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

Abstract

To provide a data processing device, a data processing system, a data processing method, and a program capable of performing safety management suited to a construction site.SOLUTION: A data processing device comprises: an acquisition part 292 for acquiring user input received by a smart device as requested information; a processing part 294 for performing specification processing using a retrieval program and a generative AI model; and an output part 296 for transmitting the result of the specification processing to the smart device.SELECTED DRAWING: Figure 4

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in order to achieve zero work-related accidents, thorough safety measures must be implemented at construction sites, but conventional technologies leave room for improvement in terms of implementing safety management at construction sites. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein is a data processing device that includes an acquisition unit that acquires requirement information requesting anticipated risks for work content at a construction site, a processing unit that extracts information that is likely to correspond to the requirement information acquired by the acquisition unit from a database that pre-stores information on past construction work, uses the extracted information and the requirement information to generate input information to be input into a generative AI model that can generate data according to input data, and performs specific processing to generate response information for the requirement information based on the output result of the generative AI model, and an output unit that outputs the response information generated by the processing unit.

[0006] A second aspect of the technology disclosed herein is a data processing method in which a computer obtains requirement information requesting anticipated risks for work content at a construction site, extracts information that is likely to correspond to the requirement information from a database that pre-stores information on past construction work, uses the extracted information and the requirement information to generate input information to be input into a generative AI model that can generate data according to the input data, and generates and outputs response information to the requirement information based on the output results of the generative AI model.

[0007] A third aspect of the technology disclosed herein is a program for causing a computer to execute a process of obtaining requirement information requesting anticipated risks for work content at a construction site, extracting information that likely corresponds to the requirement information from a database that pre-stores information on past construction work, using the extracted information and the requirement information to generate input information to be input into a generative AI model that can generate data according to the input data, and generating and outputting response information to the requirement information based on the output results of the generative AI model. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Figure 2] FIG. 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device. [Figure 3]FIG. 10 is a block diagram showing an outline of a specification process. [Figure 4] FIG. 10 is a diagram illustrating a specific example of a specific process. [Figure 5] 2 is a block diagram illustrating a schematic functional configuration of a specific processing unit of the data processing device. FIG. [Figure 6] 10 is a flowchart illustrating an example of an operational flow of a specific process performed by the data processing device. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. An example of the smart device 14 is a tablet terminal or a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure, and the smart device 14 is an example of a "smart device" according to the technology of the present disclosure.

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

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to a person by outputting the data in a form of expression that the person can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

[0025] A search program 58A and a generative AI model 58B are stored in the storage 32. The search program 58A and the generative AI model 58B are used by the specific processing unit 290.

[0026] The generative AI model 58B is a so-called generative AI (Artificial Intelligence). An example of the generative AI model 58B is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generative AI models. The generative AI model 58B is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the generative AI model 58B, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The generative AI model 58B performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0027] For example, the search program 58A and the generative AI model 58B may use "Azure Cognitive Search" and "Azure Open AI" provided by Microsoft. The former is a cloud-based search service, and the latter is an AI service provided on the cloud service provided by Microsoft.

[0028] Meanwhile, in the smart device 14, the processor 46 performs a reception output process. A reception output program 62 is stored in the storage 50. The reception output program 62 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 62 from the storage 50 and executes the read reception output program 62 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48. Note that, for example, an application for accepting input of request information from a user is applied as the reception output program 62. The smart device 14 accepts input of the request information from the user and accepts and presents a response to the request information from the data processing device 12. As an example, the smart device 14 accepts the request information from the user in a chat format and presents a response to the request information.

[0029] In this embodiment, safety measures are necessary at construction sites to achieve zero work-related accidents. However, the current situation where skilled workers are increasingly dependent on tacit knowledge and risk prediction activities are becoming increasingly monotonous is recognized as an issue, and a data processing device 12 is realized that can point out anticipated risks at the site.

