Print definition generating device, print definition generating method, and print definition generating program

Abstract

To easily generate print definition information. [Solution] An input unit 21 inputs image information of a target form to a trained model 40 that has been given sample information, which is a set of image information 31 of a sample form and print definition information 32, which is setting information for printing the sample form. An output unit 22 acquires and outputs print definition information that is generated by the trained model 40 in response to the image information of the target form and is setting information for printing the target form.

Description

[Technical Field]

[0001] The present disclosure relates to a technique for generating a print definition for printing a form from image information of the form. [Background technology]

[0002] Recently, there has been a push to go paperless, where paper forms are digitized. However, in payroll systems, for example, progress has been slow to go paperless, and many paper forms are still in use to prevent information leaks. Paper forms in payroll systems include management forms used in operations, such as payment statements, and forms in prescribed formats designated by the relevant government agency, such as tax return forms for dependent deductions.

[0003] The format of payment statements and other documents changes whenever the number of itemized items increases, and for documents specified by government agencies, changes every time a law is revised. Every time the format changes, the print definition information for the document must be modified. The print definition information is the setting information for printing the document, such as the print position of each item, font, and borders. Forms specified by government agencies are often presented as image information, with complex lines and fields. The fields are display fields and input fields. Even with other forms, there are cases where only image information is available. To create print definition information from image information, it is necessary to visually check the positions of the lines and fields and generate definition information for each one. For example, Patent Document 1 describes generating form data for a form using form editor software. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-138322 Summary of the Invention [Problem to be solved by the invention]

[0005] Every time the format of a form changes, time-consuming work of creating or modifying print definition information must be carried out. The present disclosure aims to make it possible to easily generate print definition information. [Means for solving the problem]

[0006] A print definition generating device according to the present disclosure includes: An input unit that inputs image information of a target form to a trained model that is given sample information that is a set of image information of a sample form and print definition information that is setting information for printing the sample form; an output unit that outputs print definition information generated by the trained model in response to image information of the target form input by the input unit, the print definition information being setting information for printing the target form; Equipped with. [Effects of the Invention]

[0007] In this disclosure, image information of a target form is input into a trained model to obtain print definition information, which is setting information for printing the target form. This makes it possible to easily generate print definition information without visually checking the positions of ruled lines and items and generating definition information for each one. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram of a print definition generating device 10 according to a first embodiment. [Figure 2] 4 is a flowchart showing the flow of processing by the print definition generating device 10 according to the first embodiment. [Figure 3] FIG. 3 is a diagram showing an example of print definition information according to the first embodiment. [Figure 4] FIG. 1 is a diagram showing an example of the configuration of a trained model 40 according to the first embodiment. [Figure 5] FIG. 3 is an explanatory diagram of a prompt generated by a first model 41 according to the first embodiment. [Figure 6] FIG. 10 is a configuration diagram of a print definition generating device 10 according to a second embodiment. [Figure 7] 10 is a flowchart showing the flow of processing by a print definition generating device 10 according to a second embodiment. [Figure 8] 10 is a flowchart showing the flow of processing by a print definition generating device 10 according to a third embodiment. [Figure 9] FIG. 10 is a configuration diagram of a print definition generating device 10 according to a fourth embodiment. [Figure 10] 10 is a flowchart showing the flow of processing by a print definition generating device 10 according to a fourth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Embodiment 1 ***Configuration Description*** The configuration of a print definition generating device 10 according to the first embodiment will be described with reference to FIG. The print definition generator 10 is a computer. The print definition generating device 10 comprises the following hardware: a processor 11, a memory 12, a storage 13, and a communication interface 14. The processor 11 is connected to other hardware via signal lines and controls this other hardware.

[0010] The processor 11 is an IC that performs processing. IC stands for Integrated Circuit. Specific examples of the processor 11 include a CPU, a DSP, and a GPU. CPU stands for Central Processing Unit. DSP stands for Digital Signal Processor. GPU stands for Graphics Processing Unit.

[0011] The memory 12 is a storage device that temporarily stores data. Specific examples of the memory 12 include SRAM and DRAM. SRAM stands for Static Random Access Memory. DRAM stands for Dynamic Random Access Memory.

