Information generation system, workflow system, information generation program and workflow program

Abstract

To provide an information generation system, a workflow system, an information generation program, and a workflow program that facilitate the creation of a template for generating specific information from images in a document.SOLUTION: An information generation system comprises a template generation unit that generates a template for generating specific information including information extracted from an invoice image and a general-purpose information generation unit that generates specific information from an invoice image without using a template. The template generation unit generates a new template (S107) based on the invoice image, the specific information generated by the general-purpose information generation unit from the invoice image, and a template managed in a template database.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to an information generation system, a workflow system, an information generation program, and a workflow program that generate specific information from an image of a document. [Background technology]

[0002] Conventionally, there is known a technique for character recognition (character extraction and analysis) of positions on a paper surface where characters are to be written that are defined by a predefined template (see Patent Document 1). This technique identifies the form ID of a document that has been converted into image data by printing or writing a form ID, which is an identifier of template definition information, on the paper surface, and performs OCR (Optical Character Recognition) processing using the corresponding template. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-181369 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional techniques have a problem in that it takes a lot of time and effort to create a template for generating specific information from a document image.

[0005] Therefore, an object of the present invention is to provide an information generation system, a workflow system, an information generation program, and a workflow program that can facilitate the creation of templates for generating specific information from document images. [Means for solving the problem]

[0006] An information generation system of the present invention includes a document classification unit that classifies documents according to their formats, a template information generation unit that generates information from an image of the document using a template for generating specific information from the image of the document, a generic information generation unit that generates the information from the image in a generic manner independent of the format, and a template generation unit that generates the template, wherein when the format of the document corresponding to the image is identified by the document classification unit, and the template corresponding to the format identified by the document classification unit is managed in a template management unit that manages the templates, the template information generation unit generates the information from the image using the template corresponding to the format identified by the document classification unit, among the templates managed in the template management unit, and when the format of the document corresponding to the image is identified by the document classification unit, when the generic information generation unit generates the information from the image, the template corresponding to the format identified by the document classification unit, based on the image, the information, and the template managed in the template management unit.

[0007] With this configuration, the information generation system of the present invention generates a template corresponding to the format of a document based on an image of the document, information generated from the image of the document by the general-purpose information generation unit, and a template managed by the template management unit, thereby eliminating the need to manually create a template corresponding to the format of the document. In other words, the information generation system of the present invention can facilitate the creation of a template for generating specific information from an image of a document.

[0008] In the information generation system of the present invention, the generic information generation unit may generate the information from the image by using a service external to the information generation system that generically generates the information from the image independent of the format.

[0009] With this configuration, the information generation system of the present invention can reduce the burden on the provider or user of the information generation system, since a learning model for generating specific information from a document image does not need to be generated in advance by the provider or user of the information generation system.

[0010] The workflow system of the present invention includes a workflow generation unit that generates a workflow indicating a series of processes by linking any of a plurality of blocks each indicating a specific process, and a workflow execution unit that executes the process indicated in the workflow generated by the workflow generation unit, wherein the workflow generation unit is capable of generating the workflow that realizes a document classification unit that classifies the documents according to their formats, a template type information generation unit that generates the information from the images of the documents using a template for generating specific information from the images of the documents, a generic type information generation unit that generates the information generically from the images independent of the format, and a template generation unit that generates the templates, and the template type information generation unit generates the templates by classifying the font of the documents corresponding to the images. When a format of the document corresponding to the image is specified by the document classification unit, and the template corresponding to the format specified by the document classification unit is managed in a template management unit that manages the templates, the template generation unit generates the information from the image using the template managed in the template management unit that corresponds to the format specified by the document classification unit, and when the format of the document corresponding to the image is specified by the document classification unit, and when the information is generated from the image by the general-purpose information generation unit, the template generation unit generates the template corresponding to the format specified by the document classification unit based on the image, the information, and the template managed in the template management unit.

[0011] With this configuration, the workflow system of the present invention can generate a template corresponding to the format of a document based on an image of the document, information generated from the image of the document by the general-purpose information generation unit, and a template managed by the template management unit, eliminating the need to manually create a template corresponding to the format of the document. In other words, the workflow system of the present invention can facilitate the creation of a template for generating specific information from an image of a document.

