Auxiliary system, auxiliary device, auxiliary method, and program

Abstract

Improve the efficiency of application document preparation for pesticide registration. [Solution] The auxiliary system is a system that assists in the preparation of application documents for pesticide registration, and has one or more processors. The processor accepts test results for the pesticide that is the subject of the application, generates application documents for the pesticide using a generation AI based on the laws and regulations regarding the registration of the pesticide and format information that defines the format of the application documents, and outputs the generated application documents to the applicant.

Description

[Technical Field]

[0001] The present invention relates to an auxiliary system, an auxiliary device, an auxiliary method, and a program for preparing application documents. [Background technology]

[0002] In countries around the world, the manufacture and sale of chemical products such as pesticides, pharmaceuticals, chemical substances, and cosmetics require approval and authorization from the appropriate administrative agency. For example, in Japan, pesticides are regulated by the Agricultural Chemicals Control Act, and only those that meet certain standards after review are registered as pesticides. In other words, when applying for pesticide registration, application documents for the pesticide's registration must be submitted to the administrative agency that acts as the registration authority, along with documents describing test results in various areas such as the pesticide's safety, toxicity, and residual properties (hereinafter referred to as "test reports"). The application must then be reviewed and approval (registration) obtained.

[0003] The application documents for the registration of pesticides are summaries (collections) of the test reports in accordance with the format specified by the country or region (for example, in Japan, regulations called dossier guidance). Application documents for the registration of pesticides are generally called "dossiers" and must be prepared for each test report.

[0004] Additionally, the current process for preparing application documents for pesticide registration requires applicants to manually review and summarize the contents of the enormous number of test reports to be submitted. The current process for preparing application documents for pesticide registration is a daunting task that requires a considerable amount of time and effort, including checking the numerical values ​​of test results, determining compliance with guidelines, and checking for typos. Furthermore, although the period varies by country and region, in Japan, the preparation and submission of such application documents is mandatory every 15 years. Therefore, there is a need for more efficient preparation of such application documents.

[0005] A system has been proposed that enables the creation of agricultural application forms required for certification applications for organic agricultural products, etc., in accordance with the variety and type of agricultural product (see, for example, Patent Document 1). However, this system does not improve the efficiency of creating application documents for the registration of pesticides. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-271703 Summary of the Invention [Problem to be solved by the invention]

[0007] The present invention aims to improve the efficiency of preparation of application documents for pesticide registration. [Means for solving the problem]

[0008] To this end, the present disclosure provides a system for assisting in the preparation of application documents for the registration of pesticides, which has one or more processors, and which accepts test results for the pesticide that is the subject of the application, generates application documents for the pesticide using a generation AI based on the laws and regulations regarding the registration of the pesticide and format information that defines the format of the application documents, and outputs the generated application documents to the applicant. [Effects of the Invention]

[0009] According to the present invention, the preparation of application documents for the registration of pesticides can be made more efficient. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram showing an outline of the configuration of an application document preparation assistance system according to an embodiment of the present invention. [Figure 2] 1 is a block diagram showing the hardware configuration of an application document preparation assisting device according to an embodiment of the present invention; [Figure 3] 1 is a block diagram illustrating an example of the configuration of an application document preparation assisting device that functions as a server in the present embodiment. [Figure 4] FIG. 10 is a sequence diagram showing an example of an application document preparation support process according to the present embodiment. [Figure 5] 1 is a flowchart illustrating an example of the basic operation of an application document generation process in the application document creation assist device according to the present embodiment. [Figure 6] FIG. 10 is a flowchart illustrating another operation of the application document generation process according to the present embodiment. [Figure 7] FIG. 10 is a flowchart illustrating another operation of the application document generation process according to the present embodiment. [Figure 8] FIG. 10 is a flowchart showing the operation of application document confirmation processing according to the present embodiment. [Figure 9] 10 is a diagram illustrating an example of display of evidence information in this embodiment. [Figure 10] FIG. 10 is a flowchart illustrating another operation of the application document confirmation process according to the present embodiment. [Figure 11] 10 is an example of a list of registerability according to the present embodiment. [Figure 12] 10 is an example of a confirmation recommendation display according to the present embodiment. [Figure 13] FIG. 10 is a flowchart illustrating another operation of the application document confirmation process according to the present embodiment. [Figure 14] FIG. 10 is a flowchart illustrating another operation of the application document confirmation process according to the present embodiment. [Figure 15] 10 is an example of a comparison column display according to the present embodiment. [Figure 16] FIG. 10 is a flowchart illustrating another operation of the application document confirmation process according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] The embodiments described below are preferred examples of the present invention and are therefore subject to various technical limitations. However, the scope of the present invention is not limited to these embodiments unless otherwise specified in the following description.

[0012] When preparing application documents for pesticide registration, it is possible to discover that test results, materials, etc. are insufficient during the preparation and submission stage. In the current situation where this is handled manually, it is difficult to carry out advance preparations for pesticide registration applications efficiently and without waste. Furthermore, when preparing application documents for pesticide registration at review agencies in countries or regions other than the home country, differences in the requirements between countries mean that the user must check and prepare test results and materials for the pesticide registration application again, which can be cumbersome. Therefore, there is a need for more efficient advance preparation for preparing application documents that take into account registration at multiple review agencies. Therefore, in this embodiment, the preparation of application documents for pesticide registration is made more efficient.

[0013] As an example of this embodiment, we will explain, with reference to the drawings, how generation AI is used to analyze the contents of test reports related to the registration of pesticides, efficiently generate application documents (hereinafter referred to as "dossiers") in accordance with a predetermined format, and assist in polishing the generated dossiers to increase the likelihood of the pesticide being registered.

[0014] (System Configuration) FIG. 1 is a diagram showing an outline of the configuration of an application document preparation support system according to this embodiment.

[0015] As shown in FIG. 1, application document preparation support system 1 in this embodiment includes application document preparation support device 10 that receives test reports describing test results regarding the safety, toxicity, residual properties, etc. of pesticides, checks the contents based on laws and regulations regarding pesticide registration (hereinafter referred to as "guidelines") and format information that defines the format of application documents, and generates a dossier. Furthermore, application document preparation support system 1 includes applicant terminal 30 that provides the test reports and receives the dossier, and administrator terminal 50 that manages this system 1 so that the dossier can be generated efficiently and accurately. Application document preparation support device 10, applicant terminal 30, and administrator terminal 50 are connected to each other so that they can communicate with each other via a network N such as the Internet. In the following description, application document preparation support system 1 may also be referred to as this system 1.

