Device and method

Abstract

The present disclosure makes it possible to efficiently create improvement information for improving the design of a system. A device 10 according the present disclosure includes: an information acquisition unit 12 that acquires system information including at least one of development information related to development of a target system and operational information related to operation of the target system; and a generation unit 17 that generates, on the basis of the system information, a prompt for instructing an AI model 41 to output improvement information that improves the design of the target system.

Description

Device and Method

[0001] One aspect of the present disclosure relates to a device and method for generating a prompt.

[0002] Patent Document 1 discloses a method for generating a system configuration plan. In the method described in Patent Document 1, the validity of the system configuration information input by the user is evaluated. When a problem is found in the validity evaluation, a design pattern that can solve the problem to be processed is searched from the design pattern set. When a design pattern that can solve the problem is found, the system configuration is optimized by applying the design pattern.

[0003] Japanese Patent Application Laid-Open No. 2015-125701

[0004] In the method as described in Patent Document 1 above, a design pattern is selected from the registered design pattern set. Therefore, it is necessary to register a large number of design patterns in advance, and there is a possibility that an appropriate system configuration plan cannot be created when an improvement plan suitable for the needs of actual system development or system operation is not included in the registered pattern set.

[0005] An object of the present disclosure is to efficiently create improvement information for improving the design of a system.

[0006] The device according to one aspect of the present disclosure includes an information acquisition unit that acquires system information including at least one of development information related to the development of a target system and operation information related to the operation of the target system, and a generation unit that generates a prompt for instructing the output of improvement information for improving the design of the target system based on the AI model based on the system information.

[0007] The method according to one aspect of the present disclosure includes a step of acquiring system information including at least one of development information related to the development of a target system and operation information related to the operation of the target system, and a step of generating a prompt for instructing the output of improvement information for improving the design of the target system based on the AI model based on the system information.

[0008] According to one aspect of this disclosure, it is possible to efficiently create improvement information to improve the system design.

[0009] Figure 1 is a diagram showing an overview of the processing of an information creation system according to one embodiment of the present disclosure. Figure 2 is a diagram showing an overview of the processing of an information creation system according to one embodiment of the present disclosure. Figure 3 is a diagram showing the device configuration of the information creation system. Figure 4 is a flowchart showing an example of the operation of the information creation system. Figure 5 is a diagram showing an example of persona setting information. Figure 6 is a diagram showing an example of persona setting information. Figure 7 is a diagram showing an example of a prompt. Figure 8 is a diagram showing the device configuration of an information creation system according to a modified example. Figure 9 is a diagram showing the device configuration of an information creation system according to a modified example. Figure 10 is a diagram showing an example of the hardware configuration of an information creation system according to one embodiment of the present disclosure.

[0010] Embodiments of this disclosure will be described with reference to the attached drawings. Where possible, the same parts will be denoted by the same reference numerals, and redundant descriptions will be omitted.

[0011] The information creation system according to this embodiment is a system that creates improvement information to improve the design of a target system. In this embodiment, the system is an information system and is composed of at least one element from, for example, hardware, software, a database, and a network. The target system is the system (the system that is the target of improvement) for which improvement information is created by the information creation system according to this embodiment.

[0012] Improvement information for improving the design of the target system refers to information for changing part or all of the target system. For example, it may be information indicating the content of changes to resolve problems or issues existing in the target system, or to respond to requirements or requests for the target system. As an example, improvement information may also be information that improves the functionality, performance, scalability, maintainability, etc., of the target system. Improvement information may also be improvement design information, which is a proposed improvement to the design information of the target system. Details of design information will be described later.

[0013] This figure shows an overview of the processing of the information creation system according to this embodiment. The processing shown below is an example of processing performed by the information creation system. As shown in Figure 1, first, the information creation system acquires design information of the target system and system information that includes at least one of development information related to the development of the target system and operation information related to the operation of the target system. Next, the information creation system generates a prompt based on the system information to instruct the AI ​​model to output improvement information to improve the design of the target system. At this time, the information creation system may also generate a prompt based on the design information of the target system in addition to the system information.

[0014] Next, as shown in Figure 2, the information creation system inputs the generated prompt to the AI ​​model, causing the AI ​​model to output improvement information. As described above, the information creation system according to this embodiment has the function of generating prompts to instruct the AI ​​model to output improvement information. Therefore, the information creation system also functions as a prompt generation system that generates prompts.

[0015] System design information is information that shows the design of a system and includes various types of information necessary to build the system. For example, design information may be a design drawing that shows the design of the system. A design drawing may be an architecture diagram, a system configuration diagram, or a cloud configuration diagram. An architecture diagram is a diagram that visually represents the overall structure of the system. For example, an architecture diagram may show the structure of the main elements of the system, such as servers, databases, networks, and user interfaces. A system configuration diagram is a diagram that shows the arrangement and structure of specific hardware and software, and may constitute a part of an architecture diagram. A cloud configuration diagram is a diagram that shows the arrangement and connection of resources in a cloud environment. A cloud configuration diagram may be a diagram that shows the combination of resources provided by cloud services such as AWS (Amazon Web Services). Resources include servers, databases, networks, software, etc. Design information may include source code for implementing each element of the system. Design information may include information indicating the type of design drawing, information indicating the name of the design drawing, and information such as the device configuration included in the design drawing.

