Parameter generation device, parameter generation method, and parameter generation program

Abstract

This allows for the easy generation of system parameters that reflect organizational rules. [Solution] The preprocessing unit 23 combines the data from multiple documents into a single document if the rule data, which defines the rules for the target organization, includes data from multiple documents. The input unit 21 inputs the rule data, which has been combined into a single document, into the trained model 40. The output unit 22 outputs parameters that indicate information about management items managed by the management system of the target organization, which are generated by the trained model 40 in response to the rule data input by the input unit 21.

Description

Technical Field

[0001] This disclosure relates to a technique for generating system parameters that reflect the rules of an organization.

Background Art

[0002] In an organization's management system such as an attendance management system, the rules of the organization are reflected as parameters. For example, in an attendance management system, information on management items such as working hours and vacations defined by the organization is reflected and the operation is controlled. In order to reflect the rules of an organization in a management system, it is necessary to extract the necessary information by an engineer reading a document in which the rules of the organization are described or by the engineer conducting a hearing with the person in charge of the organization.

[0003] Patent Document 1 describes that when logging in to a system, a questionnaire is answered and the menu screen of the system is changed according to the answer.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The items that need to be reflected in the management system are detailed and diverse. Therefore, it takes a burden and time for an engineer or the person in charge of the organization to read a document in which the rules of the organization are described or for the engineer to conduct a hearing with the person in charge of the organization and extract the information on each item. An object of this disclosure is to enable the easy generation of system parameters that reflect the rules of an organization.

Means for Solving the Problems

[0006] The parameter generation device relating to this disclosure is An input unit that inputs rule data defining the rules of the target organization into a trained model, An output unit outputs parameters that indicate information about management items managed by the management system of the target organization, which are generated by the trained model in response to the rule data input by the input unit. If the rule data includes data from multiple documents, a preprocessing unit is used to combine the data from the multiple documents into the data of a single document. Equipped with, The input unit inputs the rule data, which has been compiled into a single document by the preprocessing unit, into the trained model. [Effects of the Invention]

[0007] This disclosure involves inputting rule data into a trained model to obtain parameters that represent information about management items managed by the management system. This makes it possible to easily generate system parameters that reflect the organization's rules. [Brief explanation of the drawing]

[0008] [Figure 1] Configuration diagram of the parameter generation device 10 according to Embodiment 1. [Figure 2] A flowchart showing the processing flow of the parameter generation device 10 according to Embodiment 1. [Figure 3] This is an example of an excerpt from employment regulations data, specifically showing an example of information such as working hours and break times. [Figure 4] This is an example of an excerpt from employment regulations data, specifically an example of an excerpt regarding leave information. [Figure 5] This figure illustrates an example of a prompt for extracting working hours and break times as management items, and parameters 31 generated by a trained model 40 in response to this prompt. [Figure 6]A diagram showing an example of a prompt for extracting leave as a management item and parameters 31 generated by the learned model 40 corresponding to this prompt. [Figure 7] Configuration diagram of the parameter generation device 10 according to Embodiment 2. [Figure 8] Flowchart of the processing flow of the parameter generation device 10 according to Embodiment 2. [Figure 9] Configuration diagram of the parameter generation device 10 according to Embodiment 3. [Figure 10] Flowchart of the processing flow of the parameter generation device 10 according to Embodiment 3. [Figure 11] Configuration diagram of the parameter generation device 10 according to Embodiment 4. [Figure 12] Flowchart of the processing flow of the parameter generation device 10 according to Embodiment 4. [Figure 13] A diagram showing an example of a hearing sheet according to Embodiment 4. [Figure 14] A diagram showing an example of a hearing sheet according to Embodiment 4.

Mode for Carrying Out the Invention

[0009] Embodiment 1. In Embodiment 1, an attendance management system will be described as an example of an organization management system in which the organization's rules are reflected as parameters. However, the organization management system is not limited to the attendance management system, and other systems such as a salary system can also be considered.

[0010] ***Explanation of Configuration*** Referring to FIG. 1, the configuration of the parameter generation device [i=10] according to Embodiment 1 will be described. The parameter generation device 10 is a computer. The parameter generation device 10 includes hardware such as 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 these other hardware.