[0016] That is, this system 1 is a system that assists in the creation of dossiers for pesticide registration and has one or more processors. This system 1 accepts test results for pesticides that are the subject of an application. Furthermore, this system 1 is an auxiliary system that generates pesticide dossiers using a generation AI based on the laws and regulations related to pesticide registration and format information that defines the dossier format, and outputs the generated dossier to the applicant.

[0017] Here, the generation AI used in this embodiment can use large-scale language models (LLMs). The generation AI is obtained by performing deep learning on a neural network. A prompt containing instructions is input to the generation AI, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. The generation AI performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in a data format such as voice data and text data. Here, inference can be, for example, analysis, classification, prediction, and / or summarization. In this embodiment, a prompt is input that specifically specifies the information desired to be obtained so that the information desired to be output (generated) by the generation AI is obtained. Furthermore, in this embodiment, the prompt includes, depending on conditions, information to be used as material for generating the desired information.

[0018] The generation AI of this embodiment can also refer to organizational information limited to within an organization, such as a large amount of business documents and regulations accumulated in an organization such as a company. Furthermore, the generation AI of this embodiment can also refer to the latest information outside the organization that can be obtained via a network connected to the outside of the organization. The generation AI of this embodiment can generate information such as text based on organizational information while acquiring the latest information through information searches outside the organization.

[0019] The application document creation assistance device 10 receives a test report from the applicant terminal 30 and generates a dossier using a generation AI. The application document creation assistance device 10 not only generates a dossier efficiently, but also assists (supports) the applicant to appropriately refine the generated dossier. In addition, the application document creation assistance device 10 receives prompts and guidelines for the generation AI from the administrator terminal 50 and assists (supports) the applicant to efficiently generate a dossier and refine the generated dossier.

[0020] This application document preparation assistance device 10 has a processing function and a communication function, and functions as a server in the present system 1. In this embodiment, the application document preparation assistance device 10 is realized by an electronic device such as a personal computer such as a desktop or laptop, or a tablet computer. Therefore, in the following description, the application document preparation assistance device 10 may be referred to as a "server."

[0021] The applicant terminal 30 is a communication terminal used by an applicant, such as a practitioner, who requests the generation of a dossier from a test report using the present system 1, and is a device having a processing function and a communication function. The applicant terminal 30 is connected to the application document preparation support device 10 via a communication network (network N). The applicant terminal 30 is realized by, for example, an electronic device such as a personal computer, such as a desktop or laptop, or a tablet computer.

[0022] The administrator terminal 50 is a communication terminal used by an administrator such as a technical person who manages the entire system 1, including prompt settings and guideline registration, and is a device having a calculation function and a communication function. The administrator terminal 50 is connected to the application document preparation support device 10 via a communication network (network N). The administrator terminal 50 is realized by, for example, an electronic device such as a personal computer such as a desktop or laptop, or a tablet computer.

[0023] Furthermore, the network N is configured by the Internet, but is not particularly limited thereto, and may be a communication network such as a LAN (Local Area Network) or a WAN (Wide Area Network).The communication lines of the network N may be wired or wireless, or a combination of both may be used.

[0024] Although only one applicant terminal 30 is shown in the example of FIG. 1, the number is not particularly limited. Also, although only one application document preparation support device 10 is shown, the application document preparation support device 10 is not limited to a standalone device, but may also be a distributed server system or cloud server that operates cooperatively by communicating via a network N such as the Internet.

[0025] (Hardware configuration) FIG. 2 is a block diagram showing the hardware configuration of the application document preparation assist device 10 according to this embodiment.

[0026] The application document preparation support device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, an input unit 17, a memory unit 18, and a communication unit 19.

[0027] CPU 11 executes various processes according to programs stored in ROM 12 or programs loaded from storage unit 18 to RAM 13. In other words, CPU 11 is a processor that executes various processes according to the programs and controls the overall operation of application document preparation assist device 10. The programs are, for example, an operating system or firmware for operating each unit of application document preparation assist device 10, or application software for implementing the functional blocks described below.

[0028] The RAM 13 also stores data and the like necessary for the CPU 11 to execute various processes. The CPU 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output interface 15 is also connected to this bus 14. The input / output interface 15 is connected to an output unit 16, an input unit 17, a storage unit 18, and a communication unit 19.

[0029] The output unit 16 is composed of a display, a speaker, etc., and outputs various information as images and sounds. The input unit 17 is composed of a keyboard, mouse, microphone, camera, etc., and inputs various information in response to received instruction operations. Note that the output unit 16 and the input unit 17 may be integrated into one unit using, for example, a touch panel.

[0030] The storage unit 18 stores various data necessary for the application document preparation assist device 10 to execute information processing, and is configured, for example, with a hard disk, a DRAM (Dynamic Random Access Memory), or the like. The communication unit 19 communicates with other devices via a network N including the Internet.

[0031] The application document preparation assisting device 10 may be provided with a drive to which removable media such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory can be appropriately attached. This drive allows a program read from the removable media to be installed in the storage unit 18. Furthermore, the removable media can also store various data stored in the storage unit 18 in the same manner as the storage unit 18.

[0032] Furthermore, the hardware configurations of applicant terminal 30 and administrator terminal 50 of this embodiment are the same as those of application document preparation assist device 10 described above.

[0033] (Application document preparation assistance device 10) FIG. 3 is a block diagram illustrating an example of the configuration of the application document preparation assist device 10 that functions as a server in this embodiment.

[0034] The application document preparation support device (server) 10 includes a receiving unit 110, a presenting unit 120, an output unit 130, a confirming unit 140, a generating unit 150, a display unit 160, a proposing unit 170, and an identifying unit 180. The server 10 also includes a guideline DB 210, a prompt DB 220, a template DB 230, a result information DB 240, a test report storage 250, and a dossier storage 260 as a memory unit 18.

[0035] The reception unit 110 is a means having a function of receiving a report of test results (test report) for the pesticide that is the subject of an application. That is, the reception unit 110 receives the test report for the pesticide that is the subject of an application in creating a dossier for the pesticide registration based on the Agricultural Chemicals Control Act. The test report received by the reception unit 110 is temporarily stored in the test report storage 250.

