Information processing system and information processing program

The system uses a trained large-scale language model to automatically summarize printing workflow information, addressing the challenge of repetitive workflow definition by providing efficient summarization and reuse assessment.

JP2025150194APending Publication Date: 2025-10-09FUJIFILM BUSINESS INNOVATION CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2024050956
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-03-27
Publication Date
2025-10-09

AI Technical Summary

Technical Problem

Existing systems struggle to determine whether existing workflows can be used for new printing orders, leading to repetitive workflow definition and increased complexity due to the lack of efficient workflow information summarization.

Method used

An information processing system utilizing a trained large-scale language model to automatically summarize workflow information, including input from software that manages workflows, and generate summaries of printing job details such as printed material, processing types, order information, and costs.

Benefits of technology

Enables automatic summarization of workflow information, assisting users in determining whether existing workflows can be reused for new printing jobs, thereby reducing redundancy and improving workflow management efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025150194000001_ABST
    Figure 2025150194000001_ABST
Patent Text Reader

Abstract

To provide an information processing system and information processing program, which enable automatic summarization of printing operation-related workflow information.SOLUTION: A summarization unit 106 inputs new input information including information defining a workflow of a printing operation to a trained model pre-trained to output a summary of the input information, so as to output a summary of the information defining the workflow.SELECTED DRAWING: Figure 4
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

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

[0002] Patent document 1 discloses a print ordering system that places an order for printing with a factory, which identifies the type and amount of paper used at the factory based on information collected from the factory to which the order is placed, and sends the identified type and amount of paper to the supplier of the paper used. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-26535 Summary of the Invention [Problem to be solved by the invention]

[0004] There is software that defines workflows according to printing operations and executes and manages everything from product order receipt to shipment. When workflows are defined according to the type of order processing, from the reception desk to production and shipment, it is difficult to determine at a glance whether a workflow already registered in the system can be used for a newly received order, in other words, whether it is suitable for product manufacturing.

[0005] Therefore, even if there are already workflows that can be used, new workflows are repeatedly defined and created, and the number of registered workflows increases without limit, making it even more difficult to determine whether or not an existing workflow can be used.

[0006] Therefore, an object of the present disclosure is to provide an information processing system and an information processing program that can automatically summarize workflow information related to printing operations. [Means for solving the problem]

[0007] In order to achieve the above object, the information processing system of the first aspect includes a processor, and the processor outputs a summary of the information defining the workflow by inputting new input information including information defining the workflow of a printing job into a trained model that has been trained in advance to output a summary of the input information.

[0008] An information processing system according to a second aspect is an information processing system according to the first aspect, in which the trained model is a large-scale language model, and the processor inputs information defining a workflow of a printing job and a prompt statement instructing the processor to summarize the contents of the workflow into the large-scale language model, thereby obtaining a summary of the information defining the workflow from the output of the large-scale language model.

[0009] An information processing system according to a third aspect is the information processing system according to the first aspect, wherein the information defining the workflow of the printing job is information exported from software that manages the workflow.

[0010] An information processing system according to a fourth aspect is an information processing system according to the second aspect, wherein the prompt statement includes an instruction statement instructing that the summary of the workflow information should include the type of printed material, the type of processing, order information, raw material names, processing days, or cost.

[0011] An information processing system according to a fifth aspect is the information processing system according to the second aspect, wherein the prompt sentence includes a directive sentence instructing information that is not to be included in the summary of the workflow information.

[0012] An information processing system according to a sixth aspect is the information processing system according to the second aspect, wherein the large-scale language model is pre-trained to include the type of printed matter, the type of processing, order information, raw material names, processing days, or costs in the summary of the workflow information.

[0013] An information processing system according to a seventh aspect is the information processing system according to the third aspect, wherein the processor presents a summary of information about the workflow when a user defines a new workflow using the software.

[0014] The information processing program according to the eighth aspect causes a computer to input new input information, including information defining a workflow of a printing job, into a trained model that has been trained in advance to output a summary of the input information, thereby outputting a summary of the information defining the workflow. [Effects of the Invention]

[0015] According to the first aspect, workflow information relating to printing operations can be automatically summarized.