[0011] Processor 11 is an IC that performs processing. IC is an abbreviation for Integrated Circuit. As specific examples, processor 11 is a CPU, DSP, or GPU. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

[0012] Memory 12 is a storage device that temporarily stores data. As specific examples, memory 12 is SRAM or DRAM. SRAM is an abbreviation for Static Random Access Memory. DRAM is an abbreviation for Dynamic Random Access Memory.

[0013] Storage 13 is a storage device that stores data. As a specific example, storage 13 is an SSD. SSD is an abbreviation for Solid State Drive. Also, storage 13 may be a removable recording medium such as an SD (registered trademark) memory card, CompactFlash (registered trademark), NAND flash, flexible disk, optical disk, compact disk, Blu-ray (registered trademark) disk, or DVD. SD is an abbreviation for Secure Digital. DVD is an abbreviation for Digital Versatile Disk.

[0014] Communication interface 14 is an interface for communicating with an external device. As specific examples, communication interface 14 is a port for Ethernet (registered trademark), USB, or HDMI (registered trademark). USB is an abbreviation for Universal Serial Bus. HDMI is an abbreviation for High-Definition Multimedia Interface.

[0015] The parameter generation device 10 includes an input unit 21 and an output unit 22 as functional components. The functions of each functional component of the parameter generation device 10 are realized by software. Storage 13 stores programs that implement the functions of each functional component of the parameter generation device 10. These programs are loaded into memory 12 by the processor 11 and executed by the processor 11. This enables the implementation of the functions of each functional component of the parameter generation device 10.

[0016] Parameter 31 is stored in storage 13.

[0017] The parameter generation device 10 is connected to the trained model 40 via a communication interface 14. The trained model 40 is a so-called generative AI. AI stands for Artificial Intelligence. The training model 112 may be constructed using algorithms such as BERT or GPT, as a specific example. BERT stands for Bidirectional Encoder Representations from Transformers. GPT stands for Generative Pretrained It is an abbreviation for Transformer. The learning model 112 may be composed of a combination of multiple algorithms, including these algorithms.

[0018] In Figure 1, the trained model 40 was located outside the parameter generation device 10. However, the trained model 40 may also be included as a functional component of the parameter generation device 10.

[0019] In Figure 1, only one processor 11 was shown. However, there may be multiple processors 11, and multiple processors 11 may work together to execute programs that implement each function.

[0020] ***Explanation of operation*** The operation of the parameter generation device 10 according to Embodiment 1 will be explained with reference to Figures 2 to 6. The operation procedure of the parameter generation device 10 according to Embodiment 1 corresponds to the parameter generation method according to Embodiment 1. Furthermore, the program that implements the operation of the parameter generation device 10 according to Embodiment 1 corresponds to the parameter generation program according to Embodiment 1.

[0021] Referring to Figure 2, the processing flow of the parameter generation device 10 according to Embodiment 1 will be explained. (Step S11: Input Processing) The input unit 21 inputs rule data, which defines the rules of the target organization, into the trained model 40. In Embodiment 1, the rule data is document data that includes legally mandated rules regarding employment and regulations established by each organization. Organizational regulations include at least one of the agreements reached between labor and management and other internal rules. Specifically, these could include data outlining rules for attendance management, data outlining company regulations other than work rules, data outlining the rules for handling flextime, and data outlining work management guidelines.

[0022] In this case, the input unit 21 specifically instructs the trained model 40 as a prompt to specify the management items to be extracted. In Embodiment 1, the management items include working hours, break times, holidays, allowances, and handling of overtime. For example, the input unit 21 may generate separate prompts for each management item and input them sequentially into the trained model 40. This clarifies the extraction instructions for each management item and increases the likelihood of appropriate information extraction.

[0023] Furthermore, the input unit 21 may receive an instruction to output that information on management items that cannot be identified from the rule data cannot be identified without inferring from other information. This is because if the trained model 40 is unable to extract information on management items from the rule data, it may mistakenly extract general rules such as the Labor Standards Act as the rules of that organization. General rules may differ from organizational rules. Therefore, if general rules are extracted and reflected in the management system, it may be difficult to properly control the management system.

[0024] When rule data is entered in step S11, the trained model 40 generates parameters 31 that indicate information about the management items managed by the management system of the target organization, corresponding to the rule data. Specifically, the trained model 40 extracts information about the management items specified in step S11 from the rule data and generates it as parameters 31.