[0036] The receiving unit 110 also has the function of receiving dossiers for pesticides that have been applied for in the past. That is, when generating a dossier for the registration of the target pesticide, the receiving unit 110 receives in advance a dossier for the same pesticide that was created in the past, or a dossier for another pesticide that was most recently submitted to the examination organization. The dossiers received by the receiving unit 110 are stored in the template DB 230.

[0037] The reception unit 110 also has the function of receiving in advance information regarding the results of applications for pesticides that have been submitted in the past (hereinafter referred to as "result information"). In other words, when generating a dossier for the registration of the target pesticide, the reception unit 110 receives result information such as deficiencies in test results and comments pointed out by an examination organization in the past in applications for related pesticides, and feeds this information back to the generation AI. The result information received by the reception unit 110 is stored in the result information DB 240.

[0038] In the server 10 of this embodiment, the reception unit 110 performs the following various functions to streamline advance preparations for creating application documents that take into account registrations at multiple review organizations when creating a dossier for pesticide registration to be submitted to one or more review organizations. That is, the receiving unit 110 also functions as a means having a function of receiving information about the pesticide that is the subject of the application. The receiving unit 110 also functions as a means having a function of receiving information on one or more examination organizations requesting registration of a pesticide.

[0039] In the server 10 of this embodiment, the presentation unit 120 performs the following various functions to streamline advance preparations for creating application documents that take into account registrations at multiple review organizations when creating a dossier for pesticide registration to be submitted to one or more review organizations as described above.

[0040] That is, the presentation unit 120 is a means having a function of presenting necessary information required for generating a dossier of a pesticide by a generation AI based on guidelines for the registration of a pesticide that have been received in advance. The presentation unit 120 also functions as a means having a function of presenting necessary information required for each examination organization, or all necessary information required regardless of each examination organization.

[0041] The presentation unit 120 also functions as a means having a function of further presenting information indicating the degree to which the necessary information is required for each examination organization. The presentation unit 120 also functions as a means having the function of presenting various test results as necessary information.

[0042] In addition to presenting test results, the presenting unit 120 also functions as a means having the function of presenting information about materials that are desirable to add, such as related literature or reference literature. The presentation unit 120 also functions as a means having a function of presenting test results to be added as necessary information according to the content of the received test report. Furthermore, the presentation unit 120 also functions as a means for presenting information on materials that may be desirable to add, such as related literature or reference literature, as necessary information, depending on the content of the received test report.

[0043] The output unit 130 is a means having a function of outputting, together with the generated dossier, information for the applicant to confirm the contents of the dossier. In other words, even if a dossier can be generated automatically, a final confirmation by the applicant is required. Therefore, together with outputting the dossier generated by the generation unit 150, the output unit 130 outputs various information associated with the dossier so that the applicant can easily confirm the contents of the materials, such as test results and papers, used to generate the dossier.

[0044] This allows the user to check the contents of the generated dossier while referring to the displayed content, and to efficiently make corrections and other improvements as necessary.

[0045] The output unit 130 also has a function of outputting information that serves as the basis for generating the application documents. That is, the output unit 130 outputs information on the specific basis of the documents, such as test results and papers, that were used to generate the dossier so that the user can confirm the information. In this case, the output of the supporting information may be, for example, a popup display of images or numerical values ​​that serve as the supporting information for relatively important parts. The output of the supporting information may also be a comment indicating which test results or which page of the document is referenced.

[0046] This eliminates the need for the applicant to go through the tedious process of finding the relevant sections of test scores or documents to confirm the content, and the system 1 allows the applicant to efficiently check the content of the generated dossier, and also allows the applicant to make corrections or other improvements as necessary by referring to the information that forms the basis of the dossier.

[0047] The output unit 130 also functions as a means having a function of outputting the differences between the laws and regulations in a first period when the application documents were generated and the laws and regulations in a second period that is earlier than the first period, and the differences between the dossier generated in the first period and the dossier created in the second period. That is, the output unit 130 outputs the differences between the old and new guidelines identified by the identification unit 180 and the differences between the dossiers created based on the old and new laws and regulations.

[0048] As a result, in this system 1, the applicant can use the changes (differences) in the guidelines and the differences between previously generated dossiers and newly generated dossiers as one of the materials to confirm why the dossier was generated in the way it was by the generation AI (generation unit 150). Therefore, based on the confirmation of these differences, the applicant can efficiently and accurately perform brush-up work such as corrections in preparation for dossier registration.

[0049] In the server 10 of this embodiment, when creating a dossier for pesticide registration to be submitted to one or more reviewing organizations as described above, the output unit 130 performs the following functions to streamline advance preparations for creating application documents that take into account registrations at multiple reviewing organizations. That is, the output unit 130 also functions as a means having the function of outputting result information for the same pesticide as the pesticide that is the subject of the application when the necessary information is presented.

[0050] The confirmation unit 140 is a means having a function of checking the conformance of the generated dossier with the guidelines using the generation AI, determining the possibility of registration (hereinafter referred to as "registrability" or "accuracy") based on the conformance of the content constituting the dossier with the guidelines, and confirming information corresponding to this. That is, the confirmation unit 140 confirms the conformance of the dossier generated by the generation unit 150 with the guidelines previously accepted, and confirms information corresponding to the possibility of registration determined from this conformance. Here, the information corresponding to the accuracy can be output in the form of, for example, "◯" for a dossier determined by the AI ​​to have high conformance with the guidelines and high registerability, "×" for a dossier determined by the AI ​​to have low conformance with the guidelines and low registerability, and "△" for a dossier determined by the AI ​​to have intermediate conformance and relatively low registerability.

[0051] The confirmation unit 140 also has the function of confirming the consistency between the dossier and the test report after the dossier is generated. That is, after the generation unit 150 generates a dossier, the confirmation unit 140 checks whether the contents of the generated dossier are truly correct and whether the generated dossier is consistent with the contents of the test report. The confirmation unit 140 automatically checks (confirms) whether the dossier contains any inconsistencies with the test results.

[0052] This allows the applicant to check the content of the test results and consider whether or not correction is necessary by displaying the discrepancies without correcting them if any.

[0053] The confirmation unit 140 also has the function of confirming the contents of the test report used to generate the dossier based on the guidelines after the dossier is generated. That is, after the generation unit 150 generates the dossier, the confirmation unit 140 automatically checks (confirms) whether the dossier was generated using a test report that does not comply with the guidelines.