[0016] As another example, design information may be in the form of Infra as Code (IaC). Infra as Code is code that represents the hardware configuration of a system. For example, Infra as Code is code that defines resources such as servers, databases, and networks included in the system.

[0017] The improved design information, which is a proposed improvement to the design information of the target system, may be a design drawing showing the system design as described above, or it may be Infra as Code (IaC).

[0018] System information includes at least one of the following: development information relating to the development of the target system and operational information relating to the operation of the target system. Development information is various types of information relating to the development of the target system. Development information may, for example, be information indicating requirements for the development of the target system. Specifically, development information may include the requirements (developer's voice) of developers at each phase of system development, such as design, implementation, testing, and deployment of the target system.

[0019] Operational information refers to various types of information related to the operation of the target system. For example, operational information may include information indicating requests regarding the operation of the target system. Specifically, operational information may include requests (operator feedback) from operators in each phase of system operation, such as monitoring the operating status and performance of the target system, maintenance, and incident management. Operational information may also include log data of the target system. For example, log data may include information about errors or warnings output by applications included in the target system, or data related to user access logs to the target system.

[0020] [System Configuration] Figure 2 shows the device configuration of the information creation system 1 according to this embodiment. The information creation system 1 includes a device 10. The device 10 according to this embodiment may be, for example, a RAG (Retrieval-Augmented Generation) system. The device 10 is connected to a user terminal 20, a database 30, and a server device 40 via a communication network N. The configuration of the communication network N is not limited. For example, the communication network N may include the internet or include an intranet.

[0021] The device 10 includes, as functional components, a reception unit 11, an information acquisition unit 12, a label acquisition unit 13, a determination unit 14, a reference design information acquisition unit 15, a persona creation unit 16, a generation unit 17, and a creation unit 18.

[0022] The reception unit 11 is a functional element that receives various data and information (e.g., information related to requests and instructions) from, for example, the user terminal 20. The information acquisition unit 12 is a functional element that acquires various data and information from, for example, the user terminal 20 and the database 30. The label acquisition unit 13 is a functional element that acquires perspective labels, which will be described later, from the database 30. The determination unit 14 is a functional element that determines the importance level of the perspective labels.

[0023] The reference design information acquisition unit 15 is a functional element that acquires reference design information, which will be described later. The persona creation unit 16 is a functional element that creates setting information that indicates a persona, which will be described later. The generation unit 17 is a functional element that generates prompts to instruct the AI ​​model 41, which will be described later, to output improvement information. The creation unit 18 is a functional element for creating improvement information.

[0024] User terminal 20 is a computer used by a user. The user is a person who receives (or creates) improvement information using the information creation system 1. The user may be the developer of the target system or the operator of the target system, etc. The type of computer used as user terminal 20 is not limited. User terminal 20 may be, for example, a personal computer, a high-function mobile phone (smartphone), a mobile phone, a personal digital assistant (PDA), a tablet device, or a wearable device. The number of user terminals 20 is not limited.

[0025] Database 30 is a non-temporary storage device that stores data and information used in the information creation system 1. Database 30 may be constructed as a single database or as a collection of multiple databases. The location of database 30 is not limited. Database 30 may be located, for example, in a computer system separate from the information creation system 1.

[0026] The server device 40 is equipped with an AI model 41. The AI ​​model 41 outputs improvement information according to a given prompt. The AI ​​model 41 in this embodiment is a Generative Artificial Intelligence (Generative AI) model. A Generative AI model is a model that, in response to a prompt containing input information, creates content according to any or a combination of the instructions, context, questions, and output format indicated by the prompt, and returns that content as output information.

[0027] A prompt is a set of instructions or information input to a generative AI model. This prompt may include initial information, parameters, and questions for the generative AI model to perform a specific task. In a prompt, text is used to express, for example, the command the generative AI model should execute, the task the generative AI model should perform, the background and context that the generative AI model should consider (e.g., roles, conditions), the questions that the generative AI model should answer, and the output format of the output information from the generative AI model.

[0028] Prompts may be input to the generating AI model along with input information that is the target or reference for the instructions / tasks the generating AI model will execute. Such input information includes data files with filenames containing predetermined extensions, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data refers to data such as document data, table data, and graph data that can be processed by a default application program.

[0029] The AI ​​model 41 may be a Large Language Model (LLM). In this case, the AI ​​model 41 may be a conversational AI that includes, for example, a large language model and a user interface (UI) for interaction with the user, enabling text chat or voice chat with the user. Examples of such an AI model 41 include ChatGPT, GPT®-3.5, GPT-4V, PaLM2, etc.

[0030] The AI ​​model 41 according to this embodiment receives a prompt as input information to instruct the output of improvement information (task), generates improvement information according to the prompt, and outputs the generated improvement information as output information.

[0031] [System Operation] The operation of the information creation system 1 will be explained with reference to Figure 4. Specifically, the prompt generation method according to this embodiment and the method for creating improvement information using the prompts generated by this method will be explained. The process of the prompt generation method can be considered a part of the process of the improvement information creation method. Figure 4 is a flowchart showing an example of the operation of the information creation system 1.

