Information processing system and control program for information processing system

Abstract

This invention provides an information processing system and a control program for the information processing system that reduce the workload of the user. [Solution] The information processing system 1 comprises a receiving unit, an OCR execution unit, a management unit, an extraction unit, a correction candidate output unit, an accuracy information output unit, and a correction acceptance unit. The receiving unit receives image information. The OCR execution unit performs character recognition on the image information using OCR. The management unit stores definition data that defines the workflow based on the image information. The extraction unit extracts the items used in the workflow from the definition data. The correction candidate output unit extracts values ​​corresponding to the items used from the recognition results obtained by the OCR execution unit and outputs them as correction candidates. The accuracy information output unit outputs information based on the accuracy at which the OCR execution unit recognized the correction candidates. The correction acceptance unit accepts corrections to the correction candidates.

Description

Technical Field

[0001] Embodiments of the present invention relate to an information processing system and a control program for an information processing system.

Background Art

[0002] In order to perform processing using the result of OCR (Optical Character Recognition), there are known an apparatus, a system, a method, and a program that determine the type of text information extracted by OCR and perform processing according to the determined data type.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, when the user checks and corrects whether the OCR result is correct, if the user can check and correct even data that will not be used in subsequent processing, the user's workload may increase. One embodiment of the present invention provides an information processing system and a control program for the information processing system that suppress the user's workload.

Means for Solving the Problems

[0005] The information processing system according to the embodiment comprises a receiving unit, an OCR execution unit, a management unit, an extraction unit, a correction candidate output unit, an accuracy information output unit, and a correction acceptance unit. The receiving unit receives image information. The OCR execution unit performs character recognition on the image information using OCR. The management unit stores definition data that defines the workflow based on the image information. The extraction unit extracts the items used in the workflow from the definition data. The correction candidate output unit extracts values ​​corresponding to the items used from the recognition results obtained by the OCR execution unit and outputs them as correction candidates. The accuracy information output unit outputs information based on the accuracy at which the OCR execution unit recognized the correction candidates. The correction acceptance unit accepts corrections to the correction candidates. [Brief explanation of the drawing]

[0006] [Figure 1] A block diagram showing an example configuration of an information management system including an information processing system according to the embodiment. [Figure 2] A block diagram showing an example configuration of a processing server according to the embodiment. [Figure 3] A block diagram showing an example of the configuration of a file server according to this embodiment. [Figure 4] Block diagram showing an example configuration of an OCR server according to the embodiment. [Figure 5] A block diagram showing an example of the configuration of the functions of an information processing system according to the embodiment. [Figure 6] A flowchart illustrating the configuration operation of the information processing system according to the embodiment. [Figure 7] A table showing an example of a list of items used in the information processing system according to the embodiment. [Figure 8] A flowchart illustrating the execution operation of the workflow of the information processing system according to the embodiment. [Figure 9] A diagram showing an example of a screen displayed on a user terminal by the information processing system according to the embodiment. [Modes for carrying out the invention]

[0007] The embodiments will be described below with reference to the drawings. In the description, components having substantially the same function and configuration will be denoted by the same reference numerals. Furthermore, the embodiments shown below are illustrative of the technical concept. The embodiments do not specify the material, shape, structure, arrangement, etc., of the components. Various modifications can be made to the embodiments.

[0008] <Structure> Figure 1 is a block diagram showing an example configuration of an information management system including an information processing system according to an embodiment. The information management system is a system for managing information on documents such as slips. The information management system includes an information processing system 1, a user terminal 40, and an ERP (Enterprise Resource Planning) server 50. The information processing system 1, the user terminal 40, and the ERP server 50 are each connected to a network 60.

[0009] Information processing system 1 receives image information of a document from a user, performs character recognition using OCR processing, allows the user to confirm the recognition result, and then registers the recognition result in the ERP server. Information processing system 1 includes a processing server 10, a file server 20, and an OCR server 30. Processing server 10 is the server that controls the operation of the entire information processing system 1. File server 20 is the server that stores information. The OCR server is the server that performs OCR processing to recognize character information from image data. Processing server 10, file server 20, and OCR server 30 are each connected to network 60.

[0010] The user terminal 40 is an information processing terminal such as a PC (Personal Computer), tablet, or smartphone. The user operates the user terminal 40 to exchange information with the information processing system 1.