[0054] This allows the contents of the test report used to generate the dossier to be confirmed if the contents of the test report meet the guidelines.

[0055] In the server 10 of this embodiment, the confirmation unit 140 performs the following functions to streamline advance preparations for creating application documents that take into account registrations at multiple review organizations when creating a dossier for pesticide registration to be submitted to one or more review organizations as described above. That is, the confirmation unit 140 also serves as a means having a function of confirming the contents of the test report used to generate the dossier based on the guidelines before the dossier is generated.

[0056] The generation unit 150 is a means having the function of generating a dossier for a pesticide using a generation AI based on previously accepted guidelines (an example of regulations), a dossier template (an example of format information), and a test report for the pesticide being applied for. That is, when the acceptance unit 110 accepts a test report, the generation unit 150 analyzes the contents of the test report using the generation AI to recognize the type, formulation, and use of the pesticide. The generation unit 150 checks consistency based on predetermined guidelines accepted in advance and generates a dossier in accordance with a specified format.

[0057] Before analyzing the contents of the test report, the generation unit 150 converts the test report file stored in the test report storage 250 into Markdown format. The file can be converted into Markdown format using a processing module such as the Python library developed by Microsoft. In this way, the generation unit 150 converts test report files in PDF format, Word format, Excel format, etc. into Markdown format. The generation unit 150 uses prompt processing to check whether the contents of the test report comply with the guidelines (consistency check), and then generates a dossier. The dossier generated by the generation unit 150 is then converted into, for example, a Word format and stored in the dossier storage 260, and can be downloaded to the applicant terminal 30.

[0058] This allows the system 1 to efficiently use generation AI to perform time-consuming tasks such as checking the numerical values ​​included in test scores and determining whether they comply with guidelines. Furthermore, the system 1 can eliminate human errors such as typos, omissions, and typing errors to create highly accurate dossiers.

[0059] The generation unit 150 also has a function of generating a new dossier using a dossier of a pesticide that has been applied for in the past. That is, when generating a dossier for the registration of the target pesticide, the reception unit 110 receives in advance a dossier for the same pesticide that was previously created, or a dossier for another pesticide that was most recently submitted to the examination organization. Then, the generation unit 150 generates a dossier that conforms to a specified format (i.e., form) by referring to the format of one of the dossiers.

[0060] This allows the system 1 to efficiently create new dossiers using a generation AI according to a predetermined format by using the format of a previous dossier for the same pesticide or the dossier for another pesticide most recently submitted to an inspection agency as a template.

[0061] The generation unit 150 also has a function of generating a new dossier using result information of pesticides that have been applied for in the past. That is, when generating a dossier for the registration of a target pesticide, the generation unit 150 generates the dossier by referring to result information of pesticides that have been applied for in the past, which the reception unit 110 receives in advance.

[0062] This allows new dossiers to be created efficiently by paying attention to deficiencies and comments in test results that have been pointed out by reviewing bodies in the past, so that similar deficiencies are not pointed out. In addition, it is advisable that the result information for pesticides previously applied for should not be limited to a single review organization, but should also include result information such as deficiencies in test results and comments pointed out by review organizations in other countries or regions in response to applications for the same pesticide. This allows the possibility of registration to be efficiently increased by preparing a dossier that meets the registration requirements based on the results of the examination by the examination body that is considered to be the strictest.

[0063] The display unit 160 is a means having a function of displaying, together with the generated dossier, information according to the possibility (so-called accuracy) of the dossier's registrability. That is, the display unit 160 displays, together with the dossier generated by the generation unit 150, information such as "◯", "×", or "△" according to the accuracy of the registrability determined from the conformity of the dossier confirmed by the confirmation unit 140 with the guidelines.

[0064] At this time, the display unit 160 may output, for example, a comment according to the accuracy of the dossier's registrability in Word format. The display unit 160 may also output, in Excel format (table format), a comment according to the accuracy of the dossier's registrability together with the dossier generated by the generation unit 150. Furthermore, the display unit 160 may also output information and comments according to the accuracy of the dossier generated by the generation unit 150 in chat format using, for example, RAG Chat, a web service from Amazon.

[0065] Furthermore, the information corresponding to the degree of certainty regarding registrability may be, for example, information calculated by the confirmation unit 140 on the degree of fulfillment of the requirements in a predetermined guideline that has been accepted in advance by the generation AI. The information corresponding to the degree of certainty regarding registrability may be information that the acceptance unit 110 accepts in advance result information on pesticides that have been applied for in the past, and the generation AI calculates the presence or absence of registration and the rate of registration based on the result information.

[0066] This allows the content of the dossier generated by the generation AI to be evaluated based on the accuracy of registrability, and the priority of the dossier confirmation and whether or not to make any corrections can be considered based on the accuracy. Furthermore, based on the information corresponding to the accuracy of registrability, it may be possible to encourage brush-ups such as adding test results or adding materials such as related literature (e.g., papers) or reference literature.

[0067] The suggestion unit 170 is a means having a function of proposing, based on information regarding the accuracy of the dossier according to its registrability, that the content of the dossier be reviewed in advance by an examination organization that reviews the registration of pesticides. That is, the suggestion unit 170 makes a suggestion based on a check of the conformity of the dossier generated by the generation unit 150 with the guidelines. For example, for a dossier determined by the confirmation unit 140 to have a relatively low conformity ("△"), the suggestion unit 170 proposes that the content of the dossier be reviewed in advance (before application) by an examination organization that reviews the registration of the pesticide.

[0068] This allows you to take measures such as checking the contents of the dossier with the reviewing agency in advance, making it possible to create and submit a dossier that is highly likely to be registered.

[0069] In addition, the suggestion unit 170 is also a means having a function of proposing corrections to the content of the test report to ensure that the guideline is met when the content of the test report does not comply with the guideline. In other words, when the content of the test report confirmed by the confirmation unit 140 does not comply with the guideline, the suggestion unit 170 proposes corrections to the test report to increase the possibility of meeting the guideline.

[0070] Specifically, the proposing unit 170 considers adding data to align test scores and adding materials such as papers, and also proposes corrections to appropriately follow up the description in the discussion section of the test report so that the generated dossier can be submitted as is. At this time, test scores and materials such as papers may be added along with the correction of the discussion section.