[0032] The process for creating the following improvement information may be initiated when the device 10 receives a request for improvement information (triggered by the request). The request for improvement information may be, for example, request information notified from the user terminal 20 to the receiving unit 11 of the device 10 when a request for improvement button displayed on a web page or application page displayed on the display of the user terminal 20 is selected (for example, pressed by the user).

[0033] In step S11, the information acquisition unit 12 acquires the design information of the target system. The information acquisition unit 12 may also acquire the design information from the user terminal 20. For example, the user inputs the design information of the target system that they wish to improve into the user terminal 20 by operating the user terminal 20. The information acquisition unit 12 acquires the input design information from the user terminal 20.

[0034] The information acquisition unit 12 may acquire design information from the database 30. The user may specify a target system for which they wish to make improvements by operating the user terminal 20, and the information acquisition unit 12 may acquire design information corresponding to the specified target system from the database 30. The design information may be stored in the database 30 in advance by the user or another party. The design information may be stored in the database 30 in association with information for identifying the system (e.g., the name of the system). In this case, for example, the user may specify the target system using information for identifying the system, and the information acquisition unit 12 may acquire design information corresponding to the target system from the database 30.

[0035] The information acquisition unit 12 may acquire design information from both the user terminal 20 and the database 30. For example, the information acquisition unit 12 may acquire other design information from the database 30 based on the design information acquired from the user terminal 20. For example, the information acquisition unit 12 may acquire the architecture diagram of the target system as design information from the user terminal 20 and acquire detailed information of each element (server, etc.) of the target system included in the architecture diagram from the database 30. The information acquisition unit 12 may acquire information from the internet as design information. For example, the information acquisition unit 12 may search for information on the internet and acquire detailed information of each element (server, etc.) of the target system included in the architecture diagram as design information. In this embodiment, the information acquisition unit 12 acquires the design diagram of the target system (hereinafter also referred to as the target design diagram) input by the user from the user terminal 20 as design information.

[0036] In step S12, the information acquisition unit 12 acquires system information of the target system. The information acquisition unit 12 may also acquire system information from the user terminal 20. For example, the user inputs system information into the user terminal 20 by operating the user terminal 20. More specifically, the user inputs information indicating requirements for the development of the target system and information indicating requirements for the operation of the target system as system information into the user terminal 20. The information acquisition unit 12 acquires the input system information from the user terminal 20.

[0037] The information acquisition unit 12 may acquire system information from the database 30. The user may specify a target system by operating the user terminal 20, and the information acquisition unit 12 may acquire system information corresponding to the specified target system from the database 30. For example, the information acquisition unit 12 may acquire log data of the target system associated with the specified target system from the database 30. System information may be stored in the database 30 in advance by the user or someone other than the user. System information such as log data may be stored in the database 30 in association with information for identifying the system (for example, the name of the system). In this case, for example, the user may specify a target system using information for identifying the system, and the information acquisition unit 12 may acquire system information corresponding to the target system from the database 30.

[0038] The information acquisition unit 12 may acquire system information from both the user terminal 20 and the database 30. For example, the information acquisition unit 12 may acquire information indicating requests regarding the development of the target system and information indicating requests regarding the operation of the target system as system information from the user terminal 20, and acquire log data of the target system as other system information from the database 30.

[0039] In this embodiment, the information acquisition unit 12 acquires information indicating the user's requirements for the development of the target system (development information) and information indicating the user's requirements for the operation of the target system (operation information) as system information. More specifically, the information acquisition unit 12 acquires information indicating the user's requirements for the development of the target system, such as "Simple code is preferred. It is preferable that development be completed in four weeks by three developers," from the user terminal 20 as development information. The information acquisition unit 12 also acquires information indicating the user's requirements for the operation of the target system, such as "The service must never stop. It is preferable that the system can withstand simultaneous connections from at least 20,000 people," from the user terminal 20 as operation information.

[0040] In step S13, the label acquisition unit 13 acquires a number of labels from the database 30 that indicate perspectives on system improvement. Labels indicating perspectives on system improvement (hereinafter referred to as perspective labels) are labels that indicate elements (values) to be considered when improving the system. In this example, the perspective labels include at least one of the following: a label based on perspectives on system development (first label) and a label based on perspectives on system operation (second label). A label based on perspectives on system development (first label) is a label that indicates perspectives on system improvement that should be considered from the viewpoint of system development, and may, for example, be a label that indicates the values ​​of the system developer. As an example, the first label may be a label that indicates elements (values) related to system development, such as "emphasis on cost efficiency," "emphasis on development period," or "emphasis on development difficulty."

[0041] Labels based on system operation perspectives (second labels) are labels that indicate aspects of system improvement that should be considered from a system operation perspective, and may, for example, be labels that indicate the values ​​of the system operator. For example, the second label may be a label that indicates elements (values) related to system operation, such as "emphasis on usability," "emphasis on availability," or "emphasis on performance." Perspective labels (first labels and second labels) may be stored in the database 30 in advance by the user or a person other than the user.

[0042] In this embodiment, the label acquisition unit 13 acquires a plurality of first labels such as "emphasis on cost efficiency", "emphasis on development period", and "emphasis on development difficulty", and a plurality of second labels such as "emphasis on operability", "emphasis on usability", and "emphasis on performance" as a plurality of perspective labels.

