Information generation system, workflow system, and recording medium

Through the design information generation system, including document classification, template generation and general information generation functions, the problem of generating specific information templates in the prior art is solved for a long time, and the function of quickly generating templates is realized, which improves efficiency.

CN114970483BActive Publication Date: 2025-02-14KYOCERA DOCUMENT SOLUTIONS INC
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202210144563.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2021-02-22
Filing Date
2022-02-16
Publication Date
2025-02-14
Estimated Expiration
2042-02-16

AI Technical Summary

Technical Problem

In the prior art, it takes a long labor time to produce a template for generating specific information from a document image.

Method used

An information generation system was designed, including a document classification unit, a template type information generation unit, a general type information generation unit and a template generation unit. By classifying documents, and using the template database and information generation model to generate specific information and templates, it realizes that The ability to quickly generate templates.

Benefits of technology

The system can quickly generate templates corresponding to the document format, reducing the need for manual template creation, improving efficiency, and shortening generation time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114970483B_ABST
    Figure CN114970483B_ABST
Patent Text Reader

Abstract

The present invention provides an information generation system, a workflow system and a recording medium. When a template corresponding to the format of an invoice corresponding to an invoice image is managed in a template database, the information generation system generates information based on the invoice image using the template, and when a general type information generation unit generates information based on the invoice image, a template corresponding to the format of the invoice corresponding to the invoice image is generated based on the invoice image, the information and the template managed in the template database.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to an information generation system for generating specific information based on an image of a document, a workflow system, a computer-readable non-transitory recording medium storing an information generation program, and a computer-readable non-transitory recording medium storing a workflow program. Background Art

[0002] Conventionally, there is known a technique for performing character recognition (character extraction and analysis) at a position specified by a template in which the position of the written character on the paper is predefined. This technique recognizes the form ID of the imaged digitized document by printing or writing a form ID as an identifier of template definition information on the paper, and performs OCR (Optical Character Recognition) processing using the corresponding template.

[0003] However, in the prior art, there is a problem that it takes a lot of time to create a template for generating specific information from an image of a document. Summary of the invention

[0004] The object of the present invention is to provide an information generation system, a workflow system, a computer-readable non-temporary recording medium storing an information generation program, and a computer-readable non-temporary recording medium storing a workflow program that can easily produce a template for generating specific information based on an image of a document.

[0005] The present invention provides an information generation system, characterized in that it includes: a document classification unit, which classifies the documents according to the formats of the documents; a template type information generation unit, which generates the information according to the image using a template for generating specific information according to the image of the document; a general type information generation unit, which generates the information according to the image in a general manner without depending on the format; and a template generation unit, which generates the template, wherein when the format of the document corresponding to the image is determined by the document classification unit, when the template corresponding to the format determined by the document classification unit is managed in a template management unit that manages the template, the template type information generation unit generates the information according to the image using the template corresponding to the format determined by the document classification unit among the templates managed by the template management unit, and wherein when the general type information generation unit generates the information according to the image, the template generation unit generates the template corresponding to the format determined by the document classification unit based on the image, the information and the template managed by the template management unit.

[0006] The present invention provides a workflow system, characterized in that it includes: a workflow generation unit, which generates a workflow representing a series of processes by connecting any of a plurality of blocks that respectively represent specific processes; and a workflow execution unit, which executes the processes shown in the workflow generated by the workflow generation unit, the workflow generation unit is capable of generating the workflow that implements a document classification unit, a template type information generation unit, a general type information generation unit, and a template generation unit, the document classification unit classifies the document according to the format of the document, the template type information generation unit uses a template for generating specific information based on an image of the document, and generates the information based on the image, the general type information generation unit generates the information universally based on the image without relying on the format, and the template The generating unit generates the template, and when the format of the document corresponding to the image is determined by the document classification unit, and when the template corresponding to the format determined by the document classification unit is managed in the template management unit that manages the template, the template type information generating unit uses the template corresponding to the format determined by the document classification unit among the templates managed by the template management unit to generate the information according to the image; when the format of the document corresponding to the image is determined by the document classification unit, and when the general type information generating unit generates the information according to the image, the template generating unit generates the template corresponding to the format determined by the document classification unit based on the image, the information and the template managed by the template management unit.

