Data processing device, data processing method, and data processing program

Abstract

To provide a data processing device, method, and program for generating a protocol or a report of a pharmaceutical development test using a generative AI model.SOLUTION: A data processing device includes: an input section that receives an input of necessary information, which is information necessary for generating a protocol or a report of a pharmaceutical development test, from a user; and a generation section that inputs instruction information including the necessary information and instructing on generation of a specific portion of the protocol or the report to a user-dedicated generative AI model, inputs instruction information instructing on verification of data of the specific portion to a general-purpose generative AI model trained using public data, inputs instruction information instructing on correction of the data of the specific portion including a verification result of the acquired data of the specific portion to the user-dedicated generative AI model, and generates the protocol or the report of the pharmaceutical development test using the acquired data of the specific portion after the correction.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing program.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, there is room for improvement in creating a plan or report for a pharmaceutical development test using a generative AI model.

Means for Solving the Problems

[0005] A first aspect of the technology of this disclosure is a data processing device comprising: an input unit that receives input from a user of necessary information which is information necessary for creating a drug development trial implementation plan or report; a specific part acquisition unit that inputs instruction information, including the necessary information and instructing the creation of a specific part of the implementation plan or report, into a user-specific generating AI model that has been learned using confidential data provided by the user, and acquires data of the specific part from the output of the user-specific generating AI model; a verification result acquisition unit that inputs instruction information, including the acquired data of the specific part and instructing verification of the data of the specific part, into a general-purpose generating AI model that has been learned using public data, and acquires verification results of the data of the specific part from the output of the general-purpose generating AI model; a modification result acquisition unit that inputs instruction information, including the acquired verification results of the data of the specific part and instructing modification of the data of the specific part, into the user-specific generating AI model, and acquires modified data of the specific part from the output of the user-specific generating AI model; and a creation unit that creates a drug development trial implementation plan or report using the acquired modified data of the specific part.

[0006] A second aspect of the technology of this disclosure is a data processing method in which a computer receives input from a user of necessary information which is information necessary for creating a drug development trial implementation plan or report, inputs instruction information including the necessary information and instructing the creation of a specific part of the implementation plan or report into a user-specific generative AI model that has been learned using confidential data provided by the user, obtains data for the specific part from the output of the user-specific generative AI model, inputs instruction information including the obtained data for the specific part and instructing verification of the data for the specific part into a general-purpose generative AI model that has been learned using publicly available data, obtains verification results for the data for the specific part from the output of the general-purpose generative AI model, inputs instruction information including the obtained verification results for the data for the specific part and instructing modification of the data for the specific part into the user-specific generative AI model, obtains modified data for the specific part from the output of the user-specific generative AI model, and executes a process to create the drug development trial implementation plan or report using the obtained modified data for the specific part.

[0007] A third aspect of the technology of this disclosure is a data processing program that causes a computer to receive input from a user of necessary information which is information necessary for creating a drug development trial implementation plan or report, input instruction information including the necessary information and instructing the creation of a specific part of the implementation plan or report into a user-specific generative AI model that has been trained using confidential data provided by the user, obtain data for the specific part from the output of the user-specific generative AI model, input instruction information including the obtained data for the specific part and instructing verification of the data for the specific part into a general-purpose generative AI model that has been trained using publicly available data, obtain verification results for the data for the specific part from the output of the general-purpose generative AI model, input instruction information including the obtained verification results for the data for the specific part and instructing correction of the data for the specific part into the user-specific generative AI model, obtain the corrected data for the specific part from the output of the user-specific generative AI model, and execute a process to create the drug development trial implementation plan or report using the obtained corrected data for the specific part. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a user terminal. [Figure 3] This outlines the specific processing steps. [Figure 4] The functional configuration of a specific processing unit of a data processing device is shown in general terms. [Figure 5] This diagram outlines an example of the operation flow of a specific process performed by a data processing device. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the data processing device, data processing method, and data processing program relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0016] Figure 1 shows an example of the configuration of the data processing system 10 according to the embodiment.

[0017] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a user terminal 14. An example of the data processing device 12 is a server. An example of the user terminal 14 is a personal computer or a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" related to the technology of this disclosure.

[0018] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The user terminal 14 includes a computer 36, a reception device 38, an output device 40, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38 and the output device 40 are connected to the bus 52.