[0043] In step S14, the determination unit 14 determines the importance degree of each of the plurality of perspective labels based on the system information. In this example, first, the determination unit 14 determines the importance degree of each of the plurality of first labels based on the information indicating the requirements for the development of the target system acquired by the information acquisition unit 12. As an example, the information acquisition unit 12 may determine the importance degree of the first label by using a learned model that has learned the relevance between the information indicating the requirements for the development of the system and the first label.

[0044] Specifically, the learned model may be a model generated by training a machine learning model using, as teacher data, information indicating the requirements for the development of the system and the first label (correct data) corresponding to the information (the first label emphasized by the information). The machine learning model is a computational model used for machine learning. The learned model may be a model that accepts information indicating the requirements for the development of the system and at least one first label and outputs the importance degree of each first label. The learned model may output the importance degree of each first label, for example, by a score (numerical value).

[0045] In this example, the decision unit 14 inputs the information indicating the requirements for the development of the target system, obtained in step S11, and the multiple first labels obtained in step S13, into the trained model, which outputs the importance of each first label as a score. Specifically, the decision unit 14 inputs the information indicating the requirements for development, such as "Simple code is preferred. It is preferable that development be completed in four weeks by three developers," and the multiple first labels, such as "Emphasis on cost efficiency," "Emphasis on development period," and "Emphasis on development difficulty." In this example, the trained model outputs a score of 76 for "Emphasis on cost efficiency," a score of 46 for "Emphasis on development period," and a score of 53 for "Emphasis on development difficulty" as the importance of each first label. The higher the score value, the greater the degree to which the information indicating the requirements for the development of the target system places importance on the viewpoint of the first label corresponding to that score. The decision unit 14 obtains the importance of each first label output by the trained model. Through the above process, the decision unit 14 determines the importance of each of the multiple first labels (perspective labels).

[0046] Next, the decision unit 14 determines the importance of each of the multiple second labels based on the information indicating the requirements for the operation of the target system acquired by the information acquisition unit 12. As an example, the information acquisition unit 12 may determine the importance of the second labels using a trained model that has learned the relationship between the information indicating the requirements for the operation of the system and the second labels.

[0047] Specifically, the trained model may be a model generated by training a machine learning model using information indicating requirements for system operation and a second label (ground truth data) corresponding to that information (which is emphasized by that information) as training data. The trained model may also be a model that accepts information indicating requirements for system operation and at least one second label, and outputs the importance of each second label. The trained model may output the importance of each second label, for example, as a score (numerical value).

[0048] In this example, the determination unit 14 inputs, into the learned model that outputs the importance degree of each second label by a score, information indicating the requirements for the operation of the target system acquired in step S11 and the plurality of second labels acquired in step S13. Specifically, the determination unit 14 inputs information indicating the requirements for the operation such as "The service must never stop. A system that can withstand simultaneous connections from at least 20,000 people is preferable." and the plurality of second labels "emphasis on operability", "emphasis on availability", and "emphasis on performance". In this example, the learned model outputs 51 points corresponding to "emphasis on operability", 88 points corresponding to "emphasis on availability", and 66 points corresponding to "emphasis on performance" as the importance degree of each second label. The larger the score value, the higher the degree to which the information indicating the requirements for the operation of the target system highly values the perspective of the second label corresponding to the score. The determination unit 14 acquires the importance degree of each second label output by the learned model. Through the above processing, the determination unit 14 determines the importance degree of each of the plurality of second labels (perspective labels).

[0049] In step S15, the reference design information acquisition unit 15 acquires a plurality of reference design information. The reference design information is a sample of the design information of the system. The reference design information may be stored in the database 30 in association with at least any one of information on the type of design drawing, the configuration of the system, the configuration of the devices included in the system, and the elements (values) to be considered when improving the system. The reference design information acquisition unit 15 may, for example, extract and acquire a plurality of reference design information related to these information from the database 30 based on the system information, the perspective label, and the importance degree of the perspective label. In the present embodiment, the reference design information acquisition unit 15 acquires, from the database 30, a model (reference design drawing) of the design drawing of the system as the reference design information. The reference design information acquisition unit 15 acquires a plurality of reference design drawings.

[0050] In step S16, the persona creation unit 16 creates multiple setting information entries that represent multiple personas. A persona is a hypothetical character. In this example, the persona is a hypothetical character that evaluates the improvement information generated by the AI ​​model 41. Setting information is information that represents the persona (hypothetical character) and may include, for example, the persona's name, position, values ​​(the elements that the persona considers when improving the system and their importance), and at least one of the comments that the persona frequently makes regarding the system design information. The persona creation unit 16 may create the setting information based on the viewpoint labels obtained in step S13 and the importance levels determined in step S14. The multiple setting information entries generated by the persona creation unit 16 may be stored in the database 30.

[0051] In this example, the persona creation unit 16 creates setting information (setting information 1 and 2) for two personas shown in Figures 5 and 6. As shown in Figure 5, the persona creation unit 16 creates setting information 1, which includes the persona's name "Docomo Taro", position "Developer", values ​​"Emphasis on cost efficiency score 76 points, emphasis on development period score 46 points, emphasis on development difficulty score 53 points", and a comment that the persona frequently makes regarding design information (design drawings in this example) "Service interruptions are unacceptable!". In this example, the persona creation unit 16 creates the value information included in the setting information based on the perspective labels obtained in step S13 and the importance scores determined in step S14.

