Cloud infrastructure construction support device, cloud infrastructure construction method, cloud infrastructure construction support system, and cloud infrastructure construction support program

Abstract

To provide a technology for simply generating a program code for construction of a cloud infrastructure.SOLUTION: A cloud infrastructure construction support device includes: a prompt generation unit which reads an infrastructure resource configuration diagram of a cloud environment, and generates parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for allowing a generation AI to generate a construction program code for constructing the infrastructure resource; and a code generation unit which generates a construction program code conforming to a code generation rule by using at least the prompt, the parameter data, a prescribed code generation rule, and the generation AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a cloud infrastructure construction support device, a cloud infrastructure construction method, a cloud infrastructure construction support system, and a cloud infrastructure construction support program. [Background technology]

[0002] Cloud systems, which build computer systems using infrastructure resources such as cloud server clusters installed on the Internet, are becoming increasingly popular. However, with cloud systems, it is not possible to build an environment by directly operating cloud server equipment; instead, it is necessary to write program code (construction program code) to build the environment and execute that code to build an execution environment according to the configuration diagram. This type of development is called IaC (Infrastructure as Code).

[0003] Patent document 1 describes a module provision system that includes a module selection receiving means for receiving a selection of at least one application development module from among a plurality of application development modules, an identification means for identifying another application development module associated with the selected application development module, and a provision means for providing the selected application development module and the identified other application development module to a developer. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-018527 Summary of the Invention [Problem to be solved by the invention]

[0005] The above system allows for the use of a combination of mutually supported application development modules when constructing a development environment to improve the efficiency of application development, but it does not provide any specific support for generating the IaC construction program code described above, and its effectiveness is limited.

[0006] The present invention has been made in view of the above points, and aims to provide a technology for easily generating program code for constructing a cloud infrastructure. [Means for solving the problem]

[0007] The present application includes a number of means for solving at least part of the above problems, examples of which are as follows.

[0008] In order to solve the above problems, a cloud infrastructure construction support device according to one embodiment of the present invention is characterized in that it comprises a prompt generation unit that reads a configuration diagram of infrastructure resources in a cloud environment and generates parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for causing a generation AI to generate construction program code for constructing the infrastructure resources, and a code generation unit that uses at least the prompt, the parameter data, a predetermined code generation rule, and the generation AI to generate the construction program code in accordance with the code generation rule.

[0009] In addition, in the above-mentioned cloud infrastructure construction support device, the prompt generation unit may serialize the configuration of the infrastructure resources included in the configuration diagram and convert it into specified text data to generate the parameter data.

[0010] The cloud infrastructure construction support device may further include a code verification unit that debugs the construction program code.

[0011] In addition, in the above-mentioned cloud infrastructure construction support device, the code verification unit may request a generation AI to correct any defects in the construction program code during the process of debugging the construction program code.

[0012] In addition, in the above-mentioned cloud infrastructure construction support device, the code verification unit may, in the process of debugging the construction program code, request the generation AI to modify the construction program code so that it includes measures to deal with errors that may occur when the construction program code is executed.

[0013] In addition, a cloud infrastructure construction support device according to another aspect of the present invention is characterized in that it includes a code generation unit that reads a configuration diagram of infrastructure resources in a cloud environment and predetermined code generation rules, and causes a generation AI to generate construction program code that constructs the infrastructure resources included in the configuration diagram in accordance with the code generation rules.

[0014] In addition, a cloud infrastructure construction support method according to another aspect of the present invention is a cloud infrastructure construction support method using a cloud infrastructure construction support device, wherein the cloud infrastructure construction support device performs a prompt generation step of reading a configuration diagram of infrastructure resources of a cloud environment and generating parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for causing a generation AI to generate construction program code for constructing the infrastructure resources, and a code generation step of using at least the prompt, the parameter data, a predetermined code generation rule, and the generation AI to generate the construction program code in accordance with the code generation rule.

[0015] In addition, a cloud infrastructure construction support system according to another aspect of the present invention is characterized in that it is performed by a computer: a prompt generation process that reads a configuration diagram of infrastructure resources in a cloud environment and generates parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for causing a generation AI to generate construction program code that constructs the infrastructure resources; and a code generation process that uses at least the prompt, the parameter data, predetermined code generation rules, and the generation AI to generate the construction program code in accordance with the code generation rules.