[0012] An information generation program of the present invention causes a computer to realize a document classification unit that classifies documents according to their format, a template information generation unit that generates the information from the image of the document using a template for generating specific information from the image of the document, a generic information generation unit that generates the information from the image in a generic manner independent of the format, and a template generation unit that generates the template, wherein when the format of the document corresponding to the image is identified by the document classification unit, and the template corresponding to the format identified by the document classification unit is managed in a template management unit that manages the templates, the template information generation unit generates the information from the image using the template corresponding to the format identified by the document classification unit, among the templates managed in the template management unit, and when the format of the document corresponding to the image is identified by the document classification unit, and when the information is generated by the generic information generation unit from the image, the template generation unit generates the template corresponding to the format identified by the document classification unit, based on the image, the information, and the template managed in the template management unit.

[0013] With this configuration, the computer executing the information generation program of the present invention generates a template corresponding to the format of this document based on the image of the document, information generated from the image of this document by the general-purpose information generation unit, and the template managed by the template management unit, eliminating the need to manually create a template corresponding to the format of this document. In other words, the computer executing the information generation program of the present invention can facilitate the creation of a template for generating specific information from an image of a document.

[0014] A workflow program of the present invention causes a computer to realize a workflow generation unit that generates a workflow indicating a series of processes by linking any of a plurality of blocks each indicating a specific process, and a workflow execution unit that executes the processes indicated in the workflow generated by the workflow generation unit, the workflow generation unit being capable of generating the workflow that realizes a document classification unit that classifies the document according to a document format, a template type information generation unit that generates information from the image using a template for generating specific information from an image of the document, a generic type information generation unit that generates the information generically from the image independent of the format, and a template generation unit that generates the template, and the template type information generation unit generates the document corresponding to the image. when the format of the document corresponding to the image is specified by the document classification unit, and the template corresponding to the format specified by the document classification unit is managed in a template management unit that manages the templates, the template corresponding to the format specified by the document classification unit is used among the templates managed in the template management unit to generate the information from the image, and when the format of the document corresponding to the image is specified by the document classification unit, when the information is generated from the image by the general-purpose information generation unit, the template generation unit generates the template corresponding to the format specified by the document classification unit based on the image, the information, and the template managed in the template management unit.

[0015] With this configuration, the computer executing the workflow program of the present invention can generate a template corresponding to the format of this document based on an image of the document, information generated from the image of this document by the general-purpose information generation unit, and templates managed by the template management unit, eliminating the need to manually create a template corresponding to the format of this document. In other words, the computer executing the workflow program of the present invention can facilitate the creation of templates for generating specific information from an image of a document. Effect of the Invention

[0016] The information generation system, workflow system, information generation program, and workflow program of the present invention can facilitate the creation of a template for generating specific information from an image of a document. [Brief description of the drawings]

[0017] [Figure 1] 1 is a block diagram of an information processing system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram of the information generating system shown in FIG. 1 when configured by one computer. [Diagram 3] FIG. 2 is a block diagram of the image reading device shown in FIG. 1 when it is an MFP. [Figure 4] FIG. 2 is a block diagram of a user terminal shown in FIG. [Diagram 5] 3 is a flowchart of the operation of the information generating system shown in FIG. 2 when generating specific information from an invoice image. [Figure 6] 3 is a flowchart of the operation of the information generating system shown in FIG. 2 when generating specific information from an invoice image using a template. [Figure 7] 6 is a flowchart of the template generation process shown in FIG. 5. [Figure 8]3 is a flowchart of the operation of the information generating system shown in FIG. 2 when generating a template from an invoice image. [Figure 9] FIG. 3 is a block diagram of a workflow system that realizes the information generating system shown in FIG. 2. [Figure 10] 2 is a diagram showing an example of a workflow shown on a workflow generation screen displayed on a display unit of the user terminal shown in FIG. 1. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0019] First, a configuration of an information processing system according to an embodiment of the present invention will be described.

[0020] FIG. 1 is a block diagram of an information processing system 10 according to the present embodiment.

[0021] As shown in FIG. 1, information processing system 10 includes an information generating system 20 that generates specific information (hereinafter referred to as "specific information") including information extracted from an image of an invoice as a document (hereinafter referred to as "invoice image"), an image reading device 30 that reads an invoice image from an actual invoice (hereinafter referred to as "actual invoice") formed from a recording medium such as paper, and a user terminal 40 used by a user of information processing system 10. Information processing system 10 may include at least one image reading device similar to image reading device 30 other than image reading device 30. Information processing system 10 may include at least one user terminal similar to user terminal 40 other than user terminal 40.