[0025] (Step S12: Acquisition process) The output unit 22 obtains the parameters 31 generated by the trained model 40 in response to the rule data and prompts input in step S11. The output unit 22 then writes the obtained parameters 31 to the storage 13. In this case, the output unit 22 may output the parameter 31 to a user terminal or the like connected via the communication interface 14. This allows the user to confirm the parameter 31. This also allows the user to confirm whether or not there were any management items that could not be identified. If there were any management items that could not be identified, the user will need to identify those management items using conventional methods or the like. Here, the user is assumed to be the administrator in charge of the management system.

[0026] (Step S13: Output processing) The output unit 22 outputs the parameter 31 acquired in step S12 to the management system. In Embodiment 1, the management system is an attendance management system. As a result, the parameter 31 is reflected in the management system. In other words, the rules of the target organization are reflected in the management system.

[0027] Referring to Figures 3 to 6, an example of the prompt entered in step S11 of Embodiment 1 and the parameters 31 generated by the trained model 40 will be explained. Figures 3 and 4 are examples of excerpts from the employment regulations data. Figure 3 contains information such as working hours and break times. Figure 4 contains information regarding leave.

[0028] Figure 5 shows an example of a prompt for extracting working hours and break times as management items, and parameters 31 generated by the trained model 40 in response to this prompt. In Figure 5, the prompt is set with #command, #constraint, and #output format. The #command instructs the system to extract information about working hours. The #constraint sets the management items to be extracted as shift name, start time, end time, break start time, and break end time. The #output format outputs the shift name, start time, end time, break start time, and break end time in that order. Previously, the output format was set to hh:ss, hh:ss, hh:ss, hh:ss. In response to this, the trained model 40 extracts information from the rule data for each shift name, including the start time of work, the end time of work, the start time of break, and the end time of break, and outputs it as parameters 31 in a format that the management system can operate in. Here, this information is extracted from the information shown in Figure 3 and output in the format set by #Output Format. It is being output. Here, in the rule data, the term "shift work and work pattern" may be used as a synonym for "shift work," which is one of the names indicating work. Therefore, the first line of the constraint defines that "shift work and work pattern" should be replaced with "shift work." In this way, it is desirable in prompts to define that the name written to the right of the colon should be replaced with the name to the left of the colon, so as not to limit the extraction target by name as much as possible.

[0029] Figure 6 shows an example of a prompt instructing the extraction of vacation as a management item, and parameters 31 generated by the trained model 40 in response to this prompt. In Figure 6, the prompt is set to #command, #constraint, and #output format. The #command instructs the system to extract information about vacations. The #constraint specifies that the output should be in CSV format, and the management items to be extracted are set to be name, type, and start / end. CSV stands for Comma-Separated Values. The #output format is set to output in the order of name, type, and start / end. In response, the trained model 40 extracts information such as the type and start / end dates for each vacation name from the rule data and outputs them as parameters 31. Here, this information is extracted from the information shown in Figure 4 and output in the format set by #Output Format.

[0030] Furthermore, the parameter 31 that the output unit 22 outputs to the management system in step S13 may be data from which unnecessary information has been removed from parameter 31. For example, parameter 31 in Figure 5 includes the sentences "The following summarizes..." and "This information is...detailed...". However, these are not pieces of information that should be set in the management system. Therefore, the output unit 22 may remove the parts of parameter 31 that do not match the format set in #Output Format before outputting it to the management system.

[0031] ***Effects of Embodiment 1*** As described above, the parameter generation device 10 according to Embodiment 1 inputs rule data into the trained model 40 to obtain parameters 31 that indicate information on management items managed by the management system. This makes it possible to easily generate system parameters 31 that reflect the organization's rules.

[0032] ***Other configurations*** <Example 1> In Embodiment 1, it was assumed that the parameter generation device 10 was located outside the management system. However, the parameter generation device 10 may be part of the attendance management system. In this case, the parameter reflection unit of the management system reflects the parameters 31 acquired in step S12 into the system's configuration information.

[0033] Embodiment 2. Embodiment 2 is the case where the rule data includes data from multiple documents. The difference from Embodiment 1 is that data from multiple documents is combined into data from a single document before being input into the trained model 40. Embodiment 2 explains this difference, while omitting explanations of the same points.