[0052] As shown in Figure 6, the persona creation unit 16 creates the following information as setting information 2: persona name "ahamo Hanako", position "operator", values ​​"ease of use score 51, availability score 88, performance score 66", comments frequently made regarding reference design drawing X "In this design, there is a concern that ABC will become a bottleneck and cause service interruptions, but service interruptions are unacceptable from an operational standpoint.", and comments frequently made regarding reference design drawing Y "In this design, the possibility of service interruptions is not high, but the server may crash when access is concentrated. It would be better to duplicate XYZ.". As shown in the example in Figure 6, the persona creation unit 16 may also include comments frequently made regarding each reference design information (reference design drawing in this example) stored in the database 30 or acquired by the reference design information acquisition unit 15 in the setting information.

[0053] In step S17, the generation unit 17 generates a prompt for instructing the AI ​​model 41 to output improvement information, based on the system information. Generating a prompt based on system information may mean generating the prompt using the system information itself, or it may mean generating the prompt using information obtained using the system information (for example, viewpoint labels and their importance).

[0054] The AI ​​model 41 generates improvement information based on the input prompt. The generation unit 17 generates prompts that satisfy the conditions for prompts that can be input to the AI ​​model 41. The conditions for prompts may be, for example, the number of tokens or the format (language, etc.). The generation unit 17 may generate prompts using a generation AI model or another trained model. The generation unit 17 may also generate prompts by obtaining a prompt format stored in advance in a database 30 or the like, and incorporating system information and user requests regarding prompts obtained via the user terminal 20 into the format. The method of generating prompts is not limited.

[0055] Figure 7 shows an example of a prompt generated by the generation unit 17. The prompt includes the task to be executed by the AI ​​model 41 (instructions for the AI ​​model 41), its role, and conditions. As a result, the AI ​​model 41 executes the task according to its role and conditions. The prompt includes the following sentence as the task: "Create several improved design drawings, which are improvement proposals for the target design drawing, based on several reference design drawings. Next, as the following persona, score the several improved design drawings and create comments." The prompt also includes persona setting information as the role of the AI ​​model 41. In this example, the prompt includes two pieces of setting information created in step S16. The prompt also includes conditions that the AI ​​model 41 should consider. In this example, the prompt includes the following conditions: "Create one improvement design for each reference design (create as many improvement design drawings as there are reference design drawings)," "If multiple names are listed for a role, perform the following for each name," "Score each improvement design based on values," and "Create comments for each improvement design based on frequently made comments."

[0056] The generation unit 17 includes a prompt instructing the AI ​​model 41 to create multiple improved design drawings, which are improvement proposals for the target design drawing, based on multiple reference design drawings, as a task for the AI ​​model 41. Therefore, the generation unit 17 generates a prompt instructing the AI ​​model 41 to create multiple improved design information based on multiple reference design information. Furthermore, the generation unit 17 includes a prompt instructing the AI ​​model 41 to score the multiple improved design drawings as a task for the AI ​​model 41. Therefore, the generation unit 17 generates a prompt instructing the AI ​​model 41 to evaluate the created multiple improved design information.

[0057] The generation unit 17, as part of the AI ​​model 41's role, includes setting information indicating the persona in the prompt. Therefore, the generation unit 17 generates prompts based on the setting information. In this example, the persona setting information is created using multiple perspective labels and the importance levels of those perspective labels. Therefore, the generation unit 17 generates prompts based on the importance levels of the multiple perspective labels. More specifically, the multiple perspective labels are multiple first labels and multiple second labels, and the importance levels of the multiple perspective labels are the importance levels of the multiple first labels and the importance levels of the multiple second labels. Therefore, it can also be said that the generation unit 17 generates prompts based on the importance levels of the multiple first labels and the importance levels of the multiple second labels.

[0058] As described above, the AI ​​model 41 may receive input information that is the target or reference for the task that the AI ​​model 41 will perform, along with prompts. In this example, the design information to be improved (target design drawing) acquired in step S11 and the multiple reference design information (reference design drawings) acquired in step S15 are input to the AI ​​model 41 along with prompts. Therefore, the generation unit 17 includes information in the prompts that allows the AI ​​model 41 to identify the data files of the target design drawing and the reference design drawings, which are the input information. In this example, the generation unit 17 includes the file names of the data files of the target design drawing and the reference design drawings ("Target Design Drawing A", "Reference Design Drawing X", "Reference Design Drawing Y") in the prompts.

[0059] In step S18, the creation unit 18 creates improvement information using the AI ​​model 41. The reference design information acquisition unit 15 inputs the prompt generated in step S17, the design information to be improved (data file of the target design drawing) acquired in step S11, and the multiple reference design information (data files of reference design drawings) acquired in step S15 into the AI ​​model 41.