[0022] The specific information is information in which an item name and a value are associated with each other for each item.

[0023] The information generating system 20 may be configured with one computer, or may be configured with multiple computers.

[0024] The image reading device 30 is, for example, a dedicated scanner, an MFP (Multifunction Peripheral), or the like.

[0025] The user terminal 40 is configured, for example, by a computer such as a PC (Personal Computer).

[0026] The information generating system 20 and the image reading device can communicate with each other via a network such as a LAN (Local Area Network) or the Internet, or directly by wire or wirelessly without a network. Similarly, the information generating system 20 and the user terminal can communicate with each other via a network such as a LAN or the Internet, or directly by wire or wirelessly without a network.

[0027] FIG. 2 is a block diagram of an information generation system 20 configured by one computer.

[0028] The information generation system 20 shown in Figure 2 includes an operation unit 21 which is an operation device such as a keyboard or mouse through which various operations are input, a display unit 22 which is a display device such as an LCD (Liquid Crystal Display) that displays various information, a communication unit 23 which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly by wired or wireless means without going through a network, a memory unit 24 which is a non-volatile memory device such as a semiconductor memory or an HDD (Hard Disk Drive) that stores various information, and a control unit 25 which controls the entire information generation system 20.

[0029] The storage unit 24 stores an information generating program 24a for generating specific information. The information generating program 24a may be installed in the information generating system 20 during the manufacturing stage of the information generating system 20, or may be additionally installed in the information generating system 20 from an external storage medium such as a USB (Universal Serial Bus) memory, or may be additionally installed in the information generating system 20 from a network.

[0030] The storage unit 24 can store an invoice classification model 24b as a learning model for classifying invoices according to their formats (hereinafter simply referred to as "formats"). The invoice classification model 24b is created by machine learning.

[0031] The storage unit 24 can store a template database 24c that stores templates for generating specific information from an invoice image. The template database 24c manages templates for each format and constitutes a template management unit of the present invention. The template includes, for each item of information to be extracted from the invoice image, an anchor that is a reference for the position where information is extracted from the invoice image, the position (hereinafter referred to as the "anchor area position") of the area where the anchor exists (hereinafter referred to as the "anchor area"), and the position (hereinafter referred to as the "extraction area position") of the area where the information to be extracted from the invoice image exists (hereinafter referred to as the "extraction area") relative to the anchor. Here, the anchor may be, for example, a specific character string or a specific image such as a logo. The template is defined in, for example, XML (Extensible Markup Language) format.

[0032] The storage unit 24 can store an information generation model 24d as a learning model for generating specific information from an invoice image. The information generation model 24d is created by machine learning. The information generation model 24d is a general-purpose learning model that does not depend on a format, and can extract information from an invoice image and the position of the information on the invoice image.

[0033] The storage unit 24 can store a dictionary 24e showing various expressions of the item names of information extracted from an invoice image. For example, the dictionary 24e shows "invoice_no" and "invoice_number" as the item names of an item showing an "invoice number", shows "invoice_date" as the item name of an item showing an "invoice date", and shows "total_amount" and "total" as the item names of an item showing an "invoice amount".

[0034] The control unit 25 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory) that stores programs and various data, and a RAM (Random Access Memory) that serves as a memory used as a working area for the CPU of the control unit 25. The CPU of the control unit 25 executes programs stored in the storage unit 24 or the ROM of the control unit 25.

[0035] By executing the information generation program 24a, the control unit 25 realizes an invoice classification unit 25a as a document classification unit that classifies invoices by format, a template-type information generation unit 25b that generates specific information from an invoice image using a template, a general-purpose information generation unit 25c that generates specific information generically from an invoice image independent of the format, and a template generation unit 25d that generates templates.

[0036] FIG. 3 is a block diagram of the image reading device 30 in the case of an MFP.

[0037] The image reading device 30 shown in Figure 3 is equipped with an operation unit 31 which is an operating device such as buttons through which various operations are input, a display unit 32 which is a display device such as an LCD that displays various information, a printer 33 which is a printing device that prints images on a recording medium such as paper, a scanner 34 which is a reading device that reads images from a document, a fax communication unit 35 which is a fax device that performs fax communication with an external facsimile machine not shown via a communication line such as a public telephone line, a communication unit 36 ​​which is a communication device that communicates with an external device via a network such as a LAN or the Internet, or directly by wired or wireless means without using a network, a memory unit 37 which is a non-volatile memory device such as a semiconductor memory or HDD that stores various information, and a control unit 38 which controls the entire image reading device 30.