[0020] The reception device 38 includes a keyboard, a mouse, etc., and receives user input. Also, the reception device 38 may receive user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator with a touch panel, or may receive user input by voice by detecting the voice of the user with a microphone. The control unit 46A transmits data indicating the received user input to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, etc., and presents data to the person 20 by outputting the data in a perceptible expression form (e.g., voice and / or text) for the person 20. The display 40A displays visible information such as text and images according to an instruction from the processor 46. The speaker 40B outputs voice according to an instruction from the processor 46.

[0022] The communication I / F 44 is connected to a network 54. The communication I / F 44 and 26 manage the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the user terminal 14.

[0024] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "data processing program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores dedicated generation AI models 58A and 58B, and general-purpose generation AI model 58C. Dedicated generation AI models 58A and 58B, and general-purpose generation AI model 58C are used by the specific processing unit 290.

[0026] The dedicated generative AI models 58A and 58B, and the general-purpose generative AI model 58C are examples of so-called generative AI (Artificial Intelligence). An example of the dedicated generative AI models 58A and 58B, and the general-purpose generative AI model 58C is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include those described above. The dedicated generative AI models 58A and 58B, and the general-purpose generative AI model 58C are obtained by performing deep learning on a neural network. The dedicated generative AI models 58A and 58B, and the general-purpose generative AI model 58C are input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The dedicated generative AI models 58A and 58B, and the general-purpose generative AI model 58C perform inference on the input inference data according to the instructions shown by the prompts, and output the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0027] The dedicated generation AI models 58A and 58B were further trained using confidential data provided by users.

[0028] For example, the dedicated generation AI model 58A was further trained using a dataset provided by the user as confidential data, which included the trial plan portion of the clinical trial protocol for a drug. The dedicated generation AI model 58B was further trained using a dataset provided by the user, which included the analysis plan portion of the clinical trial protocol for a drug. Here, fine-tuning of ChatGPT can be used for the additional training.

[0029] The general-purpose generative AI model 58C has been further trained using publicly available data. For example, the general-purpose generative AI model 58C has been further trained using a dataset that includes information on guidelines and regulations related to healthcare in various countries, information on past clinical trials, and information on medical-related research papers.

[0030] The dedicated generation AI models 58A and 58B are for use only by the respective users, while the general-purpose generation AI model 58C is available for use by all users.

[0031] At the user terminal 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 62. The reception output program 62 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 62 from the storage 50 and executes the read reception output program 62 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 62 executed on the RAM 48.

[0032] Next, we will explain the processing of the specific processing unit 290 when the data processing device 12 performs specific processing to create a clinical trial protocol for a pharmaceutical product.

[0033] In the specific processing of this embodiment, as shown in Figure 3, the results of creating the trial plan portion of the clinical trial protocol for a pharmaceutical product using the dedicated generation AI model 58A are verified using the general-purpose generation AI model 58C, and the process of modifying the results using the dedicated generation AI model 58A is repeated according to the verification results.

[0034] Furthermore, for the analysis plan portion of the clinical trial protocol for pharmaceuticals, the results generated using the dedicated generation AI model 58B are verified using the general-purpose generation AI model 58C, and the process is repeated, with modifications made using the dedicated generation AI model 58B based on the verification results. Note that the trial plan portion and the analysis plan portion are examples of specific parts.

[0035] Furthermore, the ethical and other sections of the clinical trial protocol for pharmaceuticals will be created using the general-purpose generative AI model 58C. Note that the ethical and other sections are examples of parts that differ from specific sections.

[0036] Then, using the general-purpose generative AI model 58C, the various parts of the clinical trial protocol for the drug are integrated to create the clinical trial protocol for the drug.

[0037] As shown in Figure 4, the specific processing unit 290 includes an input unit 291, a specific part acquisition unit 292, a verification result acquisition unit 293, a correction result acquisition unit 294, an other part acquisition unit 295, and a creation unit 296.

[0038] The input unit 291 acquires user input received from the user terminal 14. Specifically, it acquires necessary information as user input received from the user terminal 14, which is information necessary for creating a drug development trial implementation plan or report. The necessary information includes at least the purpose of the clinical trial, the target disease, the treatment method, or information on the drug to be administered.

[0039] The specific part acquisition unit 292 inputs instruction information, which includes necessary information and instructs the creation of the test plan portion of the implementation plan or report, into the dedicated generation AI model 58A, and acquires the data for the test plan portion from the output of the dedicated generation AI model 58A. For example, "Create the test plan portion of the implementation plan for the drug development trial based on the necessary information below." ##Required Information## Objective of the clinical trial: ○○○ Target disease: ○○○ The instruction information, "Information on treatment method or medication to be administered: XXX," is input into the dedicated generation AI model 58A.