[0016] According to the second aspect, it is possible to automatically summarize information on a workflow relating to a printing job using a large-scale language model.

[0017] According to the third aspect, it is possible to automatically summarize information about a workflow relating to a printing job using information exported from software that manages a workflow.

[0018] According to the fourth aspect, it is possible to automatically summarize information on the workflow relating to printing work, including the type of printed matter, the type of processing, order information, raw material names, processing days, or costs.

[0019] According to the fifth aspect, it is possible to specify information that is not to be included in the summary of workflow information related to printing work.

[0020] According to the sixth aspect, it is possible to automatically summarize information on the workflow relating to printing work, including the type of printed matter, the type of processing, order information, raw material names, processing days, or costs.

[0021] According to the seventh aspect, when a user defines a new workflow using software, it is possible to assist the user in determining whether or not an existing workflow can be used.

[0022] According to the eighth aspect, workflow information relating to printing operations can be automatically summarized. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a diagram showing a schematic configuration of an information processing system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a block diagram showing the main configuration of an electrical system of a printing device in the information processing system according to the present embodiment. [Figure 3] 2 is a block diagram showing the configuration of the main electrical system of a management device and a client computer in the information processing system according to the present embodiment. FIG. [Figure 4] FIG. 2 is a functional block diagram showing the functional configuration of a client computer in the information processing system according to the present embodiment. [Figure 5] FIG. 10 is a diagram illustrating an example of a trained neural network model. [Figure 6] 10 is a flowchart showing an example of the flow of a learning process performed in a client computer of the information processing system according to the present embodiment. [Figure 7] FIG. 10 is a diagram showing an example of a screen in software for managing information defining a workflow of a printing job. [Figure 8] 10 is a flowchart showing an example of the flow of a summarization process performed in a client computer of the information processing system according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0024] An example of this embodiment will be described in detail below with reference to the drawings. In this embodiment, an information processing system in which a management device, a printing device, a client computer, etc. are connected to each other via communication lines such as various networks will be described as an example. Figure 1 is a diagram showing the schematic configuration of an information processing system 10 according to this embodiment.

[0025] 1, an information processing system 10 according to this embodiment includes a management device 11, a printing device 12, and a client computer 14. The management device 11, the printing device 12, and the client computer 14 are connected to each other via a communication line 18 such as a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, or an intranet. The management device 11, the printing device 12, and the client computer 14 are each capable of transmitting and receiving various data to and from each other via the communication line 18. In this embodiment, the client computer 14 issues a printing instruction to the printing device 12 via the management device 11, and the printing device 12 prints in accordance with the print instruction.

[0026] Although FIG. 1 shows one management device 11, one printing device 12, and one client computer 14, there may be a plurality of each, or there may be a plurality of any of them.

[0027] The printing device 12 according to this embodiment has multiple functions, such as a printing function for performing print processing, a post-processing function for performing post-processing on printed paper, etc. The multiple functions may include a reading function for reading an original to obtain image information representing the original, a copying function for copying an image recorded on the original onto paper, a facsimile function for sending and receiving various data via a telephone line (not shown), a transfer function for transferring original information such as image information read by the reading function, etc., and a storage function for storing original information such as read image information.

[0028] In the following description, the facsimile function may be referred to as fax, the reading function as scan, the printing function as print, and the copying function as copy.

[0029] FIG. 2 is a block diagram showing the main configuration of the electrical system of the printing device 12 in the information processing system 10 according to this embodiment.

[0030] As shown in Fig. 2, the printing device 12 according to this embodiment includes a control unit 20. The control unit 20 may include a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory).

[0031] Meanwhile, the printing device 12 according to this embodiment includes a hard disk drive (HDD) 26 that stores various data, application programs, and the like. The printing device 12 is also connected to a user interface 22 and includes a display control unit 28 that controls the display of various operation screens and the like on the display of the user interface 22. The printing device 12 is also connected to the user interface 22 and includes an operation input detection unit 30 that detects operation instructions input via the user interface 22. In the printing device 12, the HDD 26, the display control unit 28, and the operation input detection unit 30 are electrically connected to a system bus 42. While the printing device 12 according to this embodiment uses the HDD 26 as a storage unit, this is not a limitation and a non-volatile storage unit such as a flash memory may also be used. Furthermore, while this embodiment uses a touch panel capable of displaying and inputting operations as the user interface 22, this is not a limitation and a user interface having a display and an operation unit that are separate may also be used.