[0060] AI model 41 executes tasks based on input prompts. In this example, AI model 41 first creates multiple improved design drawings (improved design information), which are proposed improvements to the target design drawing, based on multiple reference design drawings (reference design information). Next, AI model 41, acting as the persona indicated in the role, scores (evaluates) the multiple improved design drawings and creates comments for each of them. For scoring (evaluation) by AI model 41, a trained model may be used, which has been trained with preferred design drawings (design drawings that match the values) for each persona as ground truth data, and which outputs a score when a design drawing is input. In this case, the AI ​​model that performs the evaluation may be AI model 41 or another AI model (i.e., AI model 41 may use another AI model that outputs a score for evaluation). AI model 41 outputs the multiple improved design drawings (improved design information) for which scoring and comment creation have been performed as improvement information to the creation unit 18. The scoring results and comments may be output in the data file of the improvement design drawing, or they may be output in a data file different from the data file of the improvement design drawing. The creation unit 18 acquires improvement information from the AI ​​model 41. Through the above process, the creation unit 18 creates improvement information. The creation unit 18 may store the created improvement information in the database 30, or it may send it to the user terminal 20.

[0061] In recent years, advancements in information processing technology have led to increased complexity in services utilizing this technology, resulting in more sophisticated service operations. However, due to factors such as the declining birthrate, a decrease in the number of personnel capable of performing these service operations is anticipated. Furthermore, the widespread adoption of agile development has made DevOps (Development and Operations) development methodologies commonplace, requiring real-time improvements to issues arising during operation while the service is running. Additionally, the system information to be considered when improving a target system (development information, operational information, etc.) encompasses a wide range of data, including developer requests, operator requests, and log data, potentially resulting in a massive amount of data. Therefore, there is a need for technologies that efficiently generate improvement information to enhance system design.

[0062] The apparatus 10 relating to one aspect of this disclosure includes an information acquisition unit 12 that acquires system information including at least one of development information relating to the development of the target system and operation information relating to the operation of the target system, and a generation unit 17 that generates a prompt for instructing the AI ​​model 41 to output improvement information to improve the design of the target system, based on the system information.

[0063] A prompt generation method relating to one aspect of this disclosure includes the steps of: acquiring system information including at least one of development information relating to the development of the target system and operation information relating to the operation of the target system; and generating a prompt based on the system information for instructing the AI ​​model 41 to output improvement information to improve the design of the target system.

[0064] In the aspects of this disclosure described above, prompts for instructing the AI ​​model 41 to output improvement information to improve the design of the target system are generated based on system information that includes at least one of development information related to the development of the target system and operational information related to the operation of the target system. Therefore, by inputting the generated prompts into the AI ​​model, improvement information that takes the system information into account (improvement information that is suitable for the needs) can be created. In other words, improvement information can be efficiently created without having to prepare a large number of improvement proposals in advance, and without the user having to consider (analyze) a large amount of system information.

[0065] Furthermore, when creating information using an AI model (such as a generative AI model), in order for the AI ​​model to output the information desired by the user, the user needs to appropriately create prompts to input to the AI ​​model. However, generating prompts can require advanced skills and a great deal of time. For example, if a prompt that does not contain clear instructions is used, the AI ​​model may create unintended information. In addition, there may be conditions (such as the number and format of tokens) on the prompts that can be input to the model, and it is not easy to generate prompts that take these conditions into account. However, in the aspect of this disclosure described above, prompts that take system information into consideration are generated by the device 10 without the user having to generate the prompts themselves. From this perspective as well, improvement information can be created efficiently according to the aspect of this disclosure.

[0066] The generation unit 17 generates prompts to cause the AI ​​model 41 to output improvement design information, which is a proposed improvement to the design information of the target system, as improvement information. This makes it possible to efficiently acquire improvement design information (specific improvement information), which is a proposed improvement to the design information of the target system.

[0067] The device 10 includes a label acquisition unit 13 that acquires multiple perspective labels indicating viewpoints for system improvement, and a determination unit 14 that determines the importance of each of the multiple perspective labels. The determination unit 14 determines the importance of each of the multiple perspective labels based on system information. The generation unit 17 generates prompts based on the importance of the multiple perspective labels. This makes it possible to efficiently acquire improvement information that appropriately considers viewpoints for system improvement.

[0068] Multiple perspective labels include multiple first labels based on perspectives related to system development. The information acquisition unit 12 acquires information indicating requirements for the development of the target system as development information. The decision unit 14 determines the importance level of each of the multiple first labels based on the information indicating requirements for the development of the target system. The generation unit 17 generates prompts based on the importance levels of the multiple first labels. This makes it possible to efficiently acquire improvement information that appropriately considers perspectives related to system development.

[0069] Multiple perspective labels include multiple second labels based on perspectives related to system operation. The information acquisition unit 12 acquires information indicating requirements for the operation of the target system as operational information. The decision unit 14 determines the importance level of each of the multiple second labels based on the information indicating requirements for the operation of the target system. The generation unit 17 generates prompts based on the importance levels of the multiple second labels. This makes it possible to efficiently acquire improvement information that appropriately considers perspectives related to system operation.

[0070] The device 10 includes a reference design information acquisition unit 15 that acquires reference design information, which is a sample of the system's design information. The generation unit 17 generates prompts that include instructions for the AI ​​model 41 to create improved design information, which is an improved version of the target system's design information, based on the reference design information. This makes it possible to provide improved design information with higher improvement accuracy that takes the reference design information into consideration.

[0071] The information acquisition unit 12 acquires multiple reference design information. The generation unit 17 generates prompts that include instructions for the AI ​​model 41 to create multiple improvement design information based on the multiple reference design information and to evaluate the created improvement design information. This makes it possible to provide useful information (evaluation results) when the user selects a specific improvement design information from the multiple improvement design information created.