[0007] The present invention provides a recording medium, which is a computer-readable non-temporary recording medium storing an information generation program, characterized in that the information generation program enables a computer to implement a document classification unit, a template type information generation unit, a general type information generation unit, and a template generation unit, wherein the document classification unit classifies the document according to the format of the document, the template type information generation unit uses a template for generating specific information based on an image of the document to generate the information based on the image, the general type information generation unit generates the information based on the image in a general manner without relying on the format, the template generation unit generates the template, and the template type information generation unit generates the template after the document classification unit determines that the information is related to the document. In the case of the format of the document corresponding to the image, when the template corresponding to the format determined by the document classification unit is managed in the template management unit that manages the template, the information is generated according to the image using the template corresponding to the format determined by the document classification unit among the templates managed by the template management unit, and in the case of the format of the document corresponding to the image determined by the document classification unit, when the general type information generation unit generates the information according to the image, the template generation unit generates the template corresponding to the format determined by the document classification unit based on the image, the information and the template managed by the template management unit.

[0008] The present invention provides a recording medium, which is a computer-readable non-temporary recording medium storing a workflow program, characterized in that the workflow program enables a computer to implement a workflow generation unit and a workflow execution unit, the workflow generation unit generates a workflow representing a series of processes by connecting any of a plurality of blocks that respectively represent specific processes, the workflow execution unit executes the processes shown in the workflow generated by the workflow generation unit, the workflow generation unit is capable of generating the workflow that implements a document classification unit, a template type information generation unit, a general type information generation unit, and a template generation unit, the document classification unit classifies the document according to the format of the document, the template type information generation unit uses a template for generating specific information based on an image of the document, and generates the information based on the image, and the general type information generation unit does not rely on The information is generally generated according to the image according to the format, the template generating unit generates the template, and when the format of the document corresponding to the image is determined by the document classification unit, the template type information generating unit generates the information according to the image using the template corresponding to the format determined by the document classification unit among the templates managed by the template management unit, when the template corresponding to the format determined by the document classification unit is managed in the template management unit that manages the template, and when the format of the document corresponding to the image is determined by the document classification unit, the template generating unit generates the template corresponding to the format determined by the document classification unit based on the image, the information and the template managed by the template management unit.

[0009] The information generation system, workflow system, computer-readable non-transitory recording medium storing an information generation program, and computer-readable non-transitory recording medium storing a workflow program of the present invention can easily create a template for generating specific information based on an image of a document. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 This is a block diagram of an information processing system according to one embodiment of the present invention.

[0011] Figure 2 If it is composed of 1 computer Figure 1 Block diagram of the information generation system shown.

[0012] Figure 3 In the case of MFP Figure 1 A block diagram of an image reading device is shown.

[0013] Figure 4 yes Figure 1A block diagram of a user terminal is shown.

[0014] Figure 5 When generating specific information based on the invoice image Figure 2 Flowchart of the operation of the information generating system shown.

[0015] Figure 6 This is when using a template to generate specific information based on an invoice image. Figure 2 Flowchart of the operation of the information generating system shown.

[0016] Figure 7 yes Figure 5 Flowchart of template generation processing shown.

[0017] Figure 8 This is the case when the template is generated based on the invoice image Figure 2 Flowchart of the operation of the information generating system shown.

[0018] Fig. 9 is realized Figure 2 A block diagram of the workflow system of the information generation system shown.

[0019] Fig.10 It means in Figure 1 FIG. 1 is a diagram showing an example of a workflow shown on a workflow generation screen displayed on a display unit of a user terminal shown. DETAILED DESCRIPTION

[0020] Hereinafter, embodiments of the present invention will be described using the drawings.

[0021] First, the configuration of an information processing system according to an embodiment of the present invention will be described.

[0022] Figure 1 It is a block diagram of the information processing system 10 according to the present embodiment.

[0023] like Figure 1 As shown, the information processing system 10 includes: an information generation system 20 that generates specific information (hereinafter referred to as "specific information"), the 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 the invoice image from an actual invoice made of a recording medium such as paper (hereinafter referred to as "actual invoice"); and a user terminal 40 used by a user of the information processing system 10. The information processing system 10 may include at least one image reading device similar to the image reading device 30 in addition to the image reading device 30. The information processing system 10 may include at least one user terminal similar to the user terminal 40 in addition to the user terminal 40.

[0024] The specific information is information in which an item name and a value are associated with each item.

[0025] The information generating system 20 may be composed of one computer or a plurality of computers.

[0026] The image reading device 30 is constituted by, for example, a dedicated scanner, an MFP (Multifunction Peripheral), or the like.

[0027] The user terminal 40 is constituted by a computer such as a PC (Personal Computer).

[0028] The information generation system 20 and the image reading device can communicate via a network such as a LAN (Local Area Network) or the Internet, or can communicate directly via a wired or wireless connection without going through a network. Similarly, the information generation system 20 and the user terminal can communicate via a network such as a LAN or the Internet, or can communicate directly via a wired or wireless connection without going through a network.