[0011] The ERP server 50 is a server that runs the integrated enterprise resource planning (ERP) system.

[0012] Network 60 is a communication path composed of a single or combination of communication means, including, for example, wired, wireless, LAN (Local Area Network), the Internet, telephone communication networks, and other proprietary communication networks.

[0013] Figure 2 is a block diagram showing an example configuration of a processing server according to an embodiment. The processing server 10 includes a processor 11, ROM (Read Only Memory) 12, RAM (Random Access Memory) 13, storage 14, a communication interface 15, and a system bus 16. The system bus 16 includes an address bus, a data bus, and control signal lines, etc. The system bus 16 connects the processor 11, ROM 12, RAM 13, storage 14, and communication interface 15 to each other. The computer of the processing server 10 is formed by connecting the processor 11, ROM 12, RAM 13, and storage 14 via the system bus 16.

[0014] The processor 11 corresponds to the central part of the computer described above. The processor 11 controls various parts in order to realize various functions as a processing server 10 according to the operating system or application program. The processor 11 is, for example, a CPU (Central Processing Unit).

[0015] ROM12 is a non-volatile storage device. ROM12 stores pre-configured operating systems or application programs, control data, and the like.

[0016] RAM13 is a volatile memory device. RAM13 is used as a work area where data is rewritten as needed by the processor 11. RAM13 is also used as a buffer memory to temporarily store data.

[0017] Storage 14 corresponds to the auxiliary storage part of the above computer. Storage 14 stores data used by the processor 11 to perform various processes, data created by the processes in the processor 11, etc. Storage 14 may also store the above application programs. Storage 14 is, for example, EEPROM (registered trademark) (Electric Erasable Programmable Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), etc.

[0018] Communication interface 15 is an interface for communicating with other devices connected through a network. Communication interface 15 is used for communication with external devices. External devices include, for example, file server 20, OCR server 30, user terminal 40, and ERP server 50. Communication interface 15 is composed of, for example, a LAN connector, etc. Communication interface 15 may perform wireless communication with other devices according to standards such as Wi-fi (registered trademark).

[0019] FIG. 3 is a block diagram showing a configuration example of a file server according to an embodiment. File server 20 includes processor 21, ROM 22, RAM 23, storage 24, communication interface 25, and system bus 26. System bus 26 includes an address bus, a data bus, control signal lines, etc. System bus 26 connects processor 21, ROM 22, RAM 23, storage 24, and communication interface 25 to each other. By connecting processor 21, ROM 22, RAM 23, and storage 24 with system bus 26, a computer of file server 20 is formed.

[0020] Processor 21 corresponds to the central part of the above computer. Processor 21 controls each part in order to realize various functions as file server 20 according to an operating system or an application program. Processor 21 is, for example, a CPU.

[0021] ROM22 is a non-volatile memory device. ROM22 stores pre-configured operating systems or application programs, control data, and other similar information.

[0022] RAM23 is a volatile memory device. RAM23 is used as a work area where data is rewritten as needed by the processor 21. RAM23 is also used as a buffer memory for temporarily storing data.

[0023] Storage 24 corresponds to the auxiliary storage portion of the computer described above. Storage 24 stores data used by the processor 21 in performing various processes, data created by the processing performed by the processor 21, etc. Storage 24 may also store the application programs described above. Storage 24 can be, for example, EEPROM (registered trademark), HDD, SSD, etc.

[0024] The communication interface 25 is an interface for communicating with other devices connected via the network. The communication interface 25 is used for communication with external devices. External devices include, for example, the processing server 10, the OCR server 30, the user terminal 40, and the ERP server 50. The communication interface 25 is composed of, for example, a LAN connector. The communication interface 25 may also perform wireless communication with other devices in accordance with standards such as Wi-Fi (registered trademark).

[0025] Figure 4 is a block diagram showing an example configuration of an OCR server according to the embodiment. The OCR server 30 includes a processor 31, ROM 32, RAM 33, storage 34, communication interface 35, and a system bus 36. The system bus 36 includes an address bus, a data bus, and control signal lines, etc. The system bus 36 connects the processor 31, ROM 32, RAM 33, storage 34, and communication interface 35 to each other. The computer of the OCR server 30 is formed by connecting the processor 31, ROM 32, RAM 33, and storage 34 via the system bus 36.

[0026] The processor 31 corresponds to the central part of the computer described above. The processor 31 controls various parts to realize various functions as an OCR server 30 according to the operating system or application program. The processor 31 is, for example, a CPU.