[0016] In addition, a cloud infrastructure construction support program according to another aspect of the present invention is a cloud infrastructure construction support program that causes an information processing device to function as a cloud infrastructure construction support device, wherein the information processing device has a processor, and is characterized in that the processor is caused to perform a prompt generation step of reading a configuration diagram of infrastructure resources of a cloud environment and generating parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for causing a generation AI to generate construction program code that constructs the infrastructure resources, and a code generation step of generating the construction program code in accordance with the code generation rules using at least the prompt, the parameter data, predetermined code generation rules, and the generation AI. [Effects of the Invention]

[0017] According to the present invention, a technique for easily generating program code for constructing a cloud infrastructure can be provided.

[0018] Problems, configurations, effects, and the like other than those described above will become clear from the following description of the embodiments. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is a diagram illustrating an example of an overview of a cloud infrastructure construction support system. [Figure 2]FIG. 10 is a diagram illustrating an example of configuration diagram data. [Figure 3] FIG. 10 is a diagram showing an example of text-converted configuration diagram data. [Figure 4] FIG. 10 is a diagram illustrating an example of resource parameters. [Figure 5] FIG. 10 is a diagram illustrating an example of a code generation rule. [Figure 6] FIG. 10 is a diagram illustrating an example of a prompt. [Figure 7] FIG. 10 is a diagram illustrating an example of a construction program code. [Figure 8] FIG. 2 illustrates an example of a hardware configuration of a cloud infrastructure construction support device. [Figure 9] FIG. 10 is a diagram illustrating an example of a flow of a construction program code generation process. [Figure 10] FIG. 10 illustrates an example of a flow of an automatic debugging process. [Figure 11] FIG. 10 illustrates an example of an error countermeasure prompt. DETAILED DESCRIPTION OF THE INVENTION

[0020] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0021] FIG. 1 is a diagram illustrating an example of an overview of a cloud infrastructure construction support system. In this example, the cloud infrastructure construction support system 1 is illustrated as targeting infrastructure construction support work for existing cloud infrastructure services. The person constructing the infrastructure environment refers to a person who prepares the operating environment for applicable business applications, such as a system engineer. The business content for which the system is being constructed may also include various business applications or entertainment applications such as games. The person constructing the infrastructure environment does not necessarily have to be a system engineer in the strict sense, but may be an amateur programmer, etc.

[0022] In cloud infrastructure construction support system 1, a builder inputs configuration information of the target system's infrastructure from builder terminal 100 to cloud infrastructure construction support device 300 via network 50, and cloud infrastructure construction support device 300 automatically generates appropriate construction program code. The builder can build infrastructure using IaC by executing the generated construction program code on the cloud infrastructure service.

[0023] Furthermore, it is desirable that the builder terminal 100 is an information processing device such as a personal computer, smartphone, PDA (Personal Digital Assistant), or tablet terminal that can communicate with the cloud infrastructure construction support device 300 via the network 50. The functions of the builder terminal 100 and the cloud infrastructure construction support device 300 are realized by software that runs on an OS (Operating System).

[0024] The builder terminal 100 is basically an information processing device used by the builder himself, or an information processing device loaned for business purposes by the company to which the builder belongs.

[0025] The network 50 is, for example, the Internet or an intranet. However, the network 50 is not limited to this and may also be a WAN (Wide Area Network), a mobile phone network, or a communication network that combines these. Alternatively, the network 50 may be a VPN (Virtual Private Network) on a wireless communication network such as a mobile phone communication network.

[0026] The cloud infrastructure construction support device 300 is an information processing device such as a server device. The cloud infrastructure construction support device 300 and the builder terminal 100 are connected via a network 50. The cloud infrastructure construction support device 300 can also use the generation AI service 200 via the network 50. The generation AI service 200 is a service that allows the use of generation AI via the network 50, and provides objects (text, audio, video, etc.) generated by the generation AI in accordance with a predetermined API (Application Programming Interface) or command. However, the use of the generation AI service 200 is not limited to this, and for example, the cloud infrastructure construction support device 300 itself may have an environment in which the generation AI can be executed.

[0027] The builder terminal 100 includes at least a processing unit 120, a display unit 130, an input unit 131, and a communication unit 140. The processing unit 120 includes a browser unit 121, and realizes a so-called web browser function. For example, the processing unit 120 transmits a predetermined URL (Uniform Resource Locator) to the cloud infrastructure construction support device 300, displays the returned HTML (HyperText Markup Language) page, and controls viewing and input.

[0028] The cloud infrastructure construction support device 300 includes a storage unit 310, a processing unit 320, and a communication unit 340. The storage unit 310 includes configuration diagram data 311, text configuration diagram data 312, resource parameters 313, code generation rules 314, prompts 315, and construction program code 316.