[0012] The storage 13 is a storage device that stores data. A specific example of the storage 13 is an SSD. SSD is an abbreviation for Solid State Drive. The storage 13 may also be a portable recording medium such as an SD (registered trademark) memory card, CompactFlash (registered trademark), NAND flash, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, or a DVD. SD is an abbreviation for Secure Digital. DVD is an abbreviation for Digital Versatile Disk.

[0013] The communication interface 14 is an interface for communicating with external devices. Specific examples of the communication interface 14 include Ethernet (registered trademark), USB, and HDMI (registered trademark) ports. USB stands for Universal Serial Bus. HDMI stands for High-Definition Multimedia Interface.

[0014] The print definition generator 10 includes, as functional components, an input unit 21 and an output unit 22. The functions of the functional components of the print definition generator 10 are realized by software. Storage 13 stores programs that realize the functions of each functional component of print definition generation device 10. These programs are loaded into memory 12 by processor 11 and executed by processor 11. In this way, the functions of each functional component of print definition generation device 10 are realized.

[0015] The storage 13 stores image information 31 and print definition information 32. The image information 31 is an image of a form, and is data in a format such as PDF. PDF stands for Portable Document Format. The print definition information 32 is setting information for printing the form indicated by the image information 31. The print definition information 32 indicates the print position, font, ruled lines, etc. of each item that makes up the form.

[0016] The print definition generation device 10 is connected to the trained model 40 via the communication interface 14. The trained model 40 is a so-called generative AI. AI stands for artificial intelligence. The trained model 112 may be configured using algorithms such as BERT and GPT, for example. BERT stands for Bidirectional Encoder Representations from Transformers. GPT stands for Generative Pretrained Transformer. The trained model 112 may be configured by combining multiple algorithms including these algorithms.

[0017] 1, trained model 40 exists outside print definition generator 10. However, trained model 40 may be provided as a functional component of print definition generator 10.

[0018] 1 shows only one processor 11. However, there may be a plurality of processors 11, and the plurality of processors 11 may cooperate to execute programs that realize the respective functions.

[0019] ***Explanation of Operation*** The operation of the print definition generating device 10 according to the first embodiment will be described with reference to FIGS. The operation procedure of print definition generation device 10 according to embodiment 1 corresponds to the print definition generation method according to embodiment 1. Furthermore, the program that realizes the operation of print definition generation device 10 according to embodiment 1 corresponds to the print definition generation program according to embodiment 1.

[0020] The flow of processing by the print definition generating device 10 according to the first embodiment will be described with reference to FIG. Here, it is assumed that a set of image information 31 and print definition information 32 for an existing form has already been stored in the storage 13.

[0021] (Step S11: Sample information acquisition process) The input unit 21 acquires sample information, which is a set of image information 31 of a sample form and print definition information 32. The image information 31 of the sample form is image information 31 of any existing form stored in the storage 13. The print definition information 32 is setting information for printing the sample form. The input unit 21 may use a plurality of existing forms as sample forms, i.e., the input unit 21 may acquire sets of image information 31 and print definition information 32 for a plurality of existing forms as sample information.

[0022] (Step S12: Image acquisition process) The input unit 21 acquires image information of a target form. For example, the input unit 21 acquires image information of a withholding tax slip, assuming that the withholding tax slip is the target form. As a specific example, if the target form is a form whose format is specified by a government agency, the input unit 21 acquires image information of the form made public by the government agency. Also, if the target form is printed on paper, the input unit 21 acquires image information generated by reading it with a scanner.

[0023] (Step S13: Input processing) The input unit 21 inputs the sample information acquired in step S11 and the image information of the target form acquired in step S12 to the trained model 40. In other words, the input unit 21 provides the sample information and the image information of the target form to the trained model 40 as inputs. Here, when the input unit 21 inputs the image information of the target form to the trained model 40, the input unit 21 also inputs the sample information to the trained model 40. However, the input unit 21 may provide the sample information to the trained model 40 in advance.

[0024] Then, the trained model 40 generates print definition information corresponding to the image information input in step S13. That is, the trained model 40 generates print definition information that is setting information for printing the target form. At this time, the trained model 40 generates print definition information that follows the format of the print definition information 32 included in the sample information, following the sample information input in step S13. For example, as shown in FIG. 3, the print definition information is information that defines the print position, font, ruled lines, etc. of each item that constitutes a form.