[0027] ROM32 is a non-volatile memory device. ROM32 stores pre-configured operating systems or application programs, control data, and other similar information.

[0028] RAM33 is a volatile memory device. RAM33 is used as a work area where data is rewritten as needed by the processor 31. RAM33 is also used as a buffer memory for temporarily storing data.

[0029] Storage 34 corresponds to the auxiliary storage portion of the computer described above. Storage 34 stores data used by the processor 31 in performing various processes, data created by the processing performed by the processor 31, etc. Storage 34 may also store the application programs described above. Storage 34 can be, for example, an EEPROM (registered trademark), HDD, SSD, etc.

[0030] The communication interface 35 is an interface for communicating with other devices connected via the network. The communication interface 35 is used for communication with external devices. External devices include, for example, the processing server 10, the file server 20, the user terminal 40, and the ERP server 50. The communication interface 35 is composed of, for example, a LAN connector. The communication interface 35 may also perform wireless communication with other devices in accordance with standards such as Wi-Fi (registered trademark).

[0031] Figure 5 is a block diagram showing an example of the configuration of the functions of an information processing system according to an embodiment. The functions of the information processing system 1 can also be represented as a collection of functional units as shown in Figure 5. The information processing system 1 includes a control unit 101, a receiving unit 102, an OCR execution unit 103, a management unit 104, an extraction unit 105, a correction candidate output unit 106, a correction reception unit 107, an undetected output unit 108, an undetected input reception unit 109, a processing content output unit 110, an accuracy information output unit 111, and a confirmation request unit 112.

[0032] The control unit 101 controls the operation of the entire information processing system 1. The functions of the control unit 101 are realized, for example, by the processor 11 of the processing server 10 executing an application program stored in the ROM 12 or storage 14.

[0033] The receiving unit 102 receives image information from the user terminal 40 and stores the received image information. The function of the receiving unit 102 is realized, for example, by the processor 21 of the file server 20 controlling the communication interface 25 to receive image information and controlling the storage 24 to store the received image information.

[0034] The OCR execution unit 103 performs OCR processing on image information stored in the file server 20 and obtains recognition results. The recognition results include an accuracy score indicating how likely the recognized result is. The OCR execution unit 103 extracts keywords and corresponding values ​​from the image information, for example, using AI (Artificial Intelligence) technology. The functions of the OCR execution unit 103 are realized, for example, when the processor 31 of the OCR server 30 controls the communication interface 35 to receive image information from the file server 20 and executes an application program stored in the ROM 32 or storage 34 to perform OCR processing.

[0035] The management unit 104 stores definition data that defines a workflow representing a series of processes based on image information. The functions of the management unit 104 are realized, for example, by the processor 11 of the processing server 10 controlling the storage 14 to store the definition data.

[0036] The extraction unit 105 extracts the usage items handled in the workflow indicated by the definition data stored in the management unit 104. The function of the extraction unit 105 is realized, for example, by the processor 11 of the processing server 10 executing an application program stored in the ROM 12 or storage 14.

[0037] The correction candidate output unit 106 extracts values ​​corresponding to the usage items obtained by the extraction unit 105 from the recognition results obtained by the OCR execution unit 103 and outputs them as correction candidates. The function of the correction candidate output unit 106 is realized, for example, by the processor 11 of the processing server 10 executing an application program stored in the ROM 12 or storage 14.

[0038] The correction reception unit 107 accepts corrections from the user regarding the correction candidates output by the correction candidate output unit 106. The function of the correction reception unit 107 is realized, for example, when the processor 11 of the processing server 10 executes an application program stored in the ROM 12 or storage 14 and receives a correction command via the communication interface 15.

[0039] The undetected output unit 108 outputs items obtained by the extraction unit 105 that are not included in the recognition results obtained by the OCR execution unit 103 as undetected items. The function of the undetected output unit 108 is realized, for example, by the processor 11 of the processing server 10 executing an application program stored in the ROM 12 or storage 14.

[0040] The undetected input receiving unit 109 accepts user input regarding undetected items obtained by the undetected output unit 108. The function of the undetected input receiving unit 109 is realized, for example, when the processor 11 of the processing server 10 executes an application program stored in the ROM 12 or storage 14 and receives input commands via the communication interface 15.