[0071] This prevents the generation AI from modifying the contents of the dossier without the approval of the person in charge of the application. Furthermore, this system 1 allows the applicant to check if, for example, the discussion section of the test report is deemed to be non-compliant with the guidelines. This system 1 allows the person in charge to take desirable measures, such as adding test results or writing a note in the discussion section to follow up on the non-compliant content. Specifically, if there are inconsistencies in the test report, the reason for the results can be explained in the discussion section so that they are consistent.

[0072] The identification unit 180 is a means having the function of identifying the differences between the guidelines at the first time when the dossier was generated and the guidelines at the second time that is earlier than the first time for the pesticide that is the subject of the application, and also identifying the differences between the dossier generated at the first time and the dossier generated at the second time.

[0073] The guideline DB 210 is a means for storing guideline information. That is, the guideline DB 210 is a database that stores laws and regulations related to the registration of pesticides, and stores not only currently applicable guidelines but also guidelines that have been applied in the past. Furthermore, the guideline DB 210 is not limited to the guidelines of a single examination organization, but also stores guidelines of examination organizations in other countries and regions. These guidelines are registered in advance by the administrator terminal 50.

[0074] The prompt DB 220 is a means for storing prompts for creating dossiers for each classification of test reports. That is, the prompt DB 220 is a database that stores prompts that indicate the instructions to be executed by the generation AI for each pesticide when creating a dossier. These prompts are registered in advance by the administrator terminal 50.

[0075] The template DB 230 is a means for storing dossiers that have been submitted in the past to regulatory authorities, i.e., examination bodies. In other words, the template DB 230 is a database that stores past dossiers for the same pesticide and dossiers for other pesticides, which are used as templates when generating a dossier. These past dossiers may be received from the applicant terminal 30, or may be registered in advance by the administrator terminal 50.

[0076] In this embodiment, a template is data that serves as a model for creating a dossier. As a model, a template contains information related to the format of an application document, such as the items to be described, the order of the items, and the layout of the items. Note that the format information for generating an application document does not have to be in the form of a template, as long as it is information that specifies the format of the application document, such as the items to be described, the order of the items, and the layout of the items.

[0077] The result information DB 240 is a means for storing past result information published by the reviewing organization, which is the regulatory authority. In other words, the result information DB 240 is a database that stores deficiencies and comments pointed out by the reviewing organization in past reviews of pesticides. This result information may also be received from the applicant terminal 30, or may be registered in advance by the administrator terminal 50.

[0078] The test report storage 250 is a means for storing test reports uploaded by applicants. In other words, the test report storage 250 is a storage area for storing test reports created by applicants for generating dossiers. These test reports are accepted from the applicant terminal 30.

[0079] The dossier storage 260 is a means for storing the generated dossier. In other words, the dossier storage 260 is a storage area for storing the dossier generated by the generation unit 150 so that it can be downloaded by the applicant terminal 30 (applicant).

[0080] As described above, in application document creation assistance device 10 according to this embodiment, various programs (such as an OS and applications) stored in the auxiliary storage device are loaded into the main storage device and executed by CPU 11. Application document creation assistance device 10 then functions as a device including a reception unit 110, a presentation unit 120, an output unit 130, a confirmation unit 140, a generation unit 150, a display unit 160, a proposal unit 170, and an identification unit 180.

[0081] Next, the basic processing flow in the application document preparation support system 1 according to this embodiment will be described. FIG. 4 is a sequence diagram showing an example of the application document preparation support process according to this embodiment.

[0082] First, in step S301, the administrator terminal 50 sets the classification of the test and registers the guidelines and prompts in the server 10. That is, the server 10 registers fields such as efficacy, phytotoxicity, toxicity, residue, environmental dynamics, and environmental toxicity for each guideline and prompt.

[0083] Specifically, the server 10 sets and registers, for example, the tests described in "Documents to be submitted in pesticide registration applications (Notice No. 30, Shoan No. 6278, Director-General of the Consumer Affairs and Food Safety Bureau, Ministry of Agriculture, Forestry and Fisheries, dated March 29, 2019) (last revised April 1, 2024)" published in the "Public Notices, Notifications, etc. Regarding Pesticide Registration Applications" section of the Ministry of Agriculture, Forestry and Fisheries' website (Home > Consumer Affairs and Food Safety > Pesticide Corner > Pesticide Registration) (https: / / www.maff.go.jp / j / nouyaku / n_touroku / ) as classifications. Additionally, at the same time as registering the guidelines and prompts, server 10 may also register previously submitted dossiers as templates.

[0084] In step S302, the server 10 stores the guidelines received from the administrator terminal 50 in the guideline DB 210, and stores the prompt in the prompt DB 220. Furthermore, if a past dossier has been received, it is saved in the template DB 230.

[0085] In step S303, the applicant terminal 30 uploads the test report to the application document preparation assistance device 10, selects the classification of the test report and the guidelines to be referenced, and instructs the execution of dossier generation. In step S304, the server 10 stores the test report uploaded from the applicant terminal 30 in the test report storage 250. Subsequently, in step S305, the server 10 converts the test report into a Markdown format in response to an instruction to generate a dossier from the applicant terminal 30.

[0086] In step S306, the server 10 applies to the AI ​​processing engine (generation AI) a prompt corresponding to the classification of the test report selected by the applicant terminal 30. Then, the server 10 uses the generation AI to analyze the contents of the test report and check its consistency with the guidelines. Furthermore, in step S307, the server 10 generates a dossier based on the checked test report. At this time, the dossier may be generated by applying a past dossier as a template.

[0087] Then, in step S308, the server 10 formats the generated dossier into, for example, Word and stores it in the dossier storage 260. Thereafter, in step S309, the applicant terminal 30 downloads the dossier stored in the dossier storage 260 from the server 10.

[0088] As described above, this system 1 automatically generates dossiers from test reports, utilizing generation AI to analyze the contents of the test reports and efficiently create dossiers that conform to a predetermined format.

[0089] Next, the flow of the application document generation process in the application document preparation support system 1 according to this embodiment will be described. FIG. 5 is a flowchart showing an example of the basic operation of the application document generation process in the application document generation assist device 10 according to this embodiment.

[0090] As shown in FIG. 5, in step S401, the accepting unit 110 performs processing to determine whether test report information has been accepted (received). If the receiving unit 110 has received the test report information (YES in S401), the process proceeds to step S402. On the other hand, if the receiving unit 110 has not received the test report information (NO in S401), the process in step S401 is repeated.