[0025] (Step S14: Print definition acquisition process) The output unit 22 acquires the print definition information generated by the trained model 40 in response to the image information input in step S13.

[0026] (Step S15: Output process) The output unit 22 outputs the print definition information acquired in step S14. For example, the output unit 22 outputs the print definition information to a user terminal or the like connected via the communication interface 14 .

[0027] (Step S16: Recording process) The output unit 22 writes the image information of the target form acquired in step S12 as image information 31, and writes the print definition information acquired in step S14 as print definition information 32 for the target form into the storage 13.

[0028] As shown in FIG. 4, the trained model 40 may include two models: a first model 41 and a second model 42. The first model 41 is a model that takes sample information and image information of a target form as input and generates a prompt that instructs the generation of print definition information, which is setting information for printing the target form. Here, the first model 41 generates a prompt that instructs the generation of print definition information in accordance with the description rules of the print definition information included in the sample information. The first model 41 also generates a prompt in text format. For example, the first model 41 generates a prompt such as that shown in FIG. 5. The second model 42 is a model that uses the prompt generated by the first model 41 as an input and generates print definition information, which is setting information for printing a target form.

[0029] ***Effects of the First Embodiment*** As described above, the print definition generation device 10 according to the first embodiment inputs image information of the target form into the trained model 40 and acquires print definition information, which is setting information for printing the target form. This makes it possible to easily generate print definition information without visually checking the positions of ruled lines and items and generating definition information for each one. Each system can easily obtain the necessary print definition information by transferring the print definition information generated by the print definition generation device 10 to other systems. For example, by transferring print definition information related to withholding tax slips to a payroll management system, the time and effort required for a system setup person to visually check the positions of lines and items and generate definition information one by one is no longer necessary.

[0030] The trained model 40 receives image information of the target form as input. Therefore, the trained model 40 must support image-format input. However, some generative AI models only support text-format input. In such cases, as described with reference to FIG. 4, the trained model 40 can be configured to include a first model 41 configured using a model that supports image-format input, and a second model 42 that does not need to support image-format input. This makes it possible to configure the main processing portion, which is generating print definition information, using a model that does not need to support image-format input.

[0031] Embodiment 2 The second embodiment differs from the first embodiment in that it extracts the difference between the print image obtained from the print definition information and the image information of the target form and feeds it back to the trained model 40. In the second embodiment, this difference will be explained, and explanations of the same points will be omitted.

[0032] ***Configuration Description*** The configuration of a print definition generating device 10 according to the second embodiment will be described with reference to FIG. 1 in that the print definition generation device 10 includes, as functional components, a difference extraction unit 23 and a repetition determination unit 24. The difference extraction unit 23 and the repetition determination unit 24 are realized by software, like the other functional components.

[0033] ***Explanation of Operation*** The flow of processing by the print definition generating device 10 according to the second embodiment will be described with reference to FIG. The processing from step S21 to step S24 is the same as the processing from step S11 to step S14 in FIG.

[0034] (Step S25: Difference extraction process) The difference extraction unit 23 extracts the differences between the print image obtained from the print definition information acquired in step S24 and the image information of the target form. The print image obtained from the print definition information is generated by the printing system by providing the print definition information to the printing system for the form. The print image represents the state that will be printed when printing is performed using the print definition information in the printing system. Therefore, by extracting the differences between the print image and the image information, it is possible to extract the differences between what will actually be printed and the provided image information. The differences here include, for example, the amount of deviation in the printing position of an item or the position of a ruled line, etc. Also included are differences such as incorrect characters displayed, different character fonts and font sizes, etc.

[0035] (Step S26: Repeated determination process) The repetition determination unit 24 determines whether the difference extracted in step S25 is smaller than a reference value. If the difference is equal to or greater than the criterion, the repetition determination unit 24 proceeds to step S27. On the other hand, if the difference is smaller than the criterion, the repetition determination unit 24 proceeds to step S28. Note that the repetition determination unit 24 determines whether the difference is smaller than the criterion by comparing the images of the print image and the image information.