[0041] The processing content output unit 110 outputs processing details indicating how the usage items obtained by the extraction unit 105 are used in the workflow. The function of the processing content output unit 110 is realized, for example, by the processor 11 of the processing server 10 executing an application program stored in the ROM 12 or storage 14.

[0042] The accuracy information output unit 111 outputs information based on the accuracy at which the OCR execution unit 103 recognized the correction candidate, based on the recognition results obtained by the OCR execution unit 103. The function of the accuracy information output unit 111 is realized, for example, by the processor 11 of the processing server 10 executing an application program stored in the ROM 12 or storage 14.

[0043] The confirmation request unit 112 outputs a message indicating that the correction candidate has been confirmed, based on the accuracy of the OCR execution unit 103's recognition of the correction candidate. The function of the confirmation request unit 112 is realized, for example, by the processor 11 of the processing server 10 executing an application program stored in the ROM 12 or storage 14.

[0044] <Operation> The information processing system 1 according to this embodiment performs different operations during workflow setup and workflow execution. The workflow setup operation and workflow execution operation in the information processing system 1 are described below.

[0045] Figure 6 is a flowchart illustrating the workflow setup operation of an information processing system according to an embodiment. When a user operates the user terminal 40 to set up the workflow (start), the information processing system 1 stores the definition data (ACT 11). In detail, the management unit 104 of the information processing system 1 stores the definition data that defines the workflow based on the settings entered by the user into the user terminal 40.

[0046] Information processing system 1 creates a list of usage items (ACT12). Specifically, the extraction unit 105 of information processing system 1 extracts the usage items handled in the workflow defined in the definition data from the definition data and stores them as a list of usage items.

[0047] Figure 7 is a table showing an example of a list of items used in the information processing system according to the embodiment. As shown in Figure 7, the list of items used records the workflow ID, item ID, processing content, and item. The workflow ID is an identification number for identifying the definition data. The item ID is a sequential number for the item handled in the workflow. The processing content indicates how the value of the item obtained in the workflow will be used for processing. The item indicates the item handled in the workflow. In the example shown in Figure 7, there are five items corresponding to workflow ID "123". The item with item ID "1" and processing content "File name change" is "Receipt date". The item with item ID "2" and processing content "File name change" is "Invoice number". The item with item ID "3" and processing content "ERP linkage" is "Invoice number". The item with item ID "4" and processing content "ERP linkage" is "Total". The item with item ID "5" and processing content "ERP integration" is "Vendor Name".

[0048] Returning to the explanation referring to Figure 6, once the ACT12 process is complete, the series of processes shown in Figure 6 will end (end).

[0049] Figure 8 is a flowchart illustrating the execution operation of a workflow in an information processing system according to an embodiment. When a user operates the user terminal 40 and commands the execution of a workflow (start), the information processing system 1 reads definition data (ACT21). In detail, the management unit 104 of the information processing system 1 reads the definition data of the workflow corresponding to the command executed by the user.

[0050] Information processing system 1 receives an image file (ACT22). More specifically, the receiving unit 102 of information processing system 1 receives an image file used in the workflow from the user terminal 40.

[0051] Information processing system 1 performs OCR processing (ACT23). Specifically, the OCR execution unit 103 of information processing system 1 performs OCR processing on the image file received by the processing in ACT22 and obtains the recognition result.

[0052] Information processing system 1 extracts the items used from the OCR processing results (ACT24). Specifically, the correction candidate output unit 106 of information processing system 1 extracts values ​​corresponding to the items used extracted by the extraction unit 105 from the recognition results obtained by the processing of ACT23, as correction candidates.

[0053] The information processing system 1 outputs correction candidates (ACT25). Specifically, the correction candidate output unit 106 of the information processing system 1 outputs the correction candidates extracted by the processing of ACT24 to the user terminal 40. In this embodiment, the correction candidate output unit 106 outputs to the user terminal 40 so that the correction candidates and the image file received by ACT22 are displayed side by side.

[0054] Information processing system 1 outputs undetected items (ACT26). Specifically, the undetected output unit 108 of information processing system 1 outputs to the user terminal 40 as undetected items any items from the usage items extracted by the extraction unit 105 that are not included in the recognition results obtained by the processing of ACT23.