[0091] Next, in step S402, the generating unit 150 performs a process of analyzing the content of the received test report information. Furthermore, in step S403, the generation unit 150 performs processing to generate a dossier using a generation AI based on (and checking consistency with) guidelines accepted in advance. Then, in step S404, the generation unit 150 performs processing to store the generated dossier in the dossier storage 260. Thereafter, the operation of the application document preparation assisting device 10 ends (END).

[0092] Next, another flow of the application document generation process in the present system 1 will be described. FIG. 6 is a flowchart showing another operation of the application document generation process according to this embodiment.

[0093] As shown in FIG. 6, the processes in steps S501 and S502 are the same as those in steps S401 and S402 described above, and therefore a description thereof will be omitted. In step S503, the generation unit 150 uses past dossiers to generate a new dossier using a generation AI based on guidelines accepted in advance. Then, in step S504, the generation unit 150 performs processing to store the generated new dossier in the dossier storage 260, similar to step S404 described above. Thereafter, the operation of the application document preparation assisting device 10 ends (END).

[0094] Next, another flow of the application document generation process in this system will be described. FIG. 7 is a flowchart showing another operation of the application document generation process according to this embodiment.

[0095] As shown in FIG. 7, the processes in steps S601 and S602 are the same as those in steps S401 and S402 described above, and therefore a description thereof will be omitted. In step S603, the generation unit 150 uses the results of past applications for agricultural chemicals and performs processing to generate a new dossier using a generation AI based on guidelines that have been accepted in advance. Then, in step S604, the generation unit 150 performs processing to store the generated new dossier in the dossier storage 260, similar to step S404 described above. Thereafter, the operation of the application document preparation assisting device 10 ends (END).

[0096] Next, the flow of application document confirmation processing in this system 1 will be described. FIG. 8 is a flowchart showing the operation of the application document confirmation process according to this embodiment.

[0097] As shown in FIG. 8, the processes in steps S701 to S703 are the same as those in steps S401 to S403 described above, and therefore a description thereof will be omitted. In step S704, the output unit 130 performs a process of outputting information for confirming the content of the generated dossier. At this time, the information for confirming the content of the dossier may be, for example, information such as test results or materials (papers) that serve as the basis for generating the dossier. Thereafter, the operation of the application document preparation assisting device 10 ends (END).

[0098] FIG. 9 shows an example of display of evidence information in this embodiment.

[0099] As shown in FIG. 9, the screen viewed by the person in charge of application displays the generated dossier 500 and a basis display section 550 showing the basis for generating the dossier. In the dossier 500 of this embodiment, a main text 510 generated based on test results and the like is displayed. The basis display sections 550 of this embodiment are provided corresponding to the items of the dossier 500. In the example of Fig. 9, the basis display sections 550 include a first basis display section 560 displayed corresponding to the item "Test Guideline" and a second basis display section 570 displayed corresponding to the item "Summary."

[0100] A guideline display button 561 for displaying the main text of the test guideline is displayed in the first basis display section 560. By selecting (e.g., clicking) the guideline display button 561, the guidelines that are the basis for the test guideline described in the main text 510 can be viewed. Furthermore, a reference information display button 562 for displaying reference information is displayed in the first basis display section 560. By selecting the reference information display button 562, reference information such as papers that serve as references for understanding the test guidelines described in the main text 510 can be viewed.

[0101] A data display button 571 for displaying the test data of the test summarized as a summary is displayed in the second basis display section 570. By selecting the data display button 571, a captured image of the test data that is the basis for the summary written in the main text 510 can be viewed. In addition, a score display button 572 for displaying the full text of the test results summarized as a summary is displayed in the second basis display section 570. By selecting the score display button 572, the main text of the test results that is the basis for the summary written in the main text 510 can be viewed.

[0102] Next, another flow of the application document confirmation process in this system 1 will be described. FIG. 10 is a flowchart showing another operation of the application document confirmation process according to this embodiment.

[0103] As shown in FIG. 10, the processes in steps S801 to S803 are the same as those in steps S401 to S403 described above, and therefore a description thereof will be omitted. In step S804, the confirmation unit 140 performs a process of confirming the possibility (so-called accuracy) of the dossier's registrability based on the conformity of the generated dossier with the guidelines. Then, in step S805, the display unit 160 performs a process of displaying information according to the accuracy of the dossier's registrability together with the generated dossier. At this time, for a dossier for which accuracy information indicating a relatively low suitability is displayed, the suggestion unit 170 may display a message suggesting that the dossier be checked by an examination organization that examines the registration of pesticides. Thereafter, the operation of the application document preparation assisting device 10 ends (END).

[0104] FIG. 11 is an example of a registerability list 600 relating to the registerability of this embodiment.

[0105] 11, the conformity of the generated dossier with the guidelines is displayed in a registration list 600. The registration list 600 includes a test field 610 indicating the type of test in the dossier, an item 620 indicating the item in the dossier, and a possibility display 630 indicating the possibility of registration.

[0106] The exam field 610 specifically displays the name of the exam field, for example. The item 620 specifically displays the name of the item in the dossier. The possibility display 630 then displays the possibility of registration for each exam field and item using a three-level evaluation of "Good", "Good", and "Poor". In this embodiment, the evaluations are "Good", "Good", and "Poor", in order of high to low likelihood of registration. By viewing the registration possibility list 600, the person in charge of application can use it as a reference when determining the priority of checks, for example, by first checking items in test fields that are unlikely to be registered, such as items marked with a "△" or "X."

[0107] FIG. 12 shows an example of a confirmation recommendation display 700 according to this embodiment.

[0108] As shown in FIG. 12, the screen viewed by the applicant making the application displays a confirmation recommendation display 700, which includes a dossier main text 710, which is the main text that constitutes the dossier, and a confirmation display 720 that prompts the applicant to confirm the contents of the dossier. The confirmation display 720 is a display that suggests, for example, that an item in the generated dossier have a relatively low conformity with the guidelines, to confirm in advance with the examination body that will be conducting the examination for the pesticide registration. In the example shown in Fig. 12, the confirmation display 720 displays a so-called pop-up message as a message to encourage the user to consult with the person in charge at the examination body to which the application for pesticide registration is to be submitted. In addition, the confirmation display 720 of this embodiment is displayed superimposed on the item in the testing field that is the subject of the criticism.