[0029] 2 is a diagram illustrating an example of configuration diagram data. The configuration diagram data 311 stores a configuration diagram that shows design information of infrastructure resources to be constructed in a predetermined description format. For example, the configuration diagram data 311 shows that a cloud service entity 311a, a private virtual network 311b provided within the cloud service entity 311a, an availability zone 311c provided in the private virtual network 311b, a public subnet 311d provided in the availability zone 311c, a security group 311e provided in the public subnet 311d, and a virtual server service 311f included in the security group 311e are provided.

[0030] The private virtual network 311b is also called a VPC (Virtual Private Cloud). The availability zone 311c is also called an AZ (Availability Zone). The security group 311e is also called an SG (Security Group). The virtual server service 311f is also called an EC2 (Elastic Compute Cloud).

[0031] The configuration diagram data 311 also indicates that the private virtual network 311b can communicate with the Internet via an Internet gateway 311g (such as a firewall), and that the virtual server service 311f is assigned a virtual IP address 311h (Elastic IP: EIP). In other words, the configuration diagram data 311 indicates the configuration of infrastructure resources used as a so-called Web server.

[0032] 3 is a diagram showing an example of text configuration diagram data. The text configuration diagram data 312 is obtained by serializing the configuration shown in the configuration diagram data 311 and re-describing it in text in a predetermined format (JSON format in FIG. 2).

[0033] 4 is a diagram showing an example of resource parameters. The resource parameters 313 are information (parameter data) extracted as parameters from variable information specifying the performance, type, name, etc. set for a resource in the configuration shown in the configuration diagram data 311.

[0034] FIG. 5 is a diagram showing an example of code generation rules. The code generation rules 314 are a document that describes the rules to be followed when writing construction program code. Typically, in software development, many code writers (programmers) are involved, so code writing rules are often established to ensure quality, readability, and ease of maintenance. The code generation rules 314 are read by a generation AI (Artificial Intelligence) to ensure that the AI ​​also follows these code writing rules. The code generation rules 314 can be used as is (without rewriting) as a document file written in a natural language that can be understood by the code writer.

[0035] Figure 6 is a diagram showing an example of a prompt. Prompt 315 is a prompt that the code generation unit 324 uses to cause the generation AI of the generation AI service 200 to generate construction program code. Prompt 315 includes the role or position of the generation AI, prerequisites, constraints, output conditions, instructions, etc. For example, prompt 315 includes, as instructions, elements such as the position of a programmer, an instruction to write program code, referencing a parameter file to include parameters, and complying with code generation rules.

[0036] The generative AI includes a generative AI that uses a large-scale language model. The generative AI is a trained model, such as GPT-4, in which a large-scale language model using a neural network (NN) is trained by machine learning or deep learning using language data in advance. The generative AI is not limited to a neural network (NN), and other well-known methods may also be used. It is also desirable to use a generative AI that has been tuned using few-shot learning, fine tuning, or the like to achieve high accuracy in program code generation.

[0037] 7 is a diagram showing an example of the construction program code. The construction program code 316 is obtained as a result of code generation by the code generation unit 324. By executing the construction program code 316, an environment including the infrastructure resources configured by the configuration diagram data 311 is constructed, thereby realizing IaC.

[0038] Returning to the explanation of Fig. 1, the processing unit 320 realizes application functions and includes a configuration diagram editing unit 321, a configuration diagram text generating unit 322, a prompt generating unit 323, a code generating unit 324, and a code verifying unit 325.

[0039] The configuration diagram editing unit 321 is a so-called visual editor that provides a WYSIWYG UI (user interface) to the builder terminal 100 and enables the builder to visually perform operations such as creating and editing the configuration diagram data 311. Note that an existing editor may be used as the configuration diagram editing unit 321.

[0040] When the configuration diagram text generation unit 322 receives input of the configuration diagram data 311, it serializes the configuration of the infrastructure resources included in the configuration diagram and converts it into predetermined text data to generate text configuration diagram data 312, and also extracts parameter information to generate resource parameters 313.

[0041] The prompt generation unit 323 generates a prompt for causing the configuration diagram text generation unit 322 to generate textual configuration diagram data 312 and resource parameters 313, and for causing the generation AI to generate construction program code for constructing infrastructure resources. Specifically, in the process of reading the configuration diagram data 311, the prompt generation unit 323 passes the configuration diagram data 311 to the configuration diagram text generation unit 322 to acquire the textual configuration diagram data 312 and resource parameters 313. Then, the prompt generation unit 323 generates a prompt 315 that includes the acquired textual configuration diagram data 312, resource parameters 313, and code generation rules 314 as conditions to be satisfied.