[0029] Figure 2 This is a block diagram of the information generating system 20 when it is composed of one computer.

[0030] Figure 2 The information generating system 20 shown comprises: an operating unit 21, which is an operating device such as a keyboard and a mouse to which various operations are input; a display unit 22, which is a display device such as an LCD (Liquid Crystal Display) for displaying various information; a communication unit 23, which is a communication device that communicates with an external device via a network such as a LAN and the Internet, or directly communicates with an external device through a wired or wireless connection without going through a network; a storage unit 24, which is a non-volatile storage device such as a semiconductor memory and an HDD (Hard Disk Drive) for storing various information; and a control unit 25, which controls the information generating system 20 as a whole.

[0031] The storage unit 24 stores an information generation program 24a for generating specific information. The information generation program 24a can be installed in the information generation system 20 at the manufacturing stage of the information generation system 20, can be additionally installed in the information generation system 20 from an external storage medium such as a USB (Universal Serial Bus) memory, or can be additionally installed in the information generation system 20 from a network.

[0032] 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.

[0033] The storage unit 24 is capable of storing a template database 24c, which stores templates for generating specific information based on an invoice image. The template database 24c manages templates according to each format, and constitutes a template management unit of the present invention. In the template, each item of information extracted from the invoice image includes: the name of the item of information extracted from the invoice image; an anchor, which serves as a reference for the position of the information extracted from the invoice image; and the position of the area where the anchor exists (hereinafter referred to as the "anchor area"); and the position of the area where the information extracted from the invoice image exists (hereinafter referred to as the "extraction area") relative to the anchor (hereinafter referred to as the "extraction area position"). Here, the anchor can be, for example, a specific string of characters or a specific image such as a logo. The template is defined in, for example, XML (Extensible Markup Language) format.

[0034] 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 learning model that is not dependent on a format and can extract information from an invoice image and the position of the information on the invoice image.

[0035] The storage unit 24 can store a dictionary 24e that indicates various expressions of item names of information extracted from the invoice image. For example, the dictionary 24e indicates "invoice_no" and "invoice_number" as item names indicating an "invoice number", "invoice_date" as an item name indicating an "invoice date", and "total_amount" and "total" as item names indicating an "invoice amount".

[0036] The control unit 25 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory) storing programs and various data, and a RAM (Random Access Memory) serving as a memory used as a work area of ​​the CPU of the control unit 25. The CPU of the control unit 25 executes the program stored in the storage unit 24 or the ROM of the control unit 25.

[0037] The control unit 25 implements an invoice classification unit 25a as a document classification unit that classifies invoices according to formats, a template type information generation unit 25b that generates specific information from an invoice image using a template, a general type information generation unit 25c that universally generates specific information from an invoice image regardless of a format, and a template generation unit 25d that generates a template by executing the information generation program 24a.

[0038] Figure 3 It is a block diagram of the image reading device 30 in the case of MFP.

[0039] Figure 3 The image reading device 30 shown in the figure comprises: an operation unit 31, which is an operation device such as a button to 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 an image on a recording medium such as paper; a scanner 34, which is a reading device that reads an image from an original; a facsimile communication unit 35, which is a facsimile device that performs facsimile communication with an external facsimile device (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 communicates with an external device by wire or wirelessly without going through a network; a storage unit 37, which is a non-volatile storage device such as a semiconductor memory or HDD that stores various information; and a control unit 38 that controls the image reading device 30 as a whole.

[0040] The control unit 38 includes, for example, a CPU, a ROM storing programs and various data, and a RAM as a memory used as a work area of ​​the CPU of the control unit 38. The CPU of the control unit 38 executes the program stored in the storage unit 37 or the ROM of the control unit 38.

[0041] Figure 4 is a block diagram of the user terminal 40 .

[0042] Figure 4 The user terminal 40 shown comprises: an operation unit 41, which is an operation device such as a keyboard and a mouse to which various operations are input; a display unit 42, which is a display device such as an LCD to display various information; a communication unit 43, which is a communication device that communicates with an external device via a network such as a LAN and the Internet, or directly communicates with an external device by wire or wirelessly without going through a network; a storage unit 44, which is a non-volatile storage device such as a semiconductor memory, HDD, etc. to store various information; and a control unit 45, which controls the user terminal 40 as a whole.