[0072] The device 10 includes a persona creation unit 16 that creates setting information representing a persona, which is a virtual profile of a person. The generation unit 17 generates prompts based on the setting information. This allows, for example, when having the AI ​​model 41 evaluate multiple improvement pieces of information, to perform a consistent evaluation that reflects the values ​​and other factors included in the setting information representing the persona.

[0073] [Modifications] This disclosure is not limited to the above embodiments. For example, in step S17, the generation unit 17 may include the system information acquired in step S12 (information indicating requirements for the development of the target system and information indicating requirements for the operation of the target system) in the prompt without changing it into other information such as perspective labels (for example, the information itself). Also, the generation unit 17 may include the perspective labels acquired in step S13 and the importance level determined in step S14 in the prompt without incorporating them into other information such as setting information indicating a persona (for example, the information itself).

[0074] In step S17, the generation unit 17 may include in the prompt an instruction to the AI ​​model 41 to output at least one (for example, a predetermined number) of improvement design information (improvement design drawings) that is well evaluated (for example, has a high scoring score).

[0075] In step S12, the information acquisition unit 12 may acquire log data (operational information) of the target system specified by the user as system information. The information acquisition unit 12 may acquire log data of the target system from the database 30. In step S17, the generation unit 17 may generate a prompt based on the log data of the target system. For example, the generation unit 17 may include log data in the prompt, or it may include instructions in the prompt to cause the AI ​​model 41 to refer to the log data that is input to the AI ​​model 41 along with the prompt.

[0076] Operational information includes log data from the target system. This allows for the provision of highly accurate improvement information that reflects the log data.

[0077] The information creation system 1 is not limited to the configuration shown in Figure 3. In the configuration shown in Figure 3, the AI ​​model 41 may be located on the device 10. As another example, as shown in Figure 8, at least one of the functional elements of the device 10 may be located on the user terminal 20. The user terminal 20 may have the functions of the device 10 and function as the device 10. That is, the device 10 may be contained within the user terminal 20. This configuration can be realized, for example, by installing an application that performs the functions of the device 10 on the user terminal 20. In this configuration, the AI ​​model 41 is located on a network (e.g., the cloud), such as ChatGPT. In this configuration, the RAG application may be installed on the user terminal 20. The information (knowledge DB) that RAG accesses may reside on the network.

[0078] As an alternative configuration, as shown in Figure 9, not only the functional elements of the device 10 but also the AI ​​model 41 may be located on the user terminal 20. That is, the device 10 and the AI ​​model 41 may be contained within the user terminal 20. This configuration can be realized, for example, by installing an application on the user terminal 20 that executes the functions of the device 10 and an application that executes the functions of the AI ​​model 41. In this configuration, the AI ​​model 41 is located inside the user terminal 20, such as tsuzumi, which is a type of Large-Scale Language Model (LLM). In this configuration, the RAG application may be provided on the user terminal 20. The information (knowledge database) that the RAG accesses may reside inside the user terminal 20 and on the network, or at least one of the other. In any of the configurations in Figures 3, 8, and 9, the external server that can be the source of information (e.g., an internal server of a company) may reside externally (e.g., on the network).

[0079] The apparatus and method of this disclosure have the following configurations.

[0080] [1] An apparatus comprising: an information acquisition unit that acquires system information including at least one of development information relating to the development of the target system and operation information relating to the operation of the target system; and a generation unit that generates a prompt for instructing an AI model to output improvement information to improve the design of the target system, based on the system information.

[0081] [2] The apparatus according to [1], wherein the generation unit generates the prompt for the AI ​​model to output improved design information, which is an improved design information of the target system, as the improved information.

[0082] [3] The device described in [1] or [2], wherein the operational information includes log data of the target system.

[0083] [4] The apparatus according to any one of [1] to [3], further comprising: a label acquisition unit that acquires a plurality of perspective labels indicating perspectives on system improvement; and a determination unit that determines the importance of each of the plurality of perspective labels, wherein the determination unit determines the importance of each of the plurality of perspective labels based on the system information, and the generation unit generates the prompt based on the importance of the plurality of perspective labels.

[0084] [5] The apparatus according to [4], wherein the plurality of perspective labels include a plurality of first labels based on perspectives relating to the development of the system, the information acquisition unit acquires information indicating requirements for the development of the target system as development information, the decision unit determines the importance of each of the plurality of first labels based on the information indicating requirements for the development of the target system, and the generation unit generates the prompt based on the importance of the plurality of first labels.

[0085] [6] The apparatus according to [4], wherein the plurality of viewpoint labels include a plurality of second labels based on viewpoints relating to the operation of the system, the information acquisition unit acquires information indicating requirements for the operation of the target system as the operation information, the decision unit determines the importance of each of the plurality of second labels based on the information indicating requirements for the operation of the target system, and the generation unit generates the prompt based on the importance of the plurality of second labels.

[0086] [7] The apparatus according to any one of [1] to [6], further comprising a reference design information acquisition unit for acquiring reference design information which is a sample of system design information, wherein the generation unit generates the prompt which includes an instruction for the AI ​​model to create improved design information which is an improved version of the design information of the target system based on the reference design information.