[0042] The code generation unit 324 generates a construction program code 316 in accordance with the code generation rules 314 using at least the prompt 315, the resource parameters 313, the code generation rules 314, and the generation AI.

[0043] The code verification unit 325 debugs the construction program code 316. Furthermore, in the process of debugging the construction program code 316, the code verification unit 325 requests the generation AI to correct any defects in the construction program code 316. Specifically, the code verification unit 325 causes the generation AI to correct the construction program code 316 so as to include measures for errors that occur when the construction program code 316 is executed.

[0044] The communication unit 340 communicates with other devices via wired or wireless communication. For example, the communication unit 340 communicates via various wired communication cables such as a wired LAN (Local Area Network) cable or via radio waves of a wireless LAN.

[0045] 8 is a diagram showing an example of the hardware configuration of a cloud infrastructure construction support device. The cloud infrastructure construction support device 300 has a processor 11, a memory 12, a storage 13, a display 15, and a communication device 16, and each component is connected by a bus. The power source may be power transmitted via a power transmission line, power extracted from a primary battery, or power extracted from a rechargeable secondary battery, and may be replaceable when worn out or deteriorated.

[0046] The processor 11 is an arithmetic device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), and executes processing in accordance with a program recorded in the memory 12 or the storage 13. In the cloud infrastructure construction support device 300, processing is performed by the processor 11 operating in accordance with a program read onto the memory 12 or the storage 13. The processing unit 320, the configuration diagram editing unit 321, the configuration diagram text generating unit 322, the prompt generating unit 323, the code generating unit 324, and the code verifying unit 325 each realize their respective functions by the processor 11 executing the program.

[0047] The memory 12 is a storage device such as RAM (Random Access Memory) or flash memory, and functions as a storage area from which programs and data are temporarily read. The storage 13 is a writable and readable storage device. The functions of the storage unit 310 are realized by the memory 12 or the storage 13. Note that the functions of the storage unit 310 may also be realized by a storage device connected via the communication device 16.

[0048] The display 15 is a device that provides an interface for input and output, and outputs to the display 15 and accepts input via a touch panel, keyboard, or mouse.

[0049] The communication device 16 is an interface for connecting the cloud infrastructure construction support device 300 to an external device for communication. For example, the communication device 16 performs wireless communication using an antenna that can use a predetermined radio wave (for example, 5 GHz band, 2.4 GHz band, etc.) that establishes a connection with the builder terminal 100 according to the Wi-Fi standard.

[0050] The processing of each component of cloud infrastructure construction support device 300 may be executed by one piece of hardware or by multiple pieces of hardware. Furthermore, the processing of each component of cloud infrastructure construction support device 300 may be realized by one program or by multiple programs.

[0051] The builder terminal 100 has roughly the same hardware configuration as the cloud infrastructure building support device 300, but like a general personal computer or smartphone, it often includes input / output devices such as a touch panel display and a microphone.

[0052] Next, we will explain the processing flow of the cloud infrastructure construction support system 1. Figure 9 is a diagram showing an example of the flow of construction program code generation processing. The processing in this flow diagram is a flow when the cloud infrastructure construction support device 300 automatically generates construction program code in response to an instruction from the builder terminal 100.

[0053] First, the configuration diagram editing unit 321 of the cloud infrastructure construction support device 300 edits the configuration diagram (step S01). Specifically, the configuration diagram editing unit 321 provides the builder terminal 100 with a function for editing the configuration diagram using a visual editor, and allows the builder to edit the configuration diagram of infrastructure resources in the cloud environment. The edited configuration diagram is stored in the configuration diagram data 311.

[0054] Then, the prompt generation unit 323 instructs the configuration diagram text generation unit 322 to convert the configuration diagram into text (step S02). Specifically, upon receiving the instruction, the configuration diagram text generation unit 322 reads the configuration diagram data 311, serializes the configuration of the infrastructure resources included in the configuration diagram, and converts it into predetermined text data (for example, JSON or XML) to generate text-converted configuration diagram data 312.

[0055] Then, the prompt generation unit 323 instructs the configuration diagram text generation unit 322 to generate resource parameters (step S03). Specifically, upon receiving the instruction, the configuration diagram text generation unit 322 extracts parameter information from the text configuration diagram data 312 and generates resource parameters 313 for each type of infrastructure resource included in the configuration diagram data 311.