[0109] By displaying the confirmation display 720, the person in charge of the application can decide whether or not to have a prior consultation to resolve any deficiencies or other issues pointed out before officially submitting the application documents to the review organization.

[0110] Next, another flow of the application document confirmation process in the present system 1 will be described. FIG. 13 is a flowchart showing another operation of the application document confirmation process according to this embodiment.

[0111] As shown in FIG. 13, the processes in steps S901 to S903 are the same as those in steps S401 to S403 described above, and therefore a description thereof will be omitted. In step S904, the checking unit 140 performs a process to check the consistency between the generated dossier and the test report. Next, in step S905, the confirmation unit 140 performs a process of determining whether or not the generated dossier contains any inconsistencies with the contents of the test report. If the confirmation unit 140 confirms any inconsistencies (if there are inconsistencies) (YES in S905), the process proceeds to step S906. On the other hand, if the confirmation unit 140 does not confirm any inconsistencies (if there are no inconsistencies) (NO in S905), the operation of the application document preparation support device 10 ends (END).

[0112] Then, in step S906, the display unit 160 performs a process to display the inconsistencies between the generated dossier and the test report. At this time, the inconsistencies can be displayed in Word format with comments corresponding to the content of the inconsistency. Also, the inconsistencies can be displayed by comparing the inconsistencies in Excel format (table format). Furthermore, the inconsistencies can be displayed by displaying the content of the test report in a pop-up format at the inconsistent part of the dossier. Also, it is preferable to display the inconsistencies in a different color from others, highlight them with a flashing light, or shade them. Thereafter, the operation of the application document preparation assisting device 10 ends (END).

[0113] Next, another flow of the application document confirmation process in the present system 1 will be described. FIG. 14 is a flowchart showing another operation of the application document confirmation process according to this embodiment.

[0114] As shown in FIG. 14, the processes in steps S1001 to S1003 are the same as those in steps S401 to S403 described above, and therefore a description thereof will be omitted. In step S1004, the identifying unit 180 performs a process of identifying the differences between the old and new laws and regulations. That is, the identifying unit 180 performs a process of identifying the differences between the guidelines at the first time when the dossier was generated and the guidelines at the second time that is earlier than the first time, for the pesticide that is the subject of the application. In step S1005, the identifying unit 180 performs a process of identifying differences between the dossier generated based on the old regulations and the dossier generated based on the new regulations. That is, the identifying unit 180 performs a process of identifying differences between the dossier generated in the first period and the dossier generated in the second period for the pesticide that is the subject of the application.

[0115] Then, in step S1006, the output unit 130 performs a process of outputting the differences between the new and old laws and regulations and the differences between the dossiers generated based on the new and old laws. That is, the output unit 130 performs a process of outputting the differences between the guidelines and the dossiers identified by the identification unit 180. Thereafter, the operation of the application document preparation assisting device 10 ends (END).

[0116] FIG. 15 is an example of a comparison column display 800 according to this embodiment.

[0117] As shown in FIG. 15, a comparison column display 800 of this embodiment includes the following items: guidelines 810, guideline contents 830, and application documents 850. For example, the specific name of an old guideline is displayed in the upper section of the guideline 810. For example, the specific name of a new guideline is displayed in the lower section of the guideline 810. In this way, the guideline 810 compares the specific names of the guidelines from the first period and the second period.

[0118] For example, the specific content of an old guideline is displayed in the upper section of guideline content 830. For example, the specific content of a new guideline is displayed in the lower section of guideline content 830. In this way, guideline content 830 compares the specific content of the guidelines from the first period and the second period.

[0119] The contents of a dossier created based on, for example, old guidelines are displayed in the upper section of application document 850. The contents of a dossier created based on, for example, new guidelines are displayed in the lower section of application document 850. In this way, application document 850 compares the contents of application documents from the first and second periods.

[0120] In the comparison column display 800, for example, a comparison of guidelines from different periods (an example of regulatory comparison information) and a comparison of different dossiers created in accordance with guidelines corresponding to different periods (an example of application comparison information) are displayed in the upper and lower sections, respectively. For example, if the content of a dossier differs from the past, the person in charge of the application can refer to the changes in the guidelines that serve as the basis for this.

[0121] Next, another flow of the application document confirmation process in the present system 1 will be described. FIG. 16 is a flowchart showing another operation of the application document confirmation process according to this embodiment.

[0122] As shown in FIG. 16, the processes in steps S1101 to S1103 are the same as those in steps S401 to S403 described above, and therefore a description thereof will be omitted. In step S1104, the confirmation unit 140 performs a process of confirming the content of the test report based on the guidelines. That is, after the dossier is generated, a process of confirming the content of the test report based on the guidelines is performed. In step S1105, the checking unit 140 performs a process of checking whether the contents of the test report comply with the guidelines. If the confirmation unit 140 determines that the document does not comply with the guidelines (YES in S1105), the process proceeds to step S1106. On the other hand, if the confirmation unit 140 determines that the document does comply with the guidelines (NO in S1105), the operation of the application document preparation support device 10 ends (END).

[0123] Then, in step S1106, the suggestion unit 170 performs a process of proposing to modify the contents of the test report so as to ensure the guidelines. That is, the suggestion unit 170 performs a process of proposing to compile test results (add data) so as to satisfy the guidelines, and proposing to consider adding materials such as papers. The suggestion unit 170 also performs a process of proposing appropriate modifications to the description of the discussion section of the test report so that the generated dossier can be used. Thereafter, the operation of the application document preparation assisting device 10 ends (END).

[0124] In this way, the present system 1 utilizes generation AI to analyze the contents of test reports related to pesticide registration and efficiently generate dossiers in accordance with a predetermined format. Furthermore, the present system 1 is desirable in that it assists in polishing the generated dossier so as to increase the registrability of the pesticide.

[0125] In addition, this system 1 is not limited to generating application documents for the registration of pesticides, but can also be applied to generating application documents for approval and authorization of the manufacture and sale of chemical products, including pharmaceuticals, chemical substances, cosmetics, etc.