[0040] Furthermore, the specific part acquisition unit 292 inputs instruction information, which includes necessary information and instructs the creation of the analysis plan portion of the implementation plan or report, into the dedicated generation AI model 58B, and acquires the data for the test plan portion from the output of the dedicated generation AI model 58B.

[0041] The verification result acquisition unit 293 inputs instruction information, including the acquired test plan data and instructing the general-purpose generation AI model 58C to verify the test plan data, and obtains the verification result for the test plan data from the output of the general-purpose generation AI model 58C. For example, "The following is the test plan portion of the drug development test implementation plan. Please verify whether it is appropriate as a drug development test implementation plan." ## Test Plan Section of the Pharmaceutical Development Test Implementation Protocol ## The instruction information "XXX" is input into the general-purpose generative AI model 58C.

[0042] Furthermore, the verification result acquisition unit 293 inputs instruction information to the general-purpose generation AI model 58C, which includes the acquired data for the analysis plan portion and instructs the model to verify the data for the analysis plan portion, and obtains the verification result for the data for the analysis plan portion from the output of the general-purpose generation AI model 58C.

[0043] The correction result acquisition unit 294 inputs instruction information, which includes the verification results for the acquired test plan data and instructs the dedicated generation AI model 58A to correct the test plan data, and acquires the corrected test plan data from the output of the dedicated generation AI model 58A. For example, "Please correct the test plan portion of the drug development test implementation plan based on the verification results below." ##Verification Results## The instruction information "XXX" is input into the dedicated generation AI model 58A.

[0044] Furthermore, the correction result acquisition unit 294 inputs instruction information, which includes the verification results for the acquired analysis plan data and instructs the dedicated generation AI model 58B to correct the analysis plan data, and acquires the corrected analysis plan data from the output of the dedicated generation AI model 58B.

[0045] As a result of verifying the data for the test plan portion, the process of acquiring corrected data by the specific portion acquisition unit 292 and acquiring verification results by the verification result acquisition unit 293 is repeated until there are no more items that need to be corrected.

[0046] Furthermore, as a result of verifying the data for the analysis plan portion, the process of acquiring corrected data by the specific portion acquisition unit 292 and acquiring verification results by the verification result acquisition unit 293 is repeated until there are no more items that need to be corrected.

[0047] The other part acquisition unit 295 inputs instruction information, which includes necessary information and instructs the creation of the ethical and other parts of the drug development trial implementation plan, into the general-purpose generation AI model 58C, and acquires data for the ethical and other parts of the drug development trial implementation plan from the output of the general-purpose generation AI model 58C.

[0048] The creation unit 296 uses the acquired data for the revised test plan, the revised analysis plan, and the acquired data for the ethics and other parts to create a drug development test implementation plan.

[0049] Specifically, the creation unit 296 inputs instruction information into the general-purpose generation AI model 58C, which includes the acquired data for the revised test plan, the revised analysis plan, and the acquired data for the ethics and other parts, and instructs the model to integrate the data to create the entire implementation plan for the drug development trial. The result of creating the implementation plan for the drug development trial is then obtained from the output of the general-purpose generation AI model 58C.

[0050] Furthermore, the creation unit 296 transmits the results of creating the drug development trial implementation plan to the user terminal 14. On the user terminal 14, the control unit 46A causes the output device 40 to output the results of creating the drug development trial implementation plan. The receiving device 38 acquires user input regarding the results of creating the drug development trial implementation plan. The control unit 46A then transmits the user input acquired by the receiving device 38 to the data processing device 12. On the data processing device 12, the specific processing unit 290 acquires the user input.

[0051] Next, the operation of the data processing system 10 will be explained.

[0052] An example of the flow of specific processing by the data processing device 12 will be explained with reference to Figure 5. Note that the flow of specific processing shown in Figure 5 is an example of a "data processing method" related to the technology of this disclosure.

[0053] In step S100, the input unit 291 acquires necessary information, which is information required to create a drug development trial implementation plan or report, as user input received from the user terminal 14.

[0054] In step S102, the specific part acquisition unit 292 inputs instruction information, which includes necessary information and instructs the creation of the test plan portion of the implementation plan or report, into the dedicated generation AI model 58A, and acquires the data for the test plan portion from the output of the dedicated generation AI model 58A.

[0055] Furthermore, the specific part acquisition unit 292 inputs instruction information, which includes necessary information and instructs the creation of the analysis plan portion of the implementation plan or report, into the dedicated generation AI model 58B, and acquires the data for the test plan portion from the output of the dedicated generation AI model 58B.