[0055] Information processing system 1 outputs accuracy-based information (ACT27). Specifically, the accuracy information output unit 111 of information processing system 1 outputs accuracy-based information from the recognition results obtained by the OCR execution unit 103, based on the accuracy at which the OCR execution unit 103 recognized a correction candidate. Accuracy-based information may be the accuracy itself, a value calculated based on the accuracy, or display information controlled based on the accuracy. In this embodiment, accuracy-based information will be explained using, as an example, a value indicating the accuracy as a percentage and emphasis information that highlights the item when the accuracy is lower than a first threshold. The first threshold is an arbitrary threshold for determining a lower accuracy that requires attention when checking the value. The first threshold is, for example, 70%. Emphasis information may be, for example, highlighting a value or accuracy by enclosing it in exclamation marks. When the accuracy information output unit 111 outputs accuracy-based information, it may output predetermined information for undetected items. For example, in this embodiment, undetected information is treated as having a confidence level of 0%.

[0056] Information processing system 1 outputs a confirmation request (ACT28). Specifically, the confirmation request unit 112 of information processing system 1 outputs a confirmation request asking the user to input that they have confirmed an item for items whose accuracy is lower than the second threshold. The second threshold is an arbitrary threshold used to determine lower accuracy levels that require careful attention when verifying the value. The second threshold is, for example, 50%. The method by which the user has confirmed an item is, for example, by checking a checkbox that indicates it has been confirmed. Information processing system 1 continues to wait for corrections or inputs from the user until this checkbox is checked, and prevents the value from being finalized.

[0057] Information processing system 1 outputs the processing details (ACT29). Specifically, the processing details output unit 110 of information processing system 1 outputs to the user terminal 40 the processing details that indicate how each of the usage items extracted by the extraction unit 105 will be used in the workflow.

[0058] The user terminal 40 asks the user whether or not to correct the correction candidates, what value to enter for the undetected items, and whether to check the checkbox indicating confirmation, and then sends the results to the information processing system 1.

[0059] Information processing system 1 accepts corrections (ACT30). Specifically, the correction acceptance unit 107 of information processing system 1 accepts corrections from the user regarding the correction candidates output in ACT25 and modifies the values.

[0060] Information processing system 1 accepts input for undetected items (ACT31). Specifically, the undetected input receiving unit 109 of information processing system 1 accepts user input for undetected items output in ACT26 and updates the values.

[0061] Information processing system 1 executes the remaining processes of the workflow (ACT32). Specifically, the control unit 101 of information processing system 1 executes the remaining processes of the workflow defined by the definition data read in the ACT21 process that have not yet been executed. For example, taking the workflow with workflow ID "123" shown in Figure 7 as an example, the remaining processes are "file name change" and "ERP linkage". The "file name change" process is the process of changing the file name of the image file stored in the file server 20. The "ERP linkage" process is the process of sending the values ​​of each item obtained from the processes from ACT21 to ACT31 in Figure 8, along with the image file on which the "file name change" process described above has been performed, to the ERP server 50.

[0062] Once the ACT32 process is complete, the series of processes shown in Figure 8 will end (end).

[0063] Figure 9 shows an example of a screen displayed on a user terminal by the information processing system according to the embodiment. As shown in Figure 9, screen SC includes an image IMG, a confirmation display TEX, a correction button BTa, and a cancel button BTb. Screen SC is displayed on the display of the user terminal 40. The image IMG displays an image file used in the workflow, which has been sent from the user terminal 40 to the information processing system 1. The confirmation display TEX is a set of correction candidates and their values, undetected items, accuracy, highlighting information, confirmation request, and processing details. In the example shown in Figure 9, the items displayed are "invoice number," "vendor name," "total," and "received date."

[0064] In the "Invoice Number" field, the OCR processing yielded the value "invoice100" with 93% accuracy, prompting the user to confirm if any corrections were needed. The "Invoice Number" field also indicates that it will be used in the "File Name Rename" and "ERP Integration" processes within the workflow.

[0065] In the "Vendor Name" field, the OCR processing yielded the value "XYZ Corporation" with 68% accuracy, prompting the user to confirm if correction is needed. Due to the low accuracy, the value "XYZ Corporation" and the 68% accuracy are enclosed in exclamation marks for emphasis. The "Vendor Name" field also indicates that this field is used in the "ERP Integration" process within the workflow.