[0038] The control unit 38 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM as a memory used as a working area for the CPU of the control unit 38. The CPU of the control unit 38 executes the programs stored in the storage unit 37 or the ROM of the control unit 38.

[0039] FIG. 4 is a block diagram of the user terminal 40. As shown in FIG.

[0040] The user terminal 40 shown in Figure 4 is equipped with an operation unit 41 which is an operating device such as a keyboard or mouse through which various operations are input, a display unit 42 which is a display device such as an LCD that displays various information, a communication unit 43 which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly by wired or wireless means without going through a network, a memory unit 44 which is a non-volatile memory device such as a semiconductor memory or HDD that stores various information, and a control unit 45 which controls the entire user terminal 40.

[0041] The control unit 45 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM as a memory used as a working area for the CPU of the control unit 45. The CPU of the control unit 45 executes the programs stored in the storage unit 44 or the ROM of the control unit 45.

[0042] Next, the operation of the information processing system 10 will be described.

[0043] First, the operation of the information generating system 20 when generating specific information from an invoice image will be described.

[0044] FIG. 5 is a flowchart showing the operation of the information generating system 20 when generating specific information from an invoice image.

[0045] A user can set an actual invoice on the scanner of an image reading device and instruct the image reading device to generate specific information from the actual invoice, for example, via an operation unit of the image reading device. When instructed to generate specific information from the actual invoice, the control unit of the image reading device reads an invoice image from the actual invoice set in the scanner of the image reading device with the scanner, and instructs information generation system 20 via a communication unit of the image reading device to generate specific information from the invoice image. Here, the instruction to generate specific information from the invoice image (hereinafter referred to as an "information generation instruction") includes the invoice image that is the subject of the information generation instruction. When the control unit 25 of information generation system 20 receives the information generation instruction via communication unit 23, it executes the operation shown in FIG. 5.

[0046] As shown in FIG. 5, the invoice classification unit 25a identifies the format of the invoice corresponding to the invoice image that is the target of the information generation instruction, based on this invoice image, by using the invoice classification model 24b (S101).

[0047] Next, template type information generating unit 25b determines whether or not a template corresponding to the format identified in S101 exists in template database 24c (S102).

[0048] When the template type information generating unit 25b determines in S102 that a template corresponding to the format specified in S101 exists in the template database 24c, the template corresponding to the format specified in S101 among the templates stored in the template database 24c is used to generate specific information from the invoice image that is the target of the information generation instruction (S103). For example, if "invoice_number", "invoice_date", and "total" are defined as the item names of the items indicating "invoice number", "invoice date", and "invoice amount", respectively, in the template corresponding to the format specified in S101 among the templates stored in the template database 24c, the template type information generating unit 25b generates specific information in S103 by extracting the values ​​of each item and associating the extracted values ​​with the item names defined in the template.

[0049] FIG. 6 is a flowchart showing the operation of the information generating system 20 when generating specific information from an invoice image using a template.

[0050] As shown in FIG. 6, template type information generating unit 25b targets one item that has not yet been targeted in the current operation shown in FIG. 6, among the items included in the target template (S121).

[0051] Next, the template type information generating unit 25b detects, in the target invoice image, an anchor included in the target template for the current target item from an anchor region included in the target template for the current target item (S122).

[0052] Next, the template type information generating unit 25b identifies an extraction area for the current target item in the target invoice image based on the anchor detected in S122 and the extraction area position for the current target item included in the target template (S123).

[0053] Next, the template type information generating unit 25b extracts information from the extraction area specified in S123 in the target invoice image (S124).

[0054] Next, template type information generating unit 25b associates the information extracted in S124 with the item name included in the target template for the current target item (S125).

[0055] Next, template type information generation unit 25b determines whether or not there is any item that has not yet been targeted in the current operation shown in FIG. 6, among the items included in the target template (S126).

[0056] When template type information generating unit 25b determines in S126 that there is an item that has not yet been targeted in the current operation shown in FIG. 6 among the items included in the target template, it executes the process of S121.

[0057] When template type information generating unit 25b determines in S126 that there is no item that has not yet been targeted in the current operation shown in FIG. 6 among the items included in the target template, it ends the operation shown in FIG.