[0034] ***Explanation of the structure*** Referring to Figure 7, the configuration of the parameter generation device 10 according to Embodiment 2 will be described. The parameter generation device 10 differs from the parameter generation device 10 shown in Figure 1 in that it includes a pre-processing unit 23 as a functional component. The functions of the pre-processing unit 23 are implemented by software, similar to other functional components.

[0035] ***Explanation of operation*** Referring to Figure 8, the processing flow of the parameter generation device 10 according to Embodiment 2 will be explained. The processes in steps S23 and S24 are the same as the processes in steps S12 and S13 in Figure 2.

[0036] (Step S21: Pre-treatment) The preprocessing unit 23 combines the data from multiple documents included in the rule data into the data of a single document. Specifically, the preprocessing unit 23 sequentially concatenates each document to generate the data of a single document.

[0037] (Step S22: Input Processing) The input unit 21 inputs the rule data, which has been consolidated into a single document in step S21, into the trained model 40. The rest of the process is the same as in step S11 in Figure 2.

[0038] ***Effects of Embodiment 2*** As described above, the parameter generation device 10 according to Embodiment 2, when the rule data includes data from multiple documents, combines the data from multiple documents into the data from one document and inputs it into the trained model 40. When data from multiple documents is input into the trained model 40, it is possible that information may be extracted only from some documents, and information contained in the remaining documents may not be extracted. The parameter generation device 10 according to Embodiment 2 prevents such a situation and makes it possible to extract information appropriately.

[0039] Embodiment 3. Embodiment 3 differs from Embodiments 1 and 2 in that, if the rule data includes reference information, the data indicated by the reference information is acquired and input into the trained model 40. Embodiment 3 explains this difference, while omitting explanations of the same points. Embodiment 3 describes a case in which a modification has been made to Embodiment 1. However, it is also possible to modify Embodiment 2.

[0040] ***Explanation of the structure*** Referring to Figure 9, the configuration of the parameter generation device 10 according to Embodiment 3 will be described. The parameter generation device 10 differs from the parameter generation device 10 shown in Figure 1 in that it includes a data extraction unit 24 as a functional component. The function of the data extraction unit 24 is implemented by software, similar to other functional components.

[0041] ***Explanation of operation*** Referring to Figure 10, the processing flow of the parameter generation device 10 according to Embodiment 3 will be explained. The process in step S33 is the same as the process in step S13 in Figure 2.

[0042] (Step S31: Input Processing) The input unit 21 prompts for an instruction to output reference information if the rule data contains reference information indicating the referenced data. Reference information is a link to the referenced data, or a URL indicating the location of the referenced data. URL is an abbreviation for Uniform Resource Locator.

[0043] (Step S32: Acquisition process) The output unit 22 retrieves the parameter 31 or reference information generated by the trained model 40 in response to the rule data and prompt input in step S11. If the parameter 31 is retrieved, the output unit 22 writes the parameter 31 to the storage 13 and proceeds to step S33. On the other hand, if the reference information is retrieved, the output unit 22 proceeds to step S34.

[0044] (Step S34: Data extraction process) The data extraction unit 24 retrieves the referenced data indicated by the referenced information obtained in step S32. Then, the data extraction unit 24 adds the referenced data to the referenced information portion of the rule data and returns the process to step S31. As a result, information is extracted from the rule data to which the referenced data has been added.

[0045] ***Effects of Embodiment 3*** As described above, the parameter generation device 10 according to Embodiment 3 acquires the data indicated by the reference information and inputs it into the trained model 40. In some cases, the documentation does not provide specific details, only stating that other data should be referenced. The parameter generation device 10 according to Embodiment 3 can appropriately extract information even in such cases.

[0046] Embodiment 4. Embodiment 4 differs from Embodiments 1 to 3 in that the generated parameters 31 are confirmed by a person in charge at the organization. Embodiment 4 explains this difference, while omitting explanations of the same points. Embodiment 4 describes a case in which a modification has been made to Embodiment 1. However, it is also possible to modify Embodiments 2 and 3.

[0047] ***Explanation of the structure*** Referring to Figure 11, the configuration of the parameter generation device 10 according to Embodiment 4 will be described. The parameter generation device 10 differs from the parameter generation device 10 shown in Figure 1 in that it includes a setting unit 25 as a functional component. The function of the setting unit 25 is implemented by software, just like the other functional components.

[0048] Referring to Figure 12, the processing flow of the parameter generation device 10 according to Embodiment 4 will be explained. The processes in steps S41 and S42 are the same as the processes in steps S11 and S12 in Figure 2.