[0036] (Step S27: Re-input process) The input unit 21 inputs the difference extracted in step S25 to the trained model 40. At this time, the input unit 21 may input an instruction to the trained model 40 to generate print definition information so as to reduce the difference. As a result, the input unit 21 causes the trained model 40 to regenerate print definition information, which is setting information for printing the target form. The input unit 21 may input to the trained model 40 not only the difference but also the sample information acquired in step S21 and the image information of the target form acquired in step S22.

[0037] (Step S28: Output processing) The output unit 22 outputs the print definition information acquired in the last executed step S24.

[0038] (Step S29: Recording process) The output unit 22 writes the image information of the target form acquired in step S22 as image information 31, and the printing definition information acquired in the last executed step S24 as printing definition information 32 for the target form to the storage 13.

[0039] ***Effects of the Second Embodiment*** As described above, the print definition generation device 10 according to the second embodiment extracts the differences between the print image obtained from the print definition information and the image information of the target form, and feeds this back to the trained model 40. This makes it possible to generate print definition information that can print something close to the image information of the target form.

[0040] Embodiment 3 The third embodiment differs from the first and second embodiments in that, together with the image information of the target form, changes to the image information of the target form are input to the trained model 40. In the third embodiment, this difference will be explained, and explanations of the same points will be omitted. In the third embodiment, a case where a modification is made to the first embodiment will be described. However, it is also possible to make modifications to the second embodiment.

[0041] ***Explanation of Operation*** The flow of processing performed by the print definition generating device 10 according to the third embodiment will be described with reference to FIG. The processes in steps S31 and S32 are the same as those in steps S11 and S12 in Fig. 2. The processes in steps S34 to S36 are the same as those in steps S14 to S16 in Fig. 2.

[0042] (Step S33: Input processing) The input unit 21 inputs to the trained model 40 the sample information acquired in step S11, the image information of the target form acquired in step S12, and the changes to be made to the image information of the target form. The changes include adding a ruled line indicating an area for displaying a seal image such as a company stamp image at a reference position, deleting information of a specified item in the target form, changing the design, changing the font or font size, etc. For example, when printing the target form with a ruled line indicating an area for affixing the company stamp added, the input unit 21 inputs the change indicating the addition of the ruled line to the trained model 40.

[0043] Then, the trained model 40 generates print definition information, which is setting information for printing a form in which the changes indicated by the change contents have been added to the target form.

[0044] ***Effects of the Third Embodiment*** As described above, the print definition generating device 10 according to the third embodiment inputs changes to the image information of the target form into the trained model 40. This makes it possible to easily change the target form and then print it.

[0045] Embodiment 4 The fourth embodiment differs from the first to third embodiments in that information on designated items is deleted from the image information of the target form before being input to the trained model 40. In the fourth embodiment, this difference will be explained, and explanation of the same points will be omitted. In the fourth embodiment, a case where a modification is made to the first embodiment will be described. However, modifications can also be made to the second and third embodiments.

[0046] ***Configuration Description*** The configuration of a print definition generating device 10 according to the fourth embodiment will be described with reference to FIG. 1 in that the print definition generation device 10 includes a preprocessing unit 25 as a functional component. The preprocessing unit 25 is realized by software, like the other functional components.

[0047] ***Explanation of Operation*** The flow of processing by the print definition generating device 10 according to the fourth embodiment will be described with reference to FIG. The processes in steps S41 and S42 are the same as those in steps S11 and S12 in Fig. 2. The processes in steps S45 to S47 are the same as those in steps S14 to S16 in Fig. 2.

[0048] (Step S43: Preprocessing) The preprocessing unit 25 generates a post-deletion image by deleting the information of the designated items from the image information of the target form. For example, the designated items are items in which personal information is set. This deletes the personal information. For example, the designated items are display characters that the system designer has determined to be unnecessary.

[0049] (Step S44: Input processing) The input unit 21 inputs the sample information acquired in step S41 to the trained model 40, and also inputs the post-deletion image generated in step S13 to the trained model 40 as image information of the target form.