[0043] The control unit 45 includes, for example, a CPU, a ROM storing programs and various data, and a RAM as a memory used as a work area of ​​the CPU of the control unit 45. The CPU of the control unit 45 executes the program stored in the storage unit 44 or the ROM of the control unit 45.

[0044] Next, the operation of the information processing system 10 will be described.

[0045] First, the operation of the information generating system 20 when generating specific information based on an invoice image will be described.

[0046] Figure 5 This is a flowchart of the operation of the information generating system 20 when generating specific information based on an invoice image.

[0047] The user can place the actual invoice on the scanner of the image reading device, and instruct the image reading device to generate specific information based on the actual invoice, for example, via the operating unit of the image reading device. When the control unit of the image reading device is instructed to generate specific information based on the actual invoice, it reads the invoice image from the actual invoice placed on the scanner of the image reading device through the scanner, and instructs the information generation system 20 to generate specific information based on the invoice image via the communication unit of the image reading device. Here, the instruction to generate specific information based on the invoice image (hereinafter referred to as "information generation instruction") includes the invoice image of the object of the information generation instruction. When the control unit 25 of the information generation system 20 receives the information generation instruction via the communication unit 23, it executes Figure 5 Action shown.

[0048] like Figure 5 As shown, the invoice classification unit 25a specifies the format of the invoice corresponding to the invoice image for which the information generation instruction is directed, based on the invoice image, using the invoice classification model 24b (S101).

[0049] Next, the template type information generating unit 25b determines whether or not a template corresponding to the format determined in S101 exists in the template database 24c (S102).

[0050] When it is determined in S102 that there is a template corresponding to the format determined in S101 in the template database 24c, the template type information generating unit 25b generates specific information based on the invoice image of the object of the information generation instruction using the template corresponding to the format determined in S101 among the templates stored in the template database 24c (S103). For example, in the template corresponding to the format determined in S101 among the templates stored in the template database 24c, when "invoice_number", "invoice_date", and "total" are defined as item names representing items of "invoice number", "invoice date", and "invoice amount", respectively, the template type information generating unit 25b extracts the value of each item in S103, associates the extracted value with the item name defined in the template, and generates specific information.

[0051] Figure 6 This is a flowchart of the operation of the information generating system 20 when generating specific information from an invoice image using a template.

[0052] like Figure 6 As shown, the template type information generating unit 25b generates the items included in the template of the object in this Figure 6 In the operation shown, one item that has not been targeted is targeted (S121).

[0053] Next, the template type information generating unit 25b detects the anchors included in the target template for the current target item from the anchor region included in the target template for the current target item in the target invoice image (S122).

[0054] Next, the template type information generating unit 25b specifies the extraction region for the current target item in the target invoice image based on the anchor detected in S122 and the extraction region position of the current target item included in the target template (S123).

[0055] Next, the template type information generating unit 25b extracts information from the extraction area determined in S123 in the target invoice image (S124).

[0056] Next, the template type information generating unit 25 b associates the information extracted in S124 with the item name included in the target template for the current target item ( S125 ).

[0057] Next, the template type information generating unit 25b determines whether there is any item in the target template that is included in the current template. Figure 6 The items that have not yet been targeted in the operation shown (S126).

[0058] When the template type information generating unit 25b determines in S126 that the items included in the target template include the items in this template, Figure 6 If there is no item that is a target in the indicated operation, the process of S121 is executed.

[0059] When the template type information generating unit 25b determines in S126 that the item included in the target template does not exist in this Figure 6 If there is no item as a target in the displayed action, the action ends. Figure 6 Action shown.

[0060] like Figure 5 As shown, after the processing of S103, the template type information generating unit 25b associates the specific information generated in S103 with the format determined in S101 and the invoice image of the object of the information generation instruction, and stores it in the storage unit 24 (S104). Therefore, the user can access the information generating system 20 by using a user terminal, for example, and can confirm the specific information stored in the storage unit 24 through the display unit of the user terminal, and can modify the specific information through the operation unit of the user terminal as needed.

[0061] After the processing of S104, the template type information generating unit 25b ends. Figure 5 Action shown.

[0062] When it is determined in S102 that there is no template corresponding to the format determined in S101 in the template database 24c, the general type information generating unit 25c generates specific information based on the invoice image of the object of the information generation instruction using the information generation model 24d (S105). For example, in the information generation model 24d, when "invoice_no", "invoice_date", and "total_amount" are defined as item names representing "invoice number", "invoice date", and "invoice amount", respectively, the general type information generating unit 25c extracts the value of each item in S105, associates the extracted value with the item name defined in the information generation model 24d, and generates specific information.