[0032] The printing device 12 according to this embodiment also includes a print control unit 34 that controls the printing process performed by the printing unit 24, the transport of paper to the printing unit 24 by the transport unit 25, and the post-processing performed by the post-processing unit 46. The printing device 12 may also include a read control unit that controls the optical image reading operation performed by the document reading unit and the document feeding operation performed by the document transport unit. The printing device 12 also includes a communication line I / F (interface) unit 36 ​​that is connected to the communication line 18 and transmits and receives communication data to and from other external devices, such as the client computer 14, connected to the communication line 18. The printing device 12 may also include a facsimile I / F (interface) unit that is connected to a telephone line (not shown) and transmits and receives facsimile data to and from a facsimile device connected to the telephone line. The printing device 12 may also include a transmission / reception control unit that controls the transmission and reception of facsimile data via the facsimile I / F unit 38. In the printing device 12, the print control unit 34 and the communication line I / F unit 36 ​​are electrically connected to a system bus 42.

[0033] With the above configuration, the printing device 12 according to this embodiment uses the control unit 20 to control the display of information such as operation screens and various messages on the display of the user interface 22 via the display control unit 28. The printing device 12 also uses the control unit 20 to control the operation of the printing unit 24, conveying unit 25, and post-processing unit 46 via the print control unit 34, and to control the sending and receiving of communication data via the communication line I / F unit 36. Furthermore, the printing device 12 uses the control unit 20 to grasp the operation content of the user interface 22 based on the operation information detected by the operation input detection unit 30, and executes various controls based on this operation content.

[0034] In this embodiment, an example of an application stored in the HDD 26 includes an application that executes a function such as printing.

[0035] Next, the configuration of the main electrical parts of the management device 11 and the client computer 14 according to this embodiment will be described. Fig. 3 is a block diagram showing the configuration of the main electrical parts of the management device 11 and the client computer 14 in the information processing system 10 according to this embodiment. Note that the management device 11 and the client computer 14 have general computer configurations, and therefore, the following description will be given using the management device 11 as a representative.

[0036] As shown in FIG. 3 , the management device 11 according to this embodiment includes a CPU 11A as an example of a processor, a ROM 11B, a RAM 11C, a storage 11D, an operation unit 11E, a display unit 11F, and a communication line I / F (interface) unit 11G. The CPU 11A controls the overall operation of the management device 11. The ROM 11B stores various control programs and parameters in advance. The RAM 11C is used as a work area when the CPU 11A executes various programs. The storage 11D stores various data and application programs. The operation unit 11E is used to input various information. The display unit 11F is used to display various information. The communication line I / F unit 11G is connected to a communication line 18 and transmits and receives various data to and from other devices connected to the communication line 18. The communication line I / F unit 11G may also be configured to be capable of directly communicating with each device using various well-known wireless communications. The above-described components of the management device 11 are electrically connected to one another via a system bus 111. In the management device 11 according to this embodiment, the storage 11D is used as a storage unit, and examples of storage include non-volatile storage units such as HDDs (Hard Disk Drives) and flash memories.

[0037] With the above configuration, the management device 11 according to this embodiment uses the CPU 11A to access the ROM 11B, RAM 11C, and storage 11D, to obtain various data via the operation unit 11E, and to display various information on the display unit 11F. In addition, the management device 11 uses the CPU 11A to control the transmission and reception of communication data via the communication line I / F unit 11G.

[0038] In the information processing system 10 configured as above, the management device 11 manages a series of manufacturing processes. The series of manufacturing processes includes, for example, a production process, a prepress process, a plate making process, a printing process, a processing process, and a delivery process.

[0039] Next, a description will be given of the functional configuration of the client computer 14. Fig. 4 is a block diagram showing an example of the functional configuration of the client computer 14.