[0050] ***Effects of the Fourth Embodiment*** As described above, the print definition generation device 10 according to the fourth embodiment deletes information about designated items from the image information of the target form and then inputs the information to the trained model 40. This makes it possible to generate print definition information in a state where the information about designated items has been deleted. When personal information or other information is displayed on a target form, there may be cases where it is desired to remove this information before generating print definition information. Since designated items can be deleted based on a specification from the system administrator, it is possible to reuse existing image information to generate print definition information with different details. The print definition generation device 10 according to the fourth embodiment can handle such cases.

[0051] ***Other Configurations*** <Variation 1> In the first to fourth embodiments, each functional component is realized by software. However, as a first modification, each functional component may be realized by hardware. The differences between this first modification and the first embodiment will be described below.

[0052] When each functional component is realized by hardware, the print definition generation device 10 includes an electronic circuit instead of the processor 11, memory 12, and storage 13. The electronic circuit is a dedicated circuit that realizes the functions of each functional component, memory 12, and storage 13.

[0053] Possible electronic circuits include single circuits, composite circuits, programmed processors, parallel programmed processors, logic ICs, GAs, ASICs, and FPGAs. GA stands for Gate Array. ASIC stands for Application Specific Integrated Circuit. FPGA stands for Field-Programmable Gate Array. Each functional component may be realized by one electronic circuit, or each functional component may be realized by distributing it among a plurality of electronic circuits.

[0054] <Variation 2> As a second modification, some of the functional components may be realized by hardware, and other functional components may be realized by software.

[0055] The processor 11, memory 12, storage 13, and electronic circuitry are collectively referred to as a processing circuit. In other words, the functions of the functional components are realized by the processing circuit.

[0056] Furthermore, the term "unit" in the above description may be read as a "circuit," "step," "procedure," "process," or "processing circuit."

[0057] Various aspects of the present disclosure are summarized below as appendices. (Appendix 1) An input unit that inputs image information of a target form to a trained model that is given sample information that is a set of image information of a sample form and print definition information that is setting information for printing the sample form; an output unit that acquires and outputs print definition information generated by the trained model in response to the image information of the target form input by the input unit, the print definition information being setting information for printing the target form; A print definition generator comprising: (Appendix 2) The trained model is a first model that generates a prompt that instructs, in text form, to generate print definition information, which is setting information for printing the target form, based on the sample information and image information of the target form, in accordance with description rules for print definition information included in the sample information; a second model that uses the prompt generated by the first model as an input and generates print definition information, which is setting information for printing the target form; 2. The print definition generator of claim 1, comprising: (Appendix 3) The print definition generator further comprises: a difference extraction unit that extracts differences between a print image obtained from the print definition information acquired by the output unit and image information of the target form; Equipped with The input unit inputs the difference extracted by the difference extraction unit into the trained model, and regenerates print definition information, which is setting information for printing the target form. 3. The print definition generator according to claim 1 or 2. (Appendix 4) The print definition generator further comprises: a repeat determination unit that determines whether the difference is smaller than a reference value, and, if the difference is smaller than the reference value, causes the input unit to stop inputting the difference to the trained model; 4. The print definition generator of claim 3, comprising: (Appendix 5) The input unit inputs changes to the image information of the target form together with the image information of the target form into the trained model; The output unit outputs print definition information generated by the trained model, the print definition information being setting information for printing a form in which the change indicated by the change content has been added to the target form. 5. The print definition generator of claim 1. (Appendix 6) The change indicates that a ruled line is added to indicate an area for displaying the seal image at a reference position. 6. The print definition generator of claim 5. (Appendix 7) The change indicates that the information of the specified item in the target form is to be deleted. 7. The print definition generator according to claim 5 or 6. (Appendix 8) The print definition generator further comprises: A preprocessing unit that generates a post-deletion image by deleting information of specified items from the image information of the target form. Equipped with The input unit inputs the post-deletion image generated by the pre-processing unit to the trained model as image information of the target form. 8. The print definition generator of claim 1. (Appendix 9) The computer inputs image information of the target form into a trained model to which sample information, which is a set of image information of a sample form and print definition information which is setting information for printing the sample form, is given; A printing definition generation method in which a computer acquires and outputs printing definition information generated by the trained model in response to image information of the target form, the printing definition information being setting information for printing the target form. (Appendix 10) An input process for inputting image information of a target form to a trained model given sample information, which is a set of image information of a sample form and print definition information, which is setting information for printing the sample form; an output process of acquiring and outputting print definition information generated by the trained model in response to the image information of the target form input by the input process, the print definition information being setting information for printing the target form; A print definition generation program that causes a computer to function as a print definition generation device that performs the above.