[0063] After the process of S105, the general type information generating unit 25c associates the specific information generated in S105 with the format determined in S101 and the invoice image of the object of the information generation instruction, and stores it in the storage unit 24 (S106). Therefore, the user can access the information generating system 20 by using a user terminal, for example, and can confirm the specific information stored in the storage unit 24 through the display unit of the user terminal, and can modify the specific information through the operation unit of the user terminal as needed.

[0064] After the process of S106, the template generating unit 25d performs a template generating process of generating a template based on the specific information generated in S105 (S107).

[0065] Figure 7 yes Figure 5 Flowchart of template generation processing shown.

[0066] like Figure 7 As shown, the template generation unit 25d obtains the item names from all the templates stored in the template database 24c (S141). For example, in the templates stored in the template database 24c, when "invoice_number", "invoice_date", and "total" are defined as the item names of the items representing "invoice number", "invoice date", and "invoice amount", respectively, the template generation unit 25d obtains "invoice_number", "invoice_date", and "total" in S141.

[0067] After the process of S141, the template generation unit 25d acquires the item names in the specific information generated by using the information generation model 24d in S105 (S142). For example, the template generation unit 25d acquires "invoice_no", "invoice_date", and "total_amount" in S142.

[0068] After the processing of S142, the template generation unit 25d determines, based on the dictionary 24e, an item name obtained in S142, that is, an item name in the specific information generated using the information generation model 24d, which corresponds to any one of the item names obtained in S141, that is, the item names obtained from all the templates (S143). For example, the template generation unit 25d determines that the item names "invoice_no", "invoice_date", and "total_amount" obtained in S142 correspond to the item names "invoice_number", "invoice_date", and "total" obtained in S141, respectively.

[0069] After the processing of S143, the template generating unit 25d determines an anchor, an anchor area position, and an extraction area position based on the invoice image of the object indicated by the information generation instruction for each item name determined in S143 (S144). Here, if any character string shown in the dictionary 24e for the object item name exists in the invoice image of the object indicated by the information generation instruction, the template generating unit 25d may use the character string as an anchor. If any character string shown in the dictionary 24e for the object item name does not exist in the invoice image of the object indicated by the information generation instruction, the template generating unit 25d may use any information such as a logo existing in the invoice image as an anchor. In addition, the template generating unit 25d uses a specific area including the area where the value of each item is extracted in S105 based on the invoice image of the object indicated by the information generation instruction as an extraction area.

[0070] After the processing of S144, the template generation unit 25d generates a template (S145) by including, for each item, an item name obtained by converting the item name determined in S143 into the item name obtained in S141, the anchor determined in S144, the anchor region position, and the extraction region position, and ends. Figure 7 The template generation process shown.

[0071] like Figure 5 As shown, after the template generation process of S107, the template generation unit 25d stores the template generated in S107 as a template of the format determined in S101 in the template database 24c (S108). Therefore, the user can access the information generation system 20 by using a user terminal, for example, so as to confirm the template stored in the template database 24c via the display unit of the user terminal, and can modify the template via the operation unit of the user terminal as needed. In addition, the template stored in the template database 24c in S108 is in a temporarily registered state. When the user confirms the template via the display unit of the user terminal, the state of the template can be changed to a formally registered state via the operation unit of the user terminal. When the template generation unit 25d stores a template in a temporarily registered state in the template database 24c, it can notify a specific contact destination of an instruction to urge the state of the template to be changed to a formally registered state.

[0072] After the processing of S108, the template generation unit 25d ends. Figure 5 Action shown.

[0073] Next, the operation of the information generating system 20 when generating a template based on an invoice image will be described.

[0074] Figure 8 This is a flowchart of the operation of the information generating system 20 when generating a template based on an invoice image.

[0075] The user can place an actual invoice on the scanner of the image reading device, and instruct the image reading device to generate a template based on the actual invoice, for example, via the operating unit of the image reading device. When the control unit of the image reading device is instructed to generate a template based on the actual invoice, it reads the invoice image from the actual invoice placed on the scanner of the image reading device through the scanner, and instructs the information generation system 20 to generate a template based on the invoice image via the communication unit of the image reading device. Here, the instruction to generate a template based on the invoice image (hereinafter referred to as "template generation instruction") includes the invoice image of the object 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 Figure 8 Action shown.

[0076] like Figure 8 As shown, the invoice classification unit 25a specifies the format of the invoice corresponding to the invoice image for which the template generation instruction is issued, based on the invoice image, using the invoice classification model 24b (S161).

[0077] Next, the general type information generating unit 25c generates specific information based on the invoice image of the target of the template generation instruction using the information generation model 24d in the same manner as in the process of S105 (S162).