[0087] [8] The apparatus according to [7], wherein the information acquisition unit acquires a plurality of reference design information, each of which is the reference design information, and the generation unit generates a prompt that includes an instruction to cause the AI ​​model to create a plurality of improved design information, each of which is the improved design information, based on the plurality of reference design information, and to evaluate the created plurality of improved design information.

[0088] [9] The apparatus according to any one of [1] to [8], further comprising a persona creation unit that creates setting information indicating a persona which is a hypothetical character, wherein the generation unit generates the prompt based on the setting information.

[0089]

[10] A method comprising the steps of: acquiring system information including at least one of development information relating to the development of a target system and operation information relating to the operation of the target system; and generating a prompt based on the system information for instructing an AI model to output improvement information for improving the design of the target system.

[0090] The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may be realized by combining the one or more devices with software.

[0091] Functions include, but are not limited to, judgment, decision, discrimination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0092] Figure 10 shows an example of the hardware configuration of the information creation system 1 (prompt generation system) according to this embodiment. The information creation system 1 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0093] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the information creation system 1 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.

[0094] Each function in the information creation system 1 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003.

[0095] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, at least one of the functional parts of the information creation system 1 described above may be implemented by the processor 1001.

[0096] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, at least one of the functional units of the information creation system 1 may be stored in the memory 1002 and implemented by a control program that runs on the processor 1001, and other functional blocks may be implemented similarly. The above-described processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0097] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out the row determination method according to one embodiment of the present disclosure.

[0098] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0099] The communication device 1004 is hardware (transmitting / receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include high-frequency switches, duplexers, filters, frequency synthesizers, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, at least one of the functional units of the information creation system 1 described above may be implemented by the communication device 1004. The communication device 1004 may be implemented with physically or logically separated transmitting and receiving units.

[0100] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0101] Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0102] Furthermore, the information creation system 1 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0103] Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.

[0104] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0105] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0106] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, by comparing with a predetermined value).

[0107] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0108] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0109] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0110] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0111] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0112] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc.

[0113] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information. For example, wireless resources may be indicated by an index.

[0114] The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way.

[0115] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

[0116] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term.

[0117] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0118] The terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0119] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0120] Any reference to elements using designations such as “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way.

[0121] Where the terms “include,” “including,” and their variations are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to be exclusive OR.

[0122] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0123] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0124] 1... Information creation system, 10... Device, 11... Reception unit, 12... Information acquisition unit, 13... Label acquisition unit, 14... Decision unit, 15... Reference design information acquisition unit, 16... Persona creation unit, 17... Generation unit, 18... Creation unit, 20... User terminal, 30... Database, 40... Server device, 41... AI model, 1001... Processor, 1002... Memory, 1003... Storage, 1004... Communication device, 1005... Input device, 1006... Output device, 1007... Bus, N... Communication network.

Claims

1. An apparatus comprising: an information acquisition unit that acquires system information including at least one of development information relating to the development of a target system and operational information relating to the operation of the target system; and a generation unit that generates a prompt for instructing an AI model to output improvement information to improve the design of the target system, based on the system information.

2. The apparatus according to claim 1, wherein the generation unit generates a prompt to cause the AI ​​model to output improved design information, which is an improved design information of the target system, as the improved information.

3. The apparatus according to claim 1, wherein the operational information includes log data of the target system.

4. The apparatus according to claim 1, further comprising: a label acquisition unit that acquires a plurality of perspective labels indicating perspectives on system improvement; and a determination unit that determines the importance of each of the plurality of perspective labels, wherein the determination unit determines the importance of each of the plurality of perspective labels based on the system information, and the generation unit generates the prompt based on the importance of the plurality of perspective labels.

5. The apparatus according to claim 4, wherein the plurality of perspective labels include a plurality of first labels based on perspectives relating to the development of the system, the information acquisition unit acquires information indicating requirements for the development of the target system as development information, the decision unit determines the importance of each of the plurality of first labels based on the information indicating requirements for the development of the target system, and the generation unit generates the prompt based on the importance of the plurality of first labels.

6. The apparatus according to claim 4, wherein the plurality of viewpoint labels include a plurality of second labels based on viewpoints relating to the operation of the system, the information acquisition unit acquires information indicating requirements for the operation of the target system as the operation information, the decision unit determines the importance of each of the plurality of second labels based on the information indicating requirements for the operation of the target system, and the generation unit generates the prompt based on the importance of the plurality of second labels.

7. The apparatus according to claim 1, further comprising a reference design information acquisition unit for acquiring reference design information which is a sample of system design information, wherein the generation unit generates a prompt which includes an instruction for the AI ​​model to create improved design information which is an improved version of the design information of the target system based on the reference design information.

8. The apparatus according to claim 7, wherein the information acquisition unit acquires a plurality of reference design information, each of which is the reference design information, and the generation unit generates a prompt that includes an instruction to cause the AI ​​model to create a plurality of improved design information, each of which is the improved design information, based on the plurality of reference design information, and to evaluate the created plurality of improved design information.

9. The apparatus according to claim 1, further comprising a persona creation unit that creates setting information representing a persona, which is a fictional character, wherein the generation unit generates the prompt based on the setting information.

10. A method comprising: acquiring system information including at least one of development information relating to the development of a target system and operational information relating to the operation of the target system; and generating a prompt based on the system information for instructing an AI model to output improvement information for improving the design of the target system.

Images