[0058] 5, after the process of S103, the template type information generating unit 25b stores the specific information generated in S103 in the storage unit 24 in association with the format specified in S101 and the invoice image that is the target of the information generation instruction (S104). Therefore, by accessing the information generating system 20 using, for example, a user terminal, the user can check the specific information stored in the storage unit 24 via the display unit of the user terminal, and can modify this specific information via the operation unit of the user terminal as necessary.

[0059] After the process of S104, template type information generating unit 25b ends the operation shown in FIG.

[0060] When it is determined in S102 that the template database 24c does not contain a template corresponding to the format identified in S101, the general-purpose information generating unit 25c generates specific information from the invoice image that is the target of the information generation instruction by using the information generation model 24d (S105). For example, when "invoice_no", "invoice_date", and "total_amount" are defined in the information generation model 24d as the item names of the items indicating "invoice number", "invoice date", and "invoice amount", respectively, the general-purpose information generating unit 25c extracts the values ​​of each item in S105 and generates specific information by associating the extracted values ​​with the item names defined in the information generation model 24d.

[0061] After the process of S105, the general-purpose information generating unit 25c stores the specific information generated in S105 in the storage unit 24 in association with the format specified in S101 and the invoice image that is the target of the information generation instruction (S106). Therefore, by accessing the information generating system 20 using, for example, a user terminal, the user can check the specific information stored in the storage unit 24 via the display unit of the user terminal, and can modify this specific information via the operation unit of the user terminal as necessary.

[0062] After the process of S106, template generating unit 25d executes a template generating process for generating a template based on the specific information generated in S105 (S107).

[0063] FIG. 7 is a flowchart of the template generation process shown in FIG.

[0064] 7, template generation unit 25d acquires item names from all templates stored in template database 24c (S141). For example, if "invoice_number", "invoice_date", and "total" are defined as the item names of the items indicating "invoice number", "invoice date", and "invoice amount" in the templates stored in template database 24c, template generation unit 25d acquires "invoice_number", "invoice_date", and "total" in S141.

[0065] After the process of S141, the template generation unit 25d acquires the item names in the specific information generated in S105 using the information generation model 24d (S142). For example, in S142, the template generation unit 25d acquires “invoice_no”, “invoice_date”, and “total_amount”.

[0066] After the process of S142, the template generation unit 25d identifies, based on the dictionary 24e, among the item names acquired in S142, i.e., the item names in the specific information generated using the information generation model 24d, those that correspond to the item names acquired in S141, i.e., any of the item names acquired from all the templates (S143). For example, the template generation unit 25d identifies that the item names "invoice_no", "invoice_date", and "total_amount" acquired in S142 correspond to the item names "invoice_number", "invoice_date", and "total" acquired in S141, respectively.

[0067] After the process of S143, the template generating unit 25d specifies an anchor, an anchor region position, and an extraction region position for each item name specified in S143 from the invoice image that is the target of the information generation instruction (S144). Here, if any character string indicated in the dictionary 24e for the target item name exists in the invoice image that is the target of the information generation instruction, the template generating unit 25d may set the character string as the anchor. If any character string indicated in the dictionary 24e for the target item name does not exist in the invoice image that is the target of the information generation instruction, the template generating unit 25d may set some information, such as a logo, that exists in this invoice image as the anchor. In addition, the template generating unit 25d sets a specific region including the region from which the value of each item is extracted in S105 from the invoice image that is the target of the information generation instruction as the extraction region.

[0068] After the processing of S144, template generation unit 25d generates a template by including, for each item, the item name identified in S143 converted into the item name acquired in S141, and the anchor, anchor region position, and extraction region position identified in S144 (S145), and terminates the template generation process shown in FIG. 7.

[0069] As shown in FIG. 5, after the template generation process of S107, the template generation unit 25d stores the template generated in S107 in the template database 24c as a template of the format specified in S101 (S108). Therefore, the user can check the template stored in the template database 24c via the display unit of the user terminal by accessing the information generation system 20 using, for example, a user terminal, and can modify this template via the operation unit of the user terminal as necessary. Note that the template stored in the template database 24c in S108 is in a provisionally registered state. When checking this template via the display unit of the user terminal, the user can change the state of this template to a fully registered state via the operation unit of the user terminal. When a provisionally registered template is stored in the template database 24c, the template generation unit 25d can notify a specific contact of an instruction to prompt the user to change the state of this template to a fully registered state.