[0078] Next, the template generating unit 25d executes a template generating process for generating a template based on the specific information generated in S162 in the same manner as in the process of S107 (S163).

[0079] Next, the template generation unit 25d stores the template generated in S163 as a candidate of the template of the format determined in S161 (hereinafter referred to as "template candidate") in the storage unit 24 (S164). Therefore, the user can access the information generation system 20 using, for example, a user terminal, thereby confirming the template candidate stored in the storage unit 24 through the display unit of the user terminal, and can modify the template candidate through the operation unit of the user terminal as needed. When the user confirms the template candidate through the display unit of the user terminal, for example, the user can instruct the information generation system 20 through the operation unit of the user terminal.

[0080] After the process of S164, the template generating unit 25d determines whether or not an instruction has been given to adopt the template candidate stored in S164 as a template, and continues until it is determined that an instruction has been given to adopt the template candidate stored in S164 as a template (S165).

[0081] When the template generating unit 25d determines in S165 that the template candidate stored in S164 is instructed to be used as a template, it stores the template candidate stored in S164 as a template of the format determined in S161 in the template database 24c (S166), and ends the process. Figure 8 Action shown.

[0082] As described above, the information generation 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 by the general type information generation unit 25c based on the invoice image, and the template managed by the template database 24c (S107 and S163), thereby eliminating the need to manually create a template corresponding to the format of the invoice. That is, the information generation system 20 can easily create a template for generating specific information based on the invoice image.

[0083] Even when there is no template corresponding to the format of the invoice corresponding to the invoice image that is the object of the information generation instruction in the template database 24c ("No" in S102), the information generation system 20 generates specific information based on the invoice image through the general type information generation unit 25c (S105), thereby eliminating the need to generate specific information based on the invoice image only by manpower, resulting in shortening the time required to generate specific information based on the invoice image.

[0084] In addition, the information generation system 20 can also be implemented through the workflow system 50 (see Fig. 9 . ) is implemented, and the workflow system 50 executes the processing shown in the workflow representing a series of processing. The workflow system 50 can be as follows Fig. 9 Although it is composed of one computer as shown, it may be composed of a plurality of computers.

[0085] Fig. 9 It is a block diagram of a workflow system 50 that realizes the information generation system 20.

[0086] Fig. 9 The workflow system 50 shown comprises: an operation unit 51, which is an operation device such as a keyboard and a mouse to which various operations are input; a display unit 52, which is a display device such as an LCD to display various information; a communication unit 53, which is a communication device that communicates with an external device via a network such as a LAN and the Internet, or directly communicates with an external device by wire or wirelessly without going through a network; a storage unit 54, which is a non-volatile storage device such as a semiconductor memory, HDD, etc. to store various information; and a control unit 55, which controls the workflow system 50 as a whole.

[0087] The storage unit 54 stores a workflow program 54a for executing the processing shown in the workflow. The workflow program 54a can be installed in the workflow system 50 at the manufacturing stage of the workflow system 50, can be additionally installed in the workflow system 50 from an external storage medium such as a USB memory, or can be additionally installed in the workflow system 50 from a network.

[0088] The storage unit 54 can store the invoice classification model 24b, the template database 24c, the information generation model 24d, and the dictionary 24e.

[0089] The control unit 55 includes, for example, a CPU, a ROM storing programs and various data, and a RAM as a memory used as a work area of ​​the CPU of the control unit 55. The CPU of the control unit 55 executes the program stored in the storage unit 54 or the ROM of the control unit 55.

[0090] The control unit 55 implements a workflow generation unit 55a and a workflow execution unit 55b by executing the workflow sequence 54a. The workflow generation unit 55a generates a workflow by connecting any blocks among a plurality of blocks respectively representing specific processing, and the workflow execution unit 55b executes the processing shown in the workflow generated by the workflow generation unit 55a.

[0091] The workflow system 50 can be instructed by the user via, for example, the operation unit of the user terminal to generate a workflow. For example, the workflow generation unit 55a can cause the display unit of the user terminal to display a workflow generation screen for generating a workflow, and can generate a workflow that implements the invoice classification unit 25a, the template type information generation unit 25b, the general type information generation unit 25c, and the template generation unit 25d according to the user's instruction on the workflow generation screen via the operation unit of the user terminal. That is, the workflow generation unit 55a can generate a workflow that implements Figure 5 Workflow and implementation of the actions shown Figure 8 The workflow of the actions shown.