[0126] <Additional Notes> (Appendix 1) A system that assists in the preparation of application documents for pesticide registration, having one or more processors, The processor: We will accept test results for the pesticides that are the subject of the application. generating the application documents for the pesticide using a generation AI based on the laws and regulations regarding the registration of the pesticide and format information that defines the format of the application documents; outputting the generated application documents to the applicant; Auxiliary systems. (Appendix 2) 2. An auxiliary system as described in Appendix 1, which accepts application documents for pesticides previously applied for and generates new application documents using the application documents. (Appendix 3) An auxiliary system as described in Appendix 1, which accepts result information regarding the results of pesticide applications previously submitted and generates new application documents using the result information. (Appendix 4) An auxiliary system as described in Appendix 1, which outputs information for the applicant to confirm the contents of the application documents along with the generated application documents. (Appendix 5) An auxiliary system as described in Appendix 4, which outputs information that serves as the basis for generating the application documents. (Appendix 6) 5. The auxiliary system of claim 4, which displays information regarding the possibility of registering the application documents together with the generated application documents. (Appendix 7) An assistance system as described in Appendix 6, which, based on information regarding the possibility of registration of the application documents, suggests that the contents of the application documents be checked in advance by an examination body that will conduct an examination regarding the registration. (Appendix 8) An auxiliary system as described in Appendix 4, which outputs, for the pesticide that is the subject of the application, regulatory comparison information regarding a comparison between the regulations at a first time point when the application documents were generated and the regulations at a second time point that is earlier than the first time point, and application comparison information regarding a comparison between the application documents generated at the first time point and the application documents generated at the second time point. (Appendix 9) An auxiliary system as described in Appendix 1, which verifies the consistency between the application documents and the test result report after the application documents are generated. (Appendix 10) An auxiliary system as described in Appendix 1, which, after the application documents are generated, verifies the contents of the test result report used to generate the application documents based on the regulations. (Appendix 11) The assistance system of Appendix 10, which, if the contents of the confirmed report do not satisfy the requirements of the law, proposes amendments that will increase the likelihood of satisfying the requirements of the law. (Appendix 12) A device that assists in the preparation of application documents for pesticide registration, having one or more processors, The processor: We will accept test results for the pesticides that are the subject of the application. generating application documents for the pesticide using a generation AI based on the laws and regulations regarding the registration of the pesticide and format information that defines the format of the application documents; Auxiliary equipment. (Appendix 13) A method for assisting in the preparation of application documents for pesticide registration, comprising: receiving test results for the pesticide that is the subject of the application; generating application documents for the pesticide using a generation AI based on the laws and regulations related to the registration of the pesticide and format information defining the format of the application documents; An auxiliary method comprising: (Appendix 14) A computer assists in the preparation of application documents for pesticide registration. A function to accept test results for pesticides that are the subject of applications, A function of generating application documents for the pesticide using a generation AI based on the laws and regulations regarding the registration of the pesticide and format information that defines the format of the application documents; A program that executes the following.

[0127] Although the present embodiment has been described above, the above-described embodiment is merely an example for facilitating understanding of the present invention and is not intended to limit the present invention. Furthermore, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the scope of achieving the object of the present invention are included in the present invention. [Explanation of symbols]

[0128] 10...Application document creation support device (server), 30...Applicant terminal, 50...Administrator terminal, 110...Reception unit, 120...Presentation unit, 130...Output unit, 140...Confirmation unit, 150...Generation unit, 160...Display unit, 170...Proposal unit, 180...Identification unit, 210...Guideline DB, 220...Prompt DB, 230...Template DB, 240...Result information DB, 250...Test report storage, 260...Dossier storage

Claims

1. A system that assists in the preparation of application documents for pesticide registration, having one or more processors, The processor: A storage means for storing format information defining the laws and regulations related to the registration of the pesticide and the format of the application documents can be referenced; generating the application documents by inputting predetermined prompts to the generation AI; the prompt includes instructions to analyze the content of a test report describing test results for the pesticide that is the subject of the application, and to generate the application documents by referring to the laws and regulations and the format information; outputting the generated application documents to the applicant; Displaying test data of the test results that are the basis for generating the application documents together with the generated application documents. Auxiliary systems.

2. An auxiliary system as described in claim 1, which is capable of displaying the possibility of registration for each item in the application documents according to compliance with the laws and regulations, and displaying the test data for each item in the application documents.

3. The assistance system according to claim 1 , which accepts application documents for pesticides previously applied for and generates new application documents using the application documents.

4. The assistance system according to claim 1 , which receives result information regarding the results of applications for pesticides that have been submitted in the past, and generates new application documents using the result information.

5. The assistance system according to claim 1 , wherein information regarding the possibility of registering the application documents is displayed together with the generated application documents.

6. The assistance system according to claim 5, which suggests that the contents of the application documents be checked in advance with an examination organization that will conduct an examination regarding the registration, based on information regarding the possibility of registration of the application documents.

7. The auxiliary system described in claim 1 outputs, for the pesticide that is the subject of the application, regulatory comparison information regarding a comparison between the regulations at a first time when the application documents were generated and the regulations at a second time that is earlier than the first time, and application comparison information regarding a comparison between the application documents generated at the first time and the application documents generated at the second time.

8. The assistance system according to claim 1 , further comprising: after generating the application documents, verifying consistency between the application documents and the test result report.

9. The assistance system according to claim 1 , further comprising: after the application documents are generated, confirming the contents of the test result report used in generating the application documents in accordance with the regulations.

10. The assistance system according to claim 9 , wherein, when the confirmed contents of the report do not satisfy the requirements of the regulations, the assistance system proposes corrections that increase the likelihood of satisfying the requirements of the regulations.

11. A device that assists in the preparation of application documents for pesticide registration, having one or more processors, The processor: A storage means for storing format information defining the laws and regulations related to the registration of the pesticide and the format of the application documents can be referenced; generating the application documents by inputting predetermined prompts to the generation AI; the prompt includes instructions to analyze the content of a test report describing test results for the pesticide that is the subject of the application, and to generate the application documents by referring to the laws and regulations and the format information; Displaying test data of the test results, which are the basis for generating the application documents, on a screen together with the generated application documents. Auxiliary equipment.

12. A computer assists in the preparation of application documents for pesticide registration. a function of referring to a storage means for storing format information that defines the laws and regulations related to the registration of the agricultural chemicals and the format of the application documents; A function of generating the application documents by inputting a predetermined prompt to the generation AI; the prompt includes instructions to analyze the content of a test report describing test results for the pesticide that is the subject of the application, and to generate the application documents by referring to the laws and regulations and the format information; a function of displaying test data of the test results, which are the basis for generating the application documents, on a screen together with the generated application documents; A program that executes the following.

Images