[0070] After the process of S108, template generating unit 25d ends the operation shown in FIG.

[0071] Next, the operation of the information generating system 20 when generating a template from a bill image will be described.

[0072] FIG. 8 is a flowchart showing the operation of the information generating system 20 when generating a template from an invoice image.

[0073] A user can set an actual bill on the scanner of an image reading device and instruct the image reading device to generate a template from the actual bill, for example, via an operation unit of the image reading device. When instructed to generate a template from the actual bill, the control unit of the image reading device reads an invoice image from the actual bill set in the scanner of the image reading device with the scanner, and instructs the information generation system 20 via the communication unit of the image reading device to generate a template from the invoice image. Here, the instruction to generate a template from a invoice image (hereinafter referred to as a "template generation instruction") includes the invoice image that is the target of the template generation instruction. When the control unit 25 of the information generation system 20 receives the template generation instruction via the communication unit 23, it executes the operation shown in FIG. 8.

[0074] As shown in FIG. 8, the invoice classification unit 25a identifies the format of the invoice corresponding to the invoice image for which a template generation instruction is issued, based on this invoice image, by using the invoice classification model 24b (S161).

[0075] Next, the general-purpose information generating unit 25c generates specific information from the invoice image that is the target of the template generation instruction by using the information generation model 24d, similar to the process of S105 (S162).

[0076] Next, template generating unit 25d executes a template generating process for generating a template, similar to the process of S107, based on the identification information generated in S162 (S163).

[0077] Next, template generation unit 25d stores the template generated in S163 in storage unit 24 as a template candidate for the format identified in S161 (hereinafter referred to as the "template candidate") (S164). Therefore, a user can access information generation system 20 using a user terminal, for example, to check the template candidate stored in storage unit 24 via a display unit of the user terminal, and can modify this template candidate via an operation unit of the user terminal as necessary. When checking this template candidate via the display unit of the user terminal, the user can instruct information generation system 20, for example via the operation unit of the user terminal, to adopt this template candidate as a template.

[0078] After the process of S164, template generation unit 25d determines whether or not an instruction has been given to adopt the template candidate saved in S164 as a template (S165) until it determines that an instruction has been given to adopt the template candidate saved in S164 as a template.

[0079] If template generation unit 25d determines in S165 that an instruction has been given to adopt the template candidate saved in S164 as a template, it stores the template candidate saved in S164 in template database 24c as a template of the format specified in S161 (S166), and then ends the operation shown in FIG. 8.

[0080] As described above, the information generating system 20 generates a template corresponding to the format of the invoice corresponding to the invoice image based on the invoice image, the specific information generated from the invoice image by the general-purpose information generating unit 25c, and the template managed in the template database 24c (S107 and S163), thereby eliminating the need to manually create a template corresponding to the invoice format. In other words, the information generating system 20 can facilitate the creation of a template for generating specific information from an invoice image.

[0081] Even if a template corresponding to the invoice format corresponding to the invoice image that is the subject of the information generation instruction does not exist in the template database 24c (NO in S102), the information generation system 20 generates specific information from the invoice image using the general-purpose information generation unit 25c (S105), thereby eliminating the need to generate specific information from the invoice image solely by manual effort, and as a result, the time required to generate specific information from the invoice image can be shortened.

[0082] The information generating system 20 may be realized by a workflow system 50 (see FIG. 9) that executes processes indicated in a workflow indicating a series of processes. The workflow system 50 may be configured by one computer as shown in FIG. 9, or may be configured by multiple computers.

[0083] FIG. 9 is a block diagram of a workflow system 50 that realizes the information generating system 20. As shown in FIG.

[0084] The workflow system 50 shown in Figure 9 comprises an operation unit 51 which is an operating device such as a keyboard or mouse through which various operations are input, a display unit 52 which is a display device such as an LCD that displays various information, a communication unit 53 which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly via wired or wireless communication without going through a network, a memory unit 54 which is a non-volatile memory device such as a semiconductor memory or HDD that stores various information, and a control unit 55 which controls the entire workflow system 50.

[0085] The storage unit 54 stores a workflow program 54a for executing the processing indicated in the workflow. The workflow program 54a may be installed in the workflow system 50 during the manufacturing stage of the workflow system 50, or may be additionally installed in the workflow system 50 from an external storage medium such as a USB memory, or may be additionally installed in the workflow system 50 from a network.

