of the character recognition result, thereby indicating the possibility of misrecognition.

2. The information processing apparatus according to claim 1 , wherein the processor further performs processing for displaying a screen on which the character image and the character information for the selected character and the character image and the character information below the threshold value can be viewed together.

3. An information processing device according to claim 1 or 2; a client terminal including a display unit, the client terminal displaying the character information on the display unit in ascending or descending order of the number of pieces of character information by processing of the information processing device; An information processing system comprising:

4. displaying, on the computer, the character information recognized by reading each of the plurality of documents in order of the number of pieces of character information recognized as common characters; receiving an instruction to select a character for which the reading result is to be confirmed, and displaying, among the character recognition results, a character image for the selected character and the character information of the character recognition results, including related characters having a predetermined similarity or higher; and an information processing program for executing a process of integrating and displaying the character images and the character information of the related characters whose total number ratio is below a predetermined threshold on a screen that displays the character image corresponding to the selected character and the character information of the character recognition result, thereby indicating the possibility of misrecognition.

Images