[0058] The embodiments and modifications of the present disclosure have been described above. Some of these embodiments and modifications may be combined and implemented. Also, one or more of them may be implemented partially. Note that the present disclosure is not limited to the above embodiments and modifications, and various modifications are possible as needed. [Explanation of symbols]

[0059] 10 Print definition generation device, 11 Processor, 12 Memory, 13 Storage, 14 Communication interface, 21 Input unit, 22 Output unit, 23 Difference extraction unit, 24 Repetition judgment unit, 25 Preprocessing unit, 31 Image information, 32 Print definition information, 40 Trained model, 41 First model, 42 Second model.

Claims

1. An input unit that inputs image information of a target form to a trained model that is given sample information that is a set of image information of a sample form and print definition information that is setting information for printing the sample form; an output unit that acquires and outputs print definition information generated by the trained model in response to the image information of the target form input by the input unit, the print definition information being setting information for printing the target form; Equipped with The trained model is a first model that generates a prompt that instructs, by text, the generation of print definition information, which is setting information for printing the target form, based on the sample information and image information of the target form, in accordance with description rules for print definition information included in the sample information; a second model that uses the prompt generated by the first model as an input and generates print definition information that is setting information for printing the target form; A print definition generator including:

2. The print definition generator further comprises: a difference extraction unit that extracts differences between a print image obtained from the print definition information acquired by the output unit and image information of the target form; Equipped with The input unit inputs the difference extracted by the difference extraction unit into the trained model, and regenerates print definition information, which is setting information for printing the target form. The print definition generator of claim 1 .

3. The print definition generator further comprises: a repeat determination unit that determines whether the difference is smaller than a reference value, and, if the difference is smaller than the reference value, causes the input unit to stop inputting the difference to the trained model; The print definition generator of claim 2 , comprising:

4. The input unit inputs changes to the image information of the target form together with the image information of the target form into the trained model; The output unit outputs print definition information generated by the trained model, the print definition information being setting information for printing a form in which the change indicated by the change content has been added to the target form. The print definition generator of claim 1 .

5. The change indicates that a ruled line is added to indicate an area for displaying the seal image at a reference position.

5. The print definition generator of claim 4.

6. The change indicates that the information of the specified item in the target form is to be deleted.

5. The print definition generator of claim 4.

7. The print definition generator further comprises: A preprocessing unit that generates a post-deletion image by deleting information of specified items from the image information of the target form. Equipped with The input unit inputs the post-deletion image generated by the pre-processing unit to the trained model as image information of the target form. The print definition generator of claim 1 .

8. The computer inputs image information of the target form into a trained model to which sample information, which is a set of image information of a sample form and print definition information which is setting information for printing the sample form, is given; The computer acquires and outputs print definition information generated by the trained model in response to image information of the target form, the print definition information being setting information for printing the target form; The trained model is a first model that generates a prompt that instructs, by text, the generation of print definition information, which is setting information for printing the target form, based on the sample information and image information of the target form, in accordance with description rules for print definition information included in the sample information; a second model that uses the prompt generated by the first model as an input and generates print definition information that is setting information for printing the target form; A method for generating print definitions, including:

9. An input process for inputting image information of a target form to a trained model to which sample information, which is a set of image information of a sample form and print definition information that is setting information for printing the sample form, has been given; an output process of acquiring and outputting print definition information generated by the trained model in response to the image information of the target form input by the input process, the print definition information being setting information for printing the target form; causing a computer to function as a print definition generator that performs The trained model is a first model that generates a prompt that instructs, by text, the generation of print definition information, which is setting information for printing the target form, based on the sample information and image information of the target form, in accordance with description rules for print definition information included in the sample information; a second model that uses the prompt generated by the first model as an input and generates print definition information that is setting information for printing the target form; A print definition generator that includes:

Images