[0086] The storage unit 54 is capable of storing an invoice classification model 24b, a template database 24c, an information generation model 24d, and a dictionary 24e.

[0087] The control unit 55 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM as a memory used as a working area for the CPU of the control unit 55. The CPU of the control unit 55 executes the programs stored in the storage unit 54 or the ROM of the control unit 55.

[0088] By executing workflow program 54a, control unit 55 realizes workflow generation unit 55a that generates a workflow by linking any blocks out of a plurality of blocks, each of which indicates a specific process, and workflow execution unit 55b that executes the process indicated in the workflow generated by workflow generation unit 55a.

[0089] In the workflow system 50, the generation of a workflow can be instructed by a user via, for example, an operation unit of a user terminal. For example, the workflow generation unit 55a can display a workflow generation screen for generating a workflow on the display unit of the user terminal, and can generate a workflow that realizes the invoice classification unit 25a, the template information generation unit 25b, the general-purpose information generation unit 25c, and the template generation unit 25d in response to an instruction from the user via the operation unit of the user terminal to the workflow generation screen. That is, the workflow generation unit 55a can generate a workflow that realizes the operation shown in FIG. 5 and a workflow that realizes the operation shown in FIG. 8.

[0090] FIG. 10 is a diagram showing an example of a workflow displayed on a workflow generation screen displayed on a display unit of a user terminal.

[0091] The workflow 60 shown in Fig. 10 is an example of a workflow that realizes the operation shown in Fig. 5. The workflow 60 is generated by linking a block 61 indicating input of an invoice image from an image reading device, a block 62 indicating the processes of S101 to S103, a block 63 indicating the process of S104, a block 64 indicating the storage unit 24, a block 65 indicating the process of S105, a block 66 indicating the process of S106, a block 67 indicating the storage unit 24, a block 68 indicating the process of S107, a block 69 indicating the process of S108, and a block 70 indicating the template database 24c.

[0092] In the workflow system 50 shown in FIG. 9, the workflow generated by the workflow generation unit 55a can be confirmed by a user via a display unit of the image reading device, and the execution of the workflow generated by the workflow generation unit 55a can be instructed by the user via an operation unit of the image reading device.

[0093] A user can set an actual invoice in the scanner of an image reading device, and instruct the image reading device, for example, via an operation unit of the image reading device, to execute a workflow that realizes the operations shown in Fig. 5. When the control unit of the image reading device is instructed to execute the workflow, the control unit reads an invoice image from the actual invoice set in the scanner of the image reading device, using the scanner, and transmits the read invoice image and an instruction to execute the workflow to workflow system 50 via the communication unit of the image reading device. When the workflow execution instruction is received via communication unit 23, workflow execution unit 55b of workflow system 50 realizes the operations shown in Fig. 5.

[0094] Similarly, a user can set an actual invoice in the scanner of an image reading device, and instruct the image reading device, for example, via an operation unit of the image reading device, to execute a workflow that realizes the operations shown in Fig. 8. When the control unit of the image reading device is instructed to execute the workflow, the control unit reads an invoice image from the actual invoice set in the scanner of the image reading device, using the scanner, and transmits the read invoice image and an instruction to execute the workflow to workflow system 50 via the communication unit of the image reading device. When the workflow execution instruction is received via communication unit 23, workflow execution unit 55b of workflow system 50 realizes the operations shown in Fig. 8.

[0095] In the above description, the general-purpose information generating unit 25c generates specific information from an invoice image using the information generation model 24d (S105 and S162). However, the general-purpose information generating unit 25c may generate specific information from an invoice image without using the information generation model 24d. For example, the general-purpose information generating unit 25c may generate specific information from an invoice image using a service external to the information generating system 20, such as a cloud service that generically generates specific information from an invoice image independent of a format. When the general-purpose information generating unit 25c generates specific information from an invoice image using a service external to the information generating system 20, the information generating system 20 can reduce the burden on the provider or user of the information generating system 20 because the information generation model 24d does not need to be generated in advance by the provider or user of the information generating system 20. In addition, in the information generating system 20, the template generating unit 25d generates a template based on the specific information generated from the invoice image by the general-purpose information generating unit 25c. Therefore, when the general-purpose information generating unit 25c generates specific information from an invoice image using a service external to the information generating system 20, even if a usage fee must be paid to the external service provider in accordance with the use of the external service, the number of times that the general-purpose information generating unit 25c generates specific information from an invoice image using a service external to the information generating system 20 can be reduced, and as a result, the usage fee paid to the external service provider can be reduced.