[0092] Fig.10 This is a diagram showing an example of a workflow displayed on a workflow generation screen displayed on the display unit of a user terminal.

[0093] Fig.10 The workflow 60 shown is to implement Figure 5The workflow 60 is generated by connecting a block 61 indicating input of an invoice image from an image reading device, a block 62 indicating the processing of S101 to S103, a block 63 indicating the processing of S104, a block 64 indicating the storage unit 24, a block 65 indicating the processing of S105, a block 66 indicating the processing of S106, a block 67 indicating the storage unit 24, a block 68 indicating the processing of S107, a block 69 indicating the processing of S108, and a block 70 indicating the template database 24c.

[0094] Fig. 9 The workflow system 50 shown in the figure allows the user to confirm the workflow generated by the workflow generation unit 55a via the display unit of the image reading device, and allows the user to instruct execution of the workflow generated by the workflow generation unit 55a via the operation unit of the image reading device.

[0095] The user can place the invoice in the scanner of the image reading device and instruct the image reading device to perform the operation, for example, via the operation unit of the image reading device. Figure 5 The control unit of the image reading device, when instructed to execute the workflow, reads the invoice image from the invoice placed on the scanner of the image reading device through the scanner, and sends the instruction to execute the workflow together with the read invoice image to the workflow system 50 via the communication unit of the image reading device. When the workflow execution unit 55b of the workflow system 50 receives the instruction to execute the workflow via the communication unit 23, it implements Figure 5 Action shown.

[0096] Similarly, the user can place the invoice in the scanner of the image reading device and instruct the image reading device to perform the operation of the image reading device, for example, via the operation unit of the image reading device. Figure 8 The control unit of the image reading device, when instructed to execute the workflow, reads the invoice image from the invoice placed on the scanner of the image reading device through the scanner, and sends the instruction to execute the workflow together with the read invoice image to the workflow system 50 via the communication unit of the image reading device. When the workflow execution unit 55b of the workflow system 50 receives the instruction to execute the workflow via the communication unit 23, it implements Figure 8 Action shown.

[0097] In the above description, the general type information generating unit 25c generates specific information based on the invoice image using the information generating model 24d (S105 and S162). However, the general type information generating unit 25c may generate specific information based on the invoice image without using the information generating model 24d. For example, the general type information generating unit 25c may also generate specific information based on the invoice image by using a cloud service or an external service of the information generating system 20 that generates specific information based on the invoice image in a universal manner regardless of the format. In the case where the general type information generating unit 25c generates specific information based on the invoice image using an external service of the information generating system 20, the information generating system 20 does not need to generate the information generating model 24d in advance by the provider or user of the information generating system 20, thereby reducing the burden on 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 by the general type information generating unit 25c according to the invoice image. Therefore, when the general type information generating unit 25c generates specific information according to the invoice image using the external service of the information generating system 20, even if it is necessary to pay a usage fee to the provider of the external service according to the use of the external service, it is possible to reduce the number of times the general type information generating unit 25c generates specific information according to the invoice image using the external service of the information generating system 20. As a result, it is possible to reduce the usage fee paid to the provider of the external service.

[0098] In the above description, the template generation unit 25d determines, based on the dictionary 24e, an item name in the specific information generated by the general type information generation unit 25c that corresponds to any one of the item names obtained from all the templates stored in the template database 24c (S143). However, the template generation unit 25d may determine, without using the dictionary 24e, an item name in the specific information generated by the general type information generation unit 25c that corresponds to any one of the item names obtained from all the templates stored in the template database 24c. For example, the template generation unit 25d may determine, using a learning model created by machine learning, an item name in the specific information generated by the general type information generation unit 25c that corresponds to any one of the item names obtained from all the templates stored in the template database 24c.

[0099] In the above, an invoice is used as an example of a document. However, the present invention can also be applied to documents other than invoices. For example, the present invention can also be applied to various forms such as quotations, receipts, and delivery notes.

Claims

1. An information generation system, characterized in that: include: A document classification unit, classifying the document according to the format of the document; a template type information generating unit, which generates the information based on the image using a template for generating specific information based on the image of the document; a general type information generating unit for generating the information generally based on the image without depending on the format; as well as A template generating unit generates the template. The template type information generating unit determines whether the template corresponding to the format determined by the document classification unit is managed in the template management unit that manages the template, when the format of the document corresponding to the image is determined by the document classification unit. When the template type information generating unit determines that the template is managed in the template management unit, the template type information generating unit generates the information based on the image using the template corresponding to the format determined by the document classification unit among the templates managed by the template management unit, and when the template type information generating unit determines that the template is not managed in the template management unit, the general type information generating unit generates the information generally based on the image. When the general type information generating unit generally generates the information according to the image, the template generating unit generates the template corresponding to the format determined by the document classification unit based on the image, the information generated by the general type information generating unit according to the image, and the template managed by the template management unit.