[0049] (Step S43: Setup process) The setting unit 25 sets the information indicated by the parameter 31 obtained in step S42 into the corresponding input fields of the management items in the setting item data, which shows descriptions and input fields for multiple management items necessary for setting the management system. The configuration item data is, for example, used when interviewing organizational personnel about organizational rules. This data is similar to the interview sheet used. In other words, the configuration item data is designed to ensure that all necessary management items are collected from the organization's personnel, and includes explanations for each management item and input fields for entering the collected information.

[0050] The setting item data, in which the information indicated by parameter 31 has been set by the setting unit 25, is sent to the person in charge of the target organization. The person in charge then verifies whether the set information is correct. It is possible that information may not be set for all management items in the setting item data. In this case, the person in charge of the organization will set the missing items with information based on the rules of the target organization.

[0051] Figure 13 shows an example in step S43 where information indicating parameter 31 is set in the setting item data in the same format as the hearing sheet. As shown in Figure 13, the leave name, acquisition unit, and other items are set based on parameter 31. The circle in the acquisition unit column indicates that it is applicable. This allows engineers and organizational personnel to verify whether parameter 31 is set to satisfy the rule data, including at least the type of leave, the number of units taken, and other supplementary information.

[0052] Figure 14 also shows an example where the management method, attendance rate calculation, and paid / unpaid leave are updated based on a request from an engineer or organizational representative, when the setting item data shown in Figure 13 is in an updatable state. In Figure 13, the half-day leave set in the second row and the half-day leave set in the third row are combined into a single annual paid leave, and a circle (〇) is set to indicate that the half-day unit of leave is applicable. By setting parameter 31 in the setting item data in this way, the degree to which parameter 31 is satisfied with the rule data can be checked at a glance. Furthermore, since the processing of the setting unit 25 may not adequately check the degree of satisfaction, configuring the system to accept specifications from engineers or organizational personnel and update the setting item data, as shown in Figure 14, may allow for more thorough verification by engineers or organizational personnel.

[0053] ***Effects of Embodiment 4*** As described above, the parameter generation device 10 according to Embodiment 4 sets the information extracted by the trained model 40 into the corresponding input fields of the management items in the setting item data, which shows the descriptions and input fields of multiple management items necessary for setting the management system. This makes it easy for the person in charge to verify whether the extracted information is correct.

[0054] ***Other configurations*** <Modification 2> In Embodiment 1, each functional component was implemented in software. However, in Modification 2, each functional component may be implemented in hardware. The differences between this Modification 2 and Embodiment 1 will be explained below.

[0055] When each functional component is implemented in hardware, the parameter generation device 10 includes electronic circuits instead of the processor 11, memory 12, and storage 13. The electronic circuits are dedicated circuits that implement the functions of each functional component, as well as the functions of the memory 12 and storage 13.

[0056] Electronic circuits can include single circuits, complex 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-P It is an abbreviation for rogrammable Gate Array. Each functional component may be implemented in a single electronic circuit, or it may be implemented by distributing each functional component across multiple electronic circuits.

[0057] <Variation 3> As a third variation, some of the functional components may be implemented in hardware, while others may be implemented in software.

[0058] The processor 11, memory 12, storage 13, and electronic circuitry are collectively referred to as the processing circuit. In other words, the function of each functional component is realized by the processing circuit.

[0059] Furthermore, the term "part" in the above explanation may be replaced with "circuit," "process," "procedure," "processing," or "processing circuit."