[0040] As shown in FIG. 4, the client computer 14 is functionally configured to include a collection unit 101, a learning data storage unit 102, a learning unit 103, a model storage unit 104, a reception unit 105, a summarization unit 106, a summary storage unit 107, and an output unit 108.

[0041] The collection unit 101 collects learning data including pairs of information defining a workflow of a past printing job and a summary corresponding to the information defining the workflow.

[0042] The information defining the workflow of a printing job includes information showing the connections between each step of the printing job and information about the processing content of each step. The information defining the workflow of a printing job includes, for example, information exported from software that manages the workflow of the printing job. The exported information includes, for example, an Excel file or XML file that records the configuration of the workflow, including the information defining the workflow.

[0043] The management device 11 has software for managing a workflow. The collection unit 101 acquires information defining a workflow from the software for managing a workflow that the management device 11 has.

[0044] A summary corresponding to information defining the workflow of past printing operations is created by a user and managed by a management device 11, and the collection unit 101 acquires the summary of the information defining the workflow of the printing operations from the management device 11.

[0045] The summary of workflow information created by the user includes, for example, the type of printed matter, the type of processing, order information (customer information), raw material names, processing days, or costs.

[0046] The types of printed materials include, for example, photo books, posters, magazines, flyers, envelopes, business cards, catalogs, newspapers, etc. The types of processing include, for example, stapling (staple position, X-point stitching, center-fold booklet X-point stitching), punching (two-hole, three-hole, four-hole, coil punch), cutting, etc. The order information includes, for example, the customer company name, the name of the customer representative, the order location, or the order time. The raw material names include, for example, the ink or toner name, the paper type, and the accessories (envelope pattern name, obi (sash), bookmark, enclosed flyer). The number of processing days includes, for example, the total number of days from order receipt to shipping. The cost includes, for example, an estimated price.

[0047] The learning data storage unit 102 stores a plurality of pieces of learning data collected by the collection unit 101.

[0048] The learning unit 103 constructs a large-scale language model based on multiple learning data by inputting information defining the workflow of a printing job and a prompt statement instructing the large-scale language model to summarize the contents of the workflow, so that the large-scale language model outputs a summary of the information defining the workflow.

[0049] Specifically, the trained large-scale language model accepts input information including information defining a printing work workflow and a prompt statement instructing that the content of the workflow be summarized, and outputs a summary of the information defining the workflow (see Figure 5). Generative AI (Artificial Intelligence) can be used as an example of a large-scale language model, and fine-tuning of generative AI can be used as an example of a learning algorithm.

[0050] The model storage unit 104 stores a trained large-scale language model. Note that the trained large-scale language model may be stored in an external device.

[0051] The receiving unit 105 receives information that defines the workflow of the printing job to be summarized.

[0052] Specifically, the receiving unit 105 receives information defining a workflow from software that manages a workflow and that is included in the management device 11. The information defining a workflow includes information exported from the software that manages the workflow.

[0053] The summarization unit 106 inputs information defining the workflow of the printing business and a prompt statement instructing to summarize the contents of the workflow into a trained large-scale language model stored in the model storage unit 104, and obtains a summary of the information defining the workflow from the output of the large-scale language model.

[0054] Specifically, the summarization unit 106 creates a prompt statement instructing that the contents of the workflow be summarized, and inputs the information defining the received workflow, the created prompt statement, and the information defining the workflow into a trained large-scale language model, thereby obtaining a summary of the information defining the workflow from the output of the large-scale language model.

[0055] The summary storage unit 107 stores summaries obtained by the summarizing unit 106 for each piece of information defining the workflow of the printing job.

[0056] The output unit 108 outputs to the user the summary stored in the summary storage unit 107. For example, when the user defines a workflow for a new printing job, the user can refer to the summary stored in the summary storage unit 107 to determine whether there is information defining the workflow of a past printing job that can be used when defining the workflow for the new printing job.

[0057] Next, specific processing performed in the information processing system 10 according to this embodiment configured as described above will be described.