[0056] Then, the prompt generation unit 323 generates a prompt for causing the generation AI to generate a construction program code for constructing the infrastructure resource (step S04). Specifically, the prompt generation unit 323 generates a prompt 315 that includes the acquired text configuration diagram data 312, resource parameters 313, and code generation rules 314 as conditions to be satisfied.

[0057] Then, the code generation unit 324 executes the prompt (step S05). Specifically, the code generation unit 324 uses at least the prompt 315 generated by the prompt generation unit 323, the resource parameters 313, the code generation rules 314, and the generation AI to generate the construction program code 316 in accordance with the code generation rules 314 in accordance with the instructions of the prompt 315.

[0058] Then, the code verification unit 325 performs automatic debugging of the construction program code (step S06). Specifically, in the process of debugging the construction program code 316, the code verification unit 325 requests the generation AI to correct any defects in the construction program code 316. Specifically, the code verification unit 325 causes the generation AI to correct the construction program code 316 so as to include measures for errors that occur when the construction program code 316 is executed.

[0059] Then, the code generation unit 324 outputs the construction program code 316 (step S07). The above is an example of the flow of the construction program code generation process. According to this example of the flow of the construction program code generation process, the builder can generate executable construction program code simply by drawing a configuration diagram of infrastructure resources using a visual editor.

[0060] 10 is a diagram showing an example of the flow of the automatic debugging process. The automatic debugging process starts in step S06 of the construction program code generation process.

[0061] First, the code verification unit 325 executes the construction program code 316 using the generated construction program code 316 and the resource parameters 313 (step S061). Specifically, the code verification unit 325 embeds parameter data defined in the resource parameters 313 into the construction program code 316 and executes it in an execution environment. Here, the code verification unit 325 uses a software execution environment provided by a cloud service provider or the like as the execution environment.

[0062] Then, the code verification unit 325 determines whether an error has occurred or whether the number of times an error has occurred is less than N (N is a predetermined natural number) (step S062).

[0063] If no error has occurred or if the number of errors is N or more ("No" in step S062), the code verification unit 325 outputs an error report if there is an unresolved error (step S066).

[0064] If an error has occurred or the number of times an error has occurred is less than N ("Yes" in step S062), the code verification unit 325 uses a prompt to instruct the generation AI on how to deal with the error that has occurred (step S063). That is, the generation AI is prompted to indicate the corrections to be made to the construction program code 316.

[0065] Then, the code verification unit 325 updates the construction program code 316 with the corrected content (step S064).

[0066] Then, the code verification unit 325 increments the number of error occurrences (by adding 1) (step S065), and returns the control to step S061.

[0067] The above is an example of the flow of the automatic debugging process. According to this example of the flow of the automatic debugging process, it is possible to have the generation AI automatically attempt to debug the construction program code 316 generated by the code generation unit 324, thereby improving the quality of the construction program code 316, increasing the debugging speed, and reducing the number of development steps.

[0068] 11 is a diagram showing an example of an error countermeasure prompt 400. The error countermeasure prompt 400 is used when the code verification unit 325 instructs the generation AI to take measures against the error that has occurred in step S063 of the automatic debugging process.

[0069] The error countermeasure prompt 400 includes the role or position of the generative AI, prerequisites, constraints, output conditions, commands, etc. For example, the error countermeasure prompt 400 includes, as commands, elements such as the position of the programmer, a command to correct the program code, and the details of the error that occurred. Note that the generative AI includes generative AI that uses a large-scale language model.

[0070] The generation AI, like the generation AI used by the code generation unit 324 to generate the construction program code, is a trained model, such as GPT-4, in which a large-scale language model using a neural network (NN) is trained by machine learning or deep learning using language data in advance. The generation AI is not limited to a neural network (NN), and other well-known methods may also be used. Furthermore, it is desirable to use a generation AI that has been tuned using few-shot learning, fine tuning, or the like to achieve high accuracy in program code generation.

[0071] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described examples of the embodiments and includes various modifications. For example, in the above-described embodiment, in the process of generating the construction program code, a prompt is configured based on the resource parameters 313 and the code generation rules 314 to generate the construction program code, but the present invention is not limited to this.