[0060] The various aspects of this disclosure are summarized below as an appendix. (Note 1) An input unit that inputs rule data defining the rules of the target organization into a trained model, An output unit outputs parameters that indicate information about management items managed by the management system of the target organization, which are generated by the trained model in response to the rule data input by the input unit. A parameter generation device equipped with the following features. (Note 2) The aforementioned rule data includes data such as employment regulations. The aforementioned management system is a system for managing attendance. The parameter generation device described in Appendix 1. (Note 3) The aforementioned management items are at least one of the following: working hours and break times, holidays, and allowances. The parameter generation device described in Appendix 2. (Note 4) The input unit receives an instruction to output that information on management items that cannot be identified from the rule data cannot be identified by inference from other information. A parameter generation device as described in any one of the items 1 to 3 in the appendix. (Note 5) The parameter generation device further, If the rule data includes data from multiple documents, a preprocessing unit combines the data from the multiple documents into the data of a single document. Equipped with, The input unit inputs the rule data, which has been compiled into a single document by the preprocessing unit, into the trained model. A parameter generation device as described in any one of the items 1 to 4 in the appendix. (Note 6) The input unit, if the rule data contains reference information indicating the referenced data, receives an instruction to output the reference information. The parameter generation device further, When the reference destination information is output from the trained model, the data acquisition unit acquires the data of the reference destination indicated by the reference destination information. Equipped with, The input unit inputs the reference data, in addition to the rule data, into the trained model. A parameter generation device as described in any one of the items 1 to 5 in the appendix. (Note 7) The parameter generation device further, The setting unit sets the information indicated by the parameters output by the output unit into the corresponding input fields of the management items in the setting item data, which shows the descriptions and input fields of multiple management items necessary for setting the management system. A parameter generation device according to any one of the appendices 1 to 6, comprising: (Note 8) The computer inputs rule data defining the rules of the target organization into a trained model. A parameter generation method in which a computer outputs parameters indicating information about management items managed by the management system of the target organization, which are generated by the trained model in response to the rule data. (Note 9) The input process involves inputting rule data, which defines the rules within the target organization, into a trained model. An output process that outputs parameters indicating information about management items managed by the management system of the target organization, which are generated by the trained model in response to the rule data input by the input process; and an output process that outputs parameters indicating information about management items managed by the management system of the target organization, which are generated by the trained model in response to the rule data input by the input process. A parameter generation program that makes a computer function as a parameter generation device.

[0061] The embodiments and variations of this disclosure have been described above. Some of these embodiments and variations may be implemented in combination. Alternatively, some or all of them may be implemented in part. However, this disclosure is not limited to the embodiments and variations described above, and various modifications are possible as needed. [Explanation of Symbols]

[0062] 10 Parameter generator, 11 Processor, 12 Memory, 13 Storage, 14 Communication interface, 21 Input unit, 22 Output unit, 23 Preprocessing unit, 24 Data extraction unit, 25 Setting unit, 31 Parameters, 40 Trained model.

Claims

1. An input unit that inputs rule data defining the rules of the target organization into a trained model, An output unit outputs parameters that indicate information about management items managed by the management system of the target organization, which are generated by the trained model in response to the rule data input by the input unit. If the rule data includes data from multiple documents, a preprocessing unit is used to combine the data from the multiple documents into the data of a single document. Equipped with, The input unit is a parameter generation device that inputs the rule data, which has been compiled into a single document by the preprocessing unit, into the trained model.

2. The aforementioned management items are at least one of the following: working hours and break times, holidays, and allowances. The parameter generation device according to claim 1.

3. The input unit, if the rule data contains reference information indicating the referenced data, receives an instruction to output the reference information. The parameter generation device further, When the reference destination information is output from the trained model, the data acquisition unit acquires the data of the reference destination indicated by the reference destination information. Equipped with, The input unit, in addition to the rule data, inputs the reference data into the trained model. to exert The parameter generation device according to claim 1.

4. The parameter generation device further, The setting unit sets the information indicated by the parameters output by the output unit into the corresponding input fields of the management items in the setting item data, which shows the descriptions and input fields of multiple management items necessary for setting the management system. The parameter generation device according to claim 1, comprising:

5. The computer inputs rule data defining the rules of the target organization into a trained model. The computer outputs parameters indicating information about management items managed by the management system of the target organization, which are generated by the trained model in response to the rule data. If the computer includes data from multiple documents as the rule data, it combines the data from the multiple documents into the data of a single document. A parameter generation method in which, if the rule data includes data from multiple documents, the computer inputs the rule data, which has been consolidated into data from a single document, into the trained model.

6. The input process involves inputting rule data, which defines the rules within the target organization, into a trained model. An output process that outputs parameters indicating information about management items managed by the management system of the target organization, which are generated by the trained model in response to the rule data input by the input process; If the aforementioned rule data includes data from multiple documents, a preprocessing step is taken to combine the data from those multiple documents into the data from a single document. The computer is used as a parameter generation device to perform this task. The input processing includes a parameter generation program that inputs the rule data, which has been consolidated into a single document by the preprocessing, into the trained model.

Images