[0058] First, in the client computer 14, the CPU 14A reads out the learning program from the ROM 14B or the storage 14D, loads it into the RAM 14C, and executes it, thereby performing the learning process shown in FIG.

[0059] In step S100, the CPU 14A, as the collection unit 101, compiles learning data including pairs of information defining the workflow of past printing operations and summaries corresponding to the information defining the workflow, and stores the learning data in the learning data storage unit 102.

[0060] In step S102, CPU 14A, as the learning unit 103, learns the large-scale language model based on multiple learning data by inputting information defining the workflow of the printing work and a prompt statement instructing the large-scale language model to summarize the contents of the workflow, so that the large-scale language model outputs a summary of the information defining the workflow, stores the summary in model storage unit 104, and terminates the learning process.

[0061] Next, in the client computer 14, the CPU 14A reads out the information processing program from the ROM 14B or the storage 14D, expands it into the RAM 14C, and executes it, thereby performing the summarization process shown in Fig. 8. At this time, a workflow for the printing job is defined in the software that manages the workflow by a user operation, as shown in Fig. 7. Then, the summarization process is repeatedly performed on each piece of information that defines the workflow and that is exported from the software that manages the workflow, as the object of summarization.

[0062] In step S110, CPU 14A, functioning as reception unit 105, receives information defining a workflow from software that management device 11 has and that manages a workflow.

[0063] In step S112, CPU 14A functions as summarizing section 106 to create a prompt statement instructing that the contents of the workflow be summarized.

[0064] In step S114, CPU 14A, functioning as summarizing unit 106, inputs the information defining the accepted workflow and the created prompt sentence into the trained large-scale language model.

[0065] In step S114, CPU 14A, functioning as summarization unit 106, acquires a summary of the information defining the workflow from the output of the large-scale language model, stores it in summary storage unit 107, and ends the summarization process.

[0066] When the user defines a workflow for a new printing job, the user refers to the summary stored in the summary storage unit 107 and determines whether there is information defining the workflow of a past printing job that can be used when defining the workflow for the new printing job.

[0067] By performing the process in this manner, it is possible to automatically summarize workflow information relating to printing operations.

[0068] <Modification> The present invention is not limited to the above-described embodiment, and various modifications and applications are possible without departing from the spirit and scope of the present invention.

[0069] For example, although a large-scale language model has been used as the trained model, the present invention is not limited to this. A model for extracting keywords related to various items to be included in a summary of information defining a workflow may also be used as the trained model. In this case, the information defining the workflow is input to the trained model, and the summary is obtained from the output of the model.

[0070] Furthermore, although the client computer 14 has been described as learning a model and acquiring summaries, it may be configured as a learning device that learns a model and a summarizing device that acquires summaries.

[0071] The prompt sentence may also include an instruction sentence that instructs the user not to include information in the summary of workflow information. For example, the prompt sentence may include an instruction sentence that instructs the user not to include customer information (customer name) in the summary. This makes it possible to exclude customer information (customer name) from the summary.

[0072] Furthermore, in the above embodiments, the term "processor" refers to a processor in a broad sense, and includes general-purpose processors (e.g., CPUs, etc.) and dedicated processors (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

[0073] Furthermore, the operations of the processors in the above embodiments may not only be performed by a single processor, but may also be performed by multiple processors located at physically separate locations working together. Furthermore, the order of the operations of the processors is not limited to the order described in the above embodiments, and may be changed as appropriate.

[0074] Furthermore, although the "system" in this embodiment is described as being composed of multiple devices as an example, it may also be composed of a single device that has some of the functions of the multiple devices.

[0075] The processing performed by the printing device 12 according to the above embodiment may be software-based, hardware-based, or a combination of both. The processing performed by the printing device 12 may also be stored as a program on a storage medium and distributed.

[0076] Furthermore, the present disclosure is not limited to the above, and it goes without saying that various modifications can be made without departing from the spirit of the present disclosure.

[0077] The following additional notes are provided regarding the above-described embodiments. (((1))) a processor, the processor comprising: By inputting new input information including information defining a workflow of a printing job into a trained model that has been trained in advance to output a summary of the input information, a summary of the information defining the workflow is output. Information processing system.