[0066] In the "Total" field, the OCR processing yielded the value "¥11,000" with 38% accuracy, prompting the user to confirm if correction is needed. In the "Total" field, due to the lower accuracy, the value "¥11,000" and the 38% accuracy are highlighted with an exclamation mark, and a checkbox indicating confirmation is displayed. The "Total" field also indicates that this field will be used in the "ERP Integration" process within the workflow.

[0067] In the "Received Date" field, "Not Detected" is displayed, indicating that the OCR processing did not find a value corresponding to this field, and a blank space is indicated for the user to enter a value. The accuracy of the "Received Date" field is 0%, and because the accuracy was low, the blank space, the 0% accuracy, and "Not Detected" are enclosed by an exclamation mark as emphasis information. Furthermore, a checkbox indicating "Confirmed" is displayed, which is a confirmation request. The "Received Date" field also indicates that this field is used in the "Rename File" process in the workflow. When the user presses the Edit button BTa, it executes a process to confirm the correction with the content shown in the confirmation display TEX. When the user presses the Cancel button BTb, it stops the execution of the workflow.

[0068] <Effects> In systems that include OCR processing, for example, users are required to verify and correct whether characters have been recognized correctly. When OCR processing involves, for example, specifying multiple areas to recognize characters, or using AI technology to extract keywords and their corresponding values, recognition results may be output for many items. If recognition results are output for items that are not used in the workflow, and users are required to verify whether they were recognized correctly, the burden on the user can increase.

[0069] According to the embodiment, the information processing system 1 includes a receiving unit 102 that receives image information, an OCR execution unit 103 that performs character recognition on the image information using OCR, a management unit 104 that stores definition data defining a workflow based on the image information, an extraction unit 105 that extracts items used in the workflow from the definition data, a correction candidate output unit 106 that extracts values ​​corresponding to the items used from the recognition results obtained by the OCR execution unit and outputs them as correction candidates, an accuracy information output unit 111 that outputs information based on the accuracy when the OCR execution unit recognizes a correction candidate, and a correction reception unit 107 that accepts corrections to the correction candidates. As a result, the information processing system 1 according to the embodiment can check and correct the results of OCR processing while referring to accuracy-based information only for items used in the workflow. Therefore, the information processing system 1 according to the embodiment can reduce the workload on the user by not requiring the user to check items not used in the workflow and by indicating the degree to which attention should be paid using accuracy-based information.

[0070] Furthermore, according to the embodiment, the accuracy information output unit 111 of the information processing system 1 outputs the accuracy as a percentage as information based on accuracy. As a result, the information processing system 1 according to the embodiment can appropriately convey the accuracy to the user.

[0071] Furthermore, according to the embodiment, the accuracy information output unit 111 of the information processing system 1 outputs emphasis information to highlight correction candidates as accuracy-based information when the accuracy is lower than the first threshold. As a result, the information processing system 1 according to the embodiment can draw the user's attention to items with low accuracy.

[0072] Furthermore, according to the embodiment, the confirmation request unit 112 of the information processing system 1 outputs a confirmation request to input that the correction candidate has been confirmed when the accuracy is lower than the second threshold. As a result, the information processing system 1 according to the embodiment can prevent the user from proceeding with the workflow without confirming items with lower accuracy that require more user confirmation.

[0073] Furthermore, according to this embodiment, the OCR execution unit 103 of the information processing system 1 uses AI technology to extract keywords and corresponding values ​​from image information. By utilizing AI technology in this way, compared to OCR processing that recognizes characters by pre-specifying an area of ​​an image, for example, it is possible to recognize many items without pre-specifying an area. In other words, by utilizing AI technology, the effort involved in OCR processing can be reduced. While an increase in the number of recognizable items may increase the amount of work required for user verification and correction, according to this embodiment, the user is only required to verify the results of the OCR processing, along with accuracy-based information, for items used in the workflow. Therefore, according to this embodiment, even when AI technology is used in OCR processing, an increase in the amount of work required for user verification and correction can be suppressed. Thus, OCR processing utilizing AI technology is suitable as the OCR processing used in this embodiment.