[0056] In step S104, the verification result acquisition unit 293 inputs instruction information to the general-purpose generation AI model 58C, which includes the acquired test plan data and instructs the verification of the test plan data, and obtains the verification result for the test plan data from the output of the general-purpose generation AI model 58C.

[0057] Furthermore, the verification result acquisition unit 293 inputs instruction information to the general-purpose generation AI model 58C, which includes the acquired data for the analysis plan portion and instructs the model to verify the data for the analysis plan portion, and obtains the verification result for the data for the analysis plan portion from the output of the general-purpose generation AI model 58C.

[0058] In step S106, the data processing device 12 determines whether there are any items that need to be corrected based on the verification results obtained in step S104. For example, if the obtained verification results include an indication of items that need to be corrected (step S106; Yes), the data processing device 12 proceeds to step S108. On the other hand, if the obtained verification results do not include an indication of items that need to be corrected (step S106; No), the data processing device 12 proceeds to step S110.

[0059] In step S108, if the verification results for the test plan data include indications of items that need to be corrected, the correction result acquisition unit 294 inputs instruction information, including the acquired verification results for the test plan data and instructing the correction of the test plan data, into the dedicated generation AI model 58A, and acquires the corrected test plan data from the output of the dedicated generation AI model 58A.

[0060] Furthermore, if the verification results for the data in the analysis plan portion include points indicating items that need to be corrected, the correction result acquisition unit 294 inputs instruction information, including the acquired verification results for the data in the analysis plan portion, to the dedicated generation AI model 58B, instructing it to correct the data in the analysis plan portion, and acquires the corrected data in the analysis plan portion from the output of the dedicated generation AI model 58B.

[0061] Then, the data processing device 12 returns to step S104.

[0062] In step S110, the other part acquisition unit 295 inputs instruction information, which includes necessary information and instructs the creation of the ethical and other parts of the drug development trial implementation plan, into the general-purpose generation AI model 58C, and acquires data for the ethical and other parts of the drug development trial implementation plan from the output of the general-purpose generation AI model 58C.

[0063] In step S112, the creation unit 296 integrates the acquired data for the revised test plan, the revised analysis plan, and the acquired data for the ethics and other parts, inputs instruction information to the general-purpose generation AI model 58C to instruct the creation of the entire drug development test implementation plan, and obtains the result of creating the drug development test implementation plan from the output of the general-purpose generation AI model 58C.

[0064] In step S114, the creation unit 296 sends the result of creating the drug development trial implementation plan to the user terminal 14 and terminates the identification process.

[0065] As described above, according to the information processing system of this embodiment, by using a user-specific generative AI model trained using confidential data provided by the user and a general-purpose generative AI model trained using publicly available data, it is possible to appropriately create a drug development trial plan or report while taking data confidentiality into consideration.

[0066] Furthermore, by creating a drug development trial protocol or report while verifying data from specific parts of the protocol or report between a user-specific generative AI model and a general-purpose generative AI model, it is possible to create a more appropriate drug development trial protocol or report.

[0067] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0068] In the above embodiment, an example was given in which data from a specific part of the drug development trial implementation plan or report is created while verifying it between a user-specific generation AI model and a general-purpose generation AI model. However, it is also possible to create the report while verifying data from parts other than the specific part of the drug development trial implementation plan or report. For example, data from the ethical and other parts of the drug development trial implementation plan is obtained from the output of the general-purpose generation AI model 58C, and instruction information that includes the obtained data from the ethical and other parts and instructs verification of the data from the ethical and other parts is input to the general-purpose generation AI model 58C, and the verification results for the data from the ethical and other parts are obtained from the output of the general-purpose generation AI model 58C. If the obtained verification results include suggestions for corrections, instruction information that includes the verification results for the obtained data from the ethical and other parts and instructs corrections to the data from the ethical and other parts is input to the general-purpose generation AI model 58C, and the corrected data from the ethical and other parts is obtained from the output of the general-purpose generation AI model 58C.