[0078] (((2))) the trained model is a large-scale language model, The processor: An information processing system as described in (((1))) in which information defining a workflow of a printing job and a prompt statement instructing that the contents of the workflow be summarized are input to the large-scale language model, and a summary of the information defining the workflow is obtained from the output of the large-scale language model.

[0079] (((3))) The information defining the workflow of the printing job is information exported from software that manages the workflow. The information processing system according to (((1))) or (((2))).

[0080] (((4))) The information processing system described in (((2))) includes an instruction statement instructing that the summary of the workflow information include the type of printed material, the type of processing, order information, raw material names, processing days, or cost.

[0081] (((5))) The information processing system according to (((2))), wherein the prompt statement includes a directive statement indicating information that is not to be included in the summary of the workflow information.

[0082] (((6))) The large-scale language model is pre-trained to include the type of printed material, the type of processing, order information, raw material names, processing time, or cost in the summary of the workflow information (((2))).

[0083] (((7))) The processor: presenting a summary of workflow information when a user defines a new workflow using the software; The information processing system according to (((3))).

[0084] (((8))) By inputting new input information including information defining a workflow of a printing job into a trained model that has been trained in advance to output a summary of the input information, a summary of the information defining the workflow is output. An information processing program that causes a computer to perform certain tasks.

[0085] According to (((1))), workflow information related to printing operations can be automatically summarized.

[0086] According to (((2))), workflow information related to printing operations can be automatically summarized using a large-scale language model.

[0087] According to (((3))), workflow information related to printing operations can be automatically summarized using information exported from software that manages workflows.

[0088] According to (((4))), it is possible to automatically summarize information on the workflow of printing work, including the type of printed matter, the type of processing, order information, raw material names, processing time, or cost.

[0089] According to (((5))), it is possible to automatically summarize information on the workflow of printing work, including the type of printed matter, the type of processing, order information, raw material names, processing days, or costs.

[0090] According to (((6))), it is possible to specify information that is not to be included in the summary of workflow information related to printing work.

[0091] According to (((7))), when a user defines a new workflow using software, it is possible to assist the user in determining whether or not an existing workflow can be used.

[0092] According to (((8))), workflow information related to printing operations can be automatically summarized. [Explanation of symbols]

[0093] 10 Information Processing Systems 11 Management device 12 Printing device 14 client computers 24 Printing Department 101 Collection Department 102 Learning data storage unit 103 Learning Department 104 Model Memory Unit 105 Reception 106 Summary 107 Summary Memory Unit 108 Output section

Claims

1. a processor, the processor comprising: By inputting new input information including information defining a workflow of a printing job into a trained model that has been trained in advance to output a summary of the input information, a summary of the information defining the workflow is output. Information processing system.

2. the trained model is a large-scale language model, The processor: An information processing system as described in claim 1, wherein information defining a workflow of a printing job and a prompt statement instructing that the contents of the workflow be summarized are input to the large-scale language model, and a summary of the information defining the workflow is obtained from the output of the large-scale language model.

3. The information defining the workflow of the printing job is information exported from software that manages the workflow. The information processing system according to claim 1 .

4. 3. The information processing system according to claim 2, wherein the prompt statement includes an instruction statement instructing that the summary of the workflow information include the type of printed matter, the type of processing, order information, raw material names, processing days, or cost.

5. 3. The information processing system according to claim 2, wherein the prompt statement includes a directive statement that indicates information that is not to be included in the summary of the workflow information.

6. 3. The information processing system according to claim 2, wherein the large-scale language model is pre-trained to include in the summary of the workflow information the type of printed material, the type of processing, order information, raw material names, processing time, or cost.

7. The processor: presenting a summary of workflow information when a user defines a new workflow using the software; The information processing system according to claim 3 .

8. By inputting new input information including information defining a workflow of a printing job into a trained model that has been trained in advance to output a summary of the input information, a summary of the information defining the workflow is output. An information processing program that causes a computer to perform certain tasks.

Citation Information

Patent Citations

  • Printing order system and program

    JP2021026535A