[0072] For example, the construction program code may be generated directly from the configuration diagram without generating a prompt, etc. Specifically, in step S02, the code generation unit 324 may read the configuration diagram data 311 of the infrastructure resources of the cloud environment and the code generation rules 314, and cause the generation AI to generate construction program code that constructs the infrastructure resources included in the configuration diagram in accordance with the code generation rules. In this way, the generation AI can be made to generate the construction program code more easily.

[0073] The above-described exemplary embodiments have been described in detail to facilitate understanding of the present invention, and the present invention is not limited to those including all of the components described herein. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment. It is also possible to add the configuration of another embodiment to the configuration of one embodiment. It is also possible to add, delete, or replace part of the configuration of each embodiment with other configurations. Furthermore, some or all of the above-described configurations, functions, processing units, processing means, etc. may be realized in hardware, for example, by designing them as integrated circuits. Furthermore, the control lines and information lines in the figures are those considered necessary for explanation, and are not necessarily all shown. It is also possible to consider that almost all of the components are interconnected. [Explanation of symbols]

[0074] 1···Cloud infrastructure construction support system, 50···Network, 100···Constructor terminal, 120···Processing unit, 121···Browser unit, 130···Display unit, 131···Input unit, 140···Communication unit, 300···Cloud infrastructure construction support device, 310···Memory unit, 311···Configuration diagram data, 312···Textualized configuration diagram data, 313···Resource parameters, 314···Code generation rules, 315···Prompt, 316···Construction program code, 320···Processing unit, 321···Configuration diagram editing unit, 322···Configuration diagram text generation unit, 323···Prompt generation unit, 324···Code generation unit, 325···Code verification unit, 340···Communication unit.

Claims

1. a prompt generation unit that reads a configuration diagram of infrastructure resources of a cloud environment and generates parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for causing a generation AI to generate a construction program code that constructs the infrastructure resources; a code generation unit that uses at least the prompt, the parameter data, a predetermined code generation rule, and the generation AI to generate the construction program code in accordance with the code generation rule; A cloud infrastructure construction support device comprising:

2. 2. The cloud infrastructure construction support device according to claim 1, the prompt generation unit serializes the configuration of the infrastructure resource included in the configuration diagram and converts it into predetermined text data to generate the parameter data. A cloud infrastructure construction support device characterized by:

3. 3. The cloud infrastructure construction support device according to claim 1, a code verification unit that debugs the construction program code; A cloud infrastructure construction support device comprising:

4. The cloud infrastructure construction support device according to claim 3, The code verification unit requests a generation AI to correct defects in the construction program code in the process of debugging the construction program code. A cloud infrastructure construction support device characterized by:

5. 5. The cloud infrastructure construction support device according to claim 4, the code verification unit, in the process of debugging the construction program code, requests the generation AI to modify the construction program code so as to include a countermeasure for an error that occurs when the construction program code is executed; A cloud infrastructure construction support device characterized by:

6. a code generation unit that reads a configuration diagram of infrastructure resources of a cloud environment and predetermined code generation rules, and causes a generation AI to generate construction program code that constructs the infrastructure resources included in the configuration diagram in accordance with the code generation rules; A cloud infrastructure construction support device comprising:

7. A cloud infrastructure construction support method using a cloud infrastructure construction support device, comprising: The cloud infrastructure construction support device includes: a prompt generation step of reading a configuration diagram of infrastructure resources of a cloud environment and generating parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for causing a generation AI to generate a construction program code for constructing the infrastructure resources; a code generation step of generating the construction program code in accordance with the code generation rules by using at least the prompt, the parameter data, a predetermined code generation rule, and the generation AI; A cloud infrastructure construction support method characterized by carrying out the steps of:

8. A prompt generation process that reads a configuration diagram of infrastructure resources in a cloud environment and generates parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for causing a generation AI to generate a construction program code that constructs the infrastructure resources; a code generation process that uses at least the prompt, the parameter data, a predetermined code generation rule, and the generation AI to generate the construction program code in accordance with the code generation rule; A cloud infrastructure construction support system characterized by performing the above steps by a computer.

9. A cloud infrastructure construction support program that causes an information processing device to function as a cloud infrastructure construction support device, The information processing device includes a processor, the processor, a prompt generation step of reading a configuration diagram of infrastructure resources of a cloud environment and generating parameter data for each type of infrastructure resource included in the configuration diagram and a prompt for causing a generation AI to generate a construction program code for constructing the infrastructure resources; a code generation step of generating the construction program code in accordance with the code generation rules by using at least the prompt, the parameter data, a predetermined code generation rule, and the generation AI; A cloud infrastructure construction support program characterized by implementing the following.

Images