[0069] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0070] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0071] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0072] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0073] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0074] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0075] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0076] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0077] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0078] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference. [Explanation of symbols]

[0079] 10 Data Processing Systems 12 Data Processing Devices 14 User terminals Dedicated generation model for 58A and 58B 290 Specific Processing Unit 291 Input section 292 Specific part acquisition part 293 Verification Result Acquisition Unit 294 Correction result acquisition part 295 Other part acquisition part 296 Creation Department

Claims

1. An input unit that receives necessary information from the user, including at least the purpose of the clinical trial, the target disease, and information on the treatment or drug to be administered, as information necessary for creating a clinical trial protocol or report for a drug. A specific part acquisition unit inputs instruction information, which includes the necessary information and instructs the creation of a specific part that is the test plan portion or analysis plan portion of an implementation plan or report, into a user-specific generating AI model that has been trained using the test plan portion or analysis plan portion of an implementation plan or report provided as confidential data by the user, and acquires data of the specific part from the output of the user-specific generating AI model. A verification result acquisition unit inputs instruction information, which includes the acquired data of the specific portion and instructs the verification of whether the data of the specific portion is appropriate as a clinical trial protocol or report for a drug, into a general-purpose generative AI model trained using publicly available data, and acquires the verification result for the data of the specific portion from the output of the general-purpose generative AI model. If the verification results for the acquired data of the specific portion include indications of items that need to be corrected, the correction result acquisition unit inputs the verification results for the acquired data of the specific portion, along with instruction information instructing the correction of the data of the specific portion, into the user-specific generation AI model, and acquires the corrected data of the specific portion from the output of the user-specific generation AI model. A creation unit inputs instruction information, which includes the acquired modified specific portion data, into the general-purpose generation AI model to instruct it to create the entire clinical trial protocol or report for the drug, and obtains the clinical trial protocol or report for the drug from the output of the general-purpose generation AI model. A data processing device that includes a data processing device.

2. The system further includes an additional part acquisition unit that inputs instruction information, including the aforementioned necessary information and instructing the creation of the ethical section of an implementation plan or report, into the general-purpose generation AI model, and acquires the data for the ethical section from the output of the general-purpose generation AI model. The data processing device according to claim 1, wherein the creation unit inputs instruction information to the general-purpose generation AI model, which includes the acquired modified specific portion data and the acquired ethical portion data, and instructs the creation of the entire implementation plan or report by integrating the data, and obtains the result of creating the implementation plan or report of the clinical trial of the pharmaceutical from the output of the general-purpose generation AI model.

3. Computers The system accepts input from users of necessary information required for creating a clinical trial protocol or report for a drug, including at least the purpose of the clinical trial, the target disease, and information on the treatment or drug administered. The necessary information is included, and instruction information that instructs the creation of a specific part which is the test plan portion or analysis plan portion of the implementation plan or report is input into a user-specific generating AI model that has been trained using the test plan portion or analysis plan portion of the implementation plan or report provided by the user as confidential data, and the data of the specific part is obtained from the output of the user-specific generating AI model. The acquired data of the specific portion, along with instruction information instructing the verification of whether the data of the specific portion is appropriate as a clinical trial protocol or report for a drug, is input into a general-purpose generative AI model trained using publicly available data, and the verification results for the data of the specific portion are obtained from the output of the general-purpose generative AI model. If the verification results for the acquired data of the specific portion include indications of items that need to be corrected, the verification results for the acquired data of the specific portion, along with instruction information instructing the correction of the data of the specific portion, are input into the user-specific generation AI model, and the corrected data of the specific portion is obtained from the output of the user-specific generation AI model. The general-purpose generation AI model is given instruction information that instructs it to create the entire clinical trial protocol or report for the drug, including the modified specific data obtained, and the clinical trial protocol or report for the drug is obtained from the output of the general-purpose generation AI model. A data processing method that performs a particular action.

4. On the computer, The system accepts input from users of necessary information required for creating a clinical trial protocol or report for a drug, including at least the purpose of the clinical trial, the target disease, and information on the treatment or drug administered. The necessary information is included, and instruction information that instructs the creation of a specific part which is the test plan portion or analysis plan portion of the implementation plan or report is input into a user-specific generating AI model that has been trained using the test plan portion or analysis plan portion of the implementation plan or report provided by the user as confidential data, and the data of the specific part is obtained from the output of the user-specific generating AI model. The acquired data of the specific portion, along with instruction information instructing the verification of whether the data of the specific portion is appropriate as a clinical trial protocol or report for a drug, is input into a general-purpose generative AI model trained using publicly available data, and the verification results for the data of the specific portion are obtained from the output of the general-purpose generative AI model. If the verification results for the acquired data of the specific portion include indications of items that need to be corrected, the verification results for the acquired data of the specific portion, along with instruction information instructing the correction of the data of the specific portion, are input into the user-specific generation AI model, and the corrected data of the specific portion is obtained from the output of the user-specific generation AI model. The general-purpose generation AI model is given instruction information that instructs it to create the entire clinical trial protocol or report for the drug, including the modified specific data obtained, and the clinical trial protocol or report for the drug is obtained from the output of the general-purpose generation AI model. A data processing program used to execute a process.

Images