[0074] <Other variations, etc.> In the above embodiment, the accuracy information output unit 111 was described as providing accuracy-based information such as a value indicating the accuracy as a percentage, and emphasis information that highlights the item when the accuracy is lower than the first threshold. However, accuracy-based information is not limited to these. For example, accuracy may be represented by a numerical value in the range of 0.00 to 1.00, or by the magnitude of a number within an arbitrary range. Also, for example, symbols such as ○, △, and × may be displayed based on the accuracy, or the color of a graphic may change from blue to red based on the accuracy. Thus, accuracy-based information is not limited to numerical values ​​and can be expressed in various ways, such as graphics and colors. The emphasis information is also not limited to switching between two states using one threshold, but may switch between any number of states according to the accuracy. Furthermore, emphasis may be expressed in various ways, not limited to displaying an exclamation mark, such as changing the font size, changing the color of the text or graphic, changing the background color of the item, or enclosing the item in a frame.

[0075] In the above embodiment, an example of a confirmation request was described as checking a checkbox indicating confirmation. However, the confirmation request is not limited to this. For example, a button indicating confirmation may be displayed on the screen, and confirmation may be recognized when this button is pressed. For example, confirmation may be automatically determined by detecting input or editing of the item.

[0076] In the above embodiment, the function of the OCR execution unit 103 was described as being realized by the processor 31 executing an application program and performing OCR processing. The OCR server 30 may include a configuration that performs calculations in addition to the processor 31, and the OCR processing may be performed by hardware other than the processor 31. For example, the OCR server 30 may further include an AI calculation unit which is a calculation unit suitable for executing processing that utilizes AI technology, and the function of the OCR execution unit 103 may be realized by this AI calculation unit performing calculations.

[0077] In the above embodiment, the case in which the information processing system 1 includes a processing server 10, a file server 20, and an OCR server 30 was described as an example. The configuration of the information processing system 1 is not limited to this, and it may be configured in any way as long as each functional unit described with reference to Figure 5 is realized. For example, the information processing system 1 may be realized by a single server or by a user terminal 40.

[0078] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of Symbols]

[0079] 1...Information processing system, 10...Processing server, 20...File server, 30...OCR server, 40...User terminal, 50...ERP server, 60...Network, 11...Processor, 12...ROM, 13...RAM, 14...Storage, 15...Communication interface, 16...System bus, 21...Processor, 22...ROM, 23...RAM, 24...Storage, 25...Communication interface, 26...System bus, 31...Processor, 32...ROM, 33...RA M, 34...Storage, 35...Communication Interface, 36...System Bus, 101...Control Unit, 102...Receiver, 103...OCR Execution Unit, 104...Management Unit, 105...Extraction Unit, 106...Correction Candidate Output Unit, 107...Correction Reception Unit, 108...Undetected Output Unit, 109...Undetected Input Reception Unit, 110...Processing Content Output Unit, 111...Accuracy Information Output Unit, 112...Confirmation Request Unit, SC...Screen, IMG...Image, TEX...Confirmation Display, BTa...Correction Button, BTb...Cancel Button.

Claims

1. A receiving unit that receives image information, An OCR execution unit performs character recognition on the aforementioned image information using OCR, A management unit that stores definition data for defining the workflow based on the aforementioned image information, An extraction unit that extracts the items used in the workflow from the definition data, A correction candidate output unit extracts values ​​corresponding to the usage items from the recognition results obtained by the OCR execution unit and outputs them as correction candidates. The OCR execution unit outputs information based on the accuracy at which it recognized the correction candidate, The correction reception department accepts corrections for the aforementioned correction candidates, An information processing system equipped with the following features.

2. The information processing system according to claim 1, wherein the accuracy information output unit outputs the accuracy as a percentage as information based on the accuracy.

3. The information processing system according to claim 1, wherein the accuracy information output unit outputs emphasis information to emphasize the correction candidate as information based on the accuracy when the accuracy is lower than a threshold.

4. The information processing system according to claim 1, further comprising a confirmation request unit that outputs a confirmation request to input that the correction candidate has been confirmed when the accuracy is lower than a threshold.

5. The information processing system according to claim 1, wherein the OCR execution unit uses AI technology to extract keywords and values ​​corresponding to the keywords from the image information.

6. In the processor of the information processing system, Receive image information, The aforementioned image information is subjected to character recognition using OCR. The system stores definition data that defines the workflow based on the aforementioned image information. From the defined data, extract the items used in the workflow. From the recognition results obtained by the aforementioned OCR character recognition, values ​​corresponding to the usage items are extracted and output as correction candidates. The system outputs information based on the accuracy at which the correction candidate was recognized by the aforementioned OCR character recognition. A control program for an information processing system that accepts corrections for the aforementioned correction candidates.

Images