2. The information generation system according to claim 1, characterized in that The general type information generating unit generates the information from the image using an external service of the information generating system that generates the information from the image in a general manner without depending on the format.

3. A workflow system, characterized in that: include: a workflow generating unit that generates a workflow representing a series of processes by connecting arbitrary blocks among a plurality of blocks that respectively represent specific processes; as well as a workflow execution unit that executes the processing indicated by the workflow generated by the workflow generation unit, The workflow generation unit is capable of generating the workflow that implements the document classification unit, the template type information generation unit, the general type information generation unit, and the template generation unit. The document classification unit classifies the documents according to the formats of the documents. The template type information generating unit generates the information based on the image using a template for generating specific information based on the image of the document, The general type information generating unit generates the information universally according to the image without depending on the format, The template generation unit generates the template, The template type information generating unit determines whether the template corresponding to the format determined by the document classification unit is managed in the template management unit that manages the template, when the format of the document corresponding to the image is determined by the document classification unit. When the template type information generating unit determines that the template is managed in the template management unit, the template type information generating unit generates the information based on the image using the template corresponding to the format determined by the document classification unit among the templates managed by the template management unit, and when the template type information generating unit determines that the template is not managed in the template management unit, the general type information generating unit generates the information generally based on the image. When the general type information generating unit generally generates the information according to the image, the template generating unit generates the template corresponding to the format determined by the document classification unit based on the image, the information generated by the general type information generating unit according to the image, and the template managed by the template management unit.

4. A recording medium, which is a computer-readable non-transitory recording medium storing an information generation program, characterized in that: The information generation program enables the computer to implement a document classification unit, a template type information generation unit, a general type information generation unit, and a template generation unit. The document classification unit classifies the documents according to the formats of the documents. The template type information generating unit generates the information based on the image using a template for generating specific information based on the image of the document, The general type information generating unit generates the information universally according to the image without depending on the format, The template generation unit generates the template, The template type information generating unit determines whether the template corresponding to the format determined by the document classification unit is managed in the template management unit that manages the template, when the format of the document corresponding to the image is determined by the document classification unit. When the template type information generating unit determines that the template is managed in the template management unit, the template type information generating unit generates the information based on the image using the template corresponding to the format determined by the document classification unit among the templates managed by the template management unit, and when the template type information generating unit determines that the template is not managed in the template management unit, the general type information generating unit generates the information generally based on the image. When the general type information generating unit generally generates the information according to the image, the template generating unit generates the template corresponding to the format determined by the document classification unit based on the image, the information generated by the general type information generating unit according to the image, and the template managed by the template management unit.

5. A recording medium is a computer-readable non-transitory recording medium storing a workflow program, characterized in that: The workflow program enables the computer to implement the workflow generation part and the workflow execution part. The workflow generation unit generates a workflow representing a series of processes by connecting any of a plurality of blocks each representing a specific process. The workflow execution unit executes the processing indicated by the workflow generated by the workflow generation unit, The workflow generation unit is capable of generating the workflow that implements the document classification unit, the template type information generation unit, the general type information generation unit, and the template generation unit. The document classification unit classifies the documents according to the formats of the documents. The template type information generating unit generates the information based on the image using a template for generating specific information based on the image of the document, The general type information generating unit generates the information universally according to the image without depending on the format, The template generation unit generates the template, The template type information generating unit determines whether the template corresponding to the format determined by the document classification unit is managed in the template management unit that manages the template, when the format of the document corresponding to the image is determined by the document classification unit. When the template type information generating unit determines that the template is managed in the template management unit, the template type information generating unit generates the information based on the image using the template corresponding to the format determined by the document classification unit among the templates managed by the template management unit, and when the template type information generating unit determines that the template is not managed in the template management unit, the general type information generating unit generates the information generally based on the image. When the general type information generating unit generally generates the information according to the image, the template generating unit generates the template corresponding to the format determined by the document classification unit based on the image, the information generated by the general type information generating unit according to the image, and the template managed by the template management unit.

Citation Information

Patent Citations

  • Image processing apparatus and information processing system

    CN101083701A

  • Invoice input method, device and equipment and computer storage medium

    CN110619056A

  • Template construction and matching method for medical document structured knowledge extraction

    CN111666885A

  • Ticket identification device and ticket information management system

    CN111860450A