[0096] In the above description, the template generating unit 25d identifies, among the item names in the specific information generated by the generalized information generating unit 25c, those that correspond to any of the item names acquired from all the templates stored in the template database 24c, based on the dictionary 24e (S143). However, the template generating unit 25d may identify, among the item names in the specific information generated by the generalized information generating unit 25c, those that correspond to any of the item names acquired from all the templates stored in the template database 24c, without using the dictionary 24e. For example, the template generating unit 25d may identify, among the item names in the specific information generated by the generalized information generating unit 25c, those that correspond to any of the item names acquired from all the templates stored in the template database 24c, by using a learning model created by machine learning.

[0097] In the above, an invoice has been described as an example of a document. However, the present invention can be applied to documents other than invoices. For example, the present invention can be applied to various forms such as estimates, receipts, and delivery slips. [Explanation of symbols]

[0098] 20 Information Generation System 24a Information Generation Program 24c Template Database (Template Management Department) 25a Bill classification section (document classification section) 25b Template type information generation unit 25c General-purpose information generation unit 25d Template Generation Unit 50 Workflow System 54a Workflow Program 55a Workflow Generation Unit 55b Workflow Execution Department

Claims

1. a template generating unit for generating a template for generating specific information including information extracted from an image of a document; an information generating unit that generates the specific information from the image without using the template; Equipped with the template generation unit generates a new template based on the image, the specific information generated from the image by the information generation unit, and the template managed by a template management unit that manages the template.

2. The specific information has an item name and a value associated with each item, the template includes, for each of the items of information, a name of the item of information and a location of an area in which the information exists; 2. The information generation system according to claim 1, wherein the template generation unit generates the new template by including, for each item, an item name in the specific information generated from the image by the information generation unit, which is converted into the item name included in the template managed by the template management unit.

3. 3. The information generation system according to claim 2, wherein the template generation unit generates the new template by including, for each item, an item name in the specific information generated from the image by the information generation unit, converted based on a dictionary into the item name included in the template managed by the template management unit.

4. the template includes an anchor for each item of information that is a reference for a position at which the information is extracted from the image; the location of the region included in the template is relative to the anchor; 4. The information generating system according to claim 3, wherein, when a character string indicated in the dictionary for the item name exists in the image, the template generating unit sets the character string as the anchor.

5. 3. The information generation system according to claim 2, wherein the template generation unit generates the new template by including, for each item, the item names in the specific information generated by the information generation unit from the image, which are converted using a learning model, in the item names contained in the template managed by the template management unit.

6. The information generating system according to claim 1 , wherein the information generating unit generates the specific information from the image by using a learning model.

7. The information generating system according to claim 1 , wherein the information generating unit generates the specific information from the image by using a service external to the information generating system.

8. a workflow generating unit that generates a workflow indicating a series of processes by linking arbitrary blocks among a plurality of blocks each indicating a specific process; a workflow execution unit that executes a process indicated in the workflow generated by the workflow generation unit; Equipped with The workflow generation unit a template generating unit for generating a template for generating specific information including information extracted from an image of a document; an information generating unit that generates the specific information from the image without using the template; The workflow may be generated to achieve the above. the template generation unit generates a new template based on the image, the specific information generated from the image by the information generation unit, and the template managed by a template management unit that manages the templates.

9. a template generating unit for generating a template for generating specific information including information extracted from an image of a document; an information generating unit that generates the specific information from the image without using the template; By implementing this on a computer, the template generation unit generates a new template based on the image, the specific information generated from the image by the information generation unit, and the template managed by a template management unit that manages the template.

10. a workflow generating unit that generates a workflow indicating a series of processes by linking arbitrary blocks among a plurality of blocks each indicating a specific process; a workflow execution unit that executes a process indicated in the workflow generated by the workflow generation unit; By implementing this on a computer, The workflow generation unit a template generating unit for generating a template for generating specific information including information extracted from an image of a document; an information generating unit that generates the specific information from the image without using the template; The workflow may be generated to achieve the above. the template generation unit generates a new template based on the image, the specific information generated from the image by the information generation unit, and the template managed by a template management unit that manages the template.

Images