[0030] The data processing device 12 according to this embodiment performs a specific process to output anticipated risks and accident cases as voice and / or text from information on past construction projects, such as implementation reports from past construction projects and accident cases that occurred at similar sites. This makes it possible to take measures against risks that workers have overlooked, and realizes safety management without omissions or oversights, free from reliance on workers' tacit knowledge.

[0031] Next, the processing of the identification processing unit 290 when the data processing device 12 performs identification processing to generate anticipated risks and accident cases at a construction site will be described.

[0032] In this embodiment, an application for generating and presenting anticipated risks for work content at construction sites such as building construction sites and base station telecommunications equipment construction sites is pre-installed on the smart device 14.

[0033] In the identification process of this embodiment, the smart device 14 receives request information requesting anticipated risks for the work content, and uses a search program 58A to extract information likely to match the acquired request information from a pre-registered database 24. The request information is then generated as a prompt together with the extracted information and input to the generation AI model 58B. Based on the output result of the generation AI model 58B, a process is performed to generate response information for the request information. Data to be used for searching, such as information on past construction projects, is pre-registered in the database 24. For example, information such as previously created risk assessment implementation reports and accident data, such as reports and case studies of accidents that occurred on-site, is pre-registered in the database 24.

[0034] 3, the identification process acquires requested information 70 input by the user from an application installed on the smart device 14. Then, the search program 58A extracts information that may correspond to the requested information 70 from the database 24 (relevant information extraction 72).

[0035] In addition, using the information obtained from the database 24 and the request information 70 obtained from the smart device 14, a prompt is generated as input information to be input to a generation AI model 58B that can generate data according to the input data (prompt generation 74), the generated prompt is input to the generation AI model 58B, and a process is performed to generate answer information corresponding to the request information 70 based on the output result of the generation AI model 58B (answer generation 76).

[0036] Then, the response information generated by the identification process is output to the application of the smart device 14, thereby presenting the user with the anticipated risks for the work content and examples of accidents that have occurred in similar construction projects.

[0037] A specific example of the processing performed by the specific processing unit 290 of the data processing device 12 will be described below. Fig. 4 is a diagram showing a specific example of the specific processing.

[0038] First, as shown in Fig. 4, request information is input to the smart device 14. Specifically, request information 70 including requests for anticipated risks at the construction site and details of the construction work, such as "Please tell me about the anticipated risk factors in the following work: concrete pillar erection work," is input to the application of the smart device 14.

[0039] The identification process, in conjunction with the process of searching for information likely to match the request information 70, generates input information to be input to the generation AI model 58B, and generates answer information using the output result of the generation AI model 58B.

[0040] Specifically, the identification process acquires the request information 70, and searches for and extracts information that is likely to correspond to the work content from information on past construction work (for example, risk assessment implementation reports 24A and accident case studies 24B) that has been stored in advance in the database 24. The search for information that is likely to correspond to the work content involves, for example, extracting predetermined words, such as words that represent the work content, that are included in the request information, and extracting information on at least one of the risk assessment implementation reports 24A and accident case studies 24B that includes the extracted words from the database 24 as information that is likely to correspond to the work content.

[0041] Furthermore, the specific process generates a prompt to be input to the generation AI model 58B using the request information 70, and inputs the generated prompt to the generation AI model 58B. An example of the generated prompt is a prompt such as "Generate an answer to the request information 70 using the information extracted from the database 24."

[0042] The identification process then inputs the information extracted from the database 24 and the generated prompt into the generation AI model 58B, and generates answer information for the request information 70 based on the output result of the generation AI model 58B. An example of the answer information, as shown in FIG. 4, is "The following risks are considered in concrete pillar erection work. Past accident case: In July 2023, a concrete pillar fell during lifting work. The cause of the accident was the use of lifting equipment. Risk reduction measures: In pillar erection work, care must be taken when lifting loads. Double-checking when using lifting equipment is effective." The answer information generated includes anticipated risks at the construction site and examples of accidents in similar construction work, and is output to the smart device 14.

[0043] Next, a description will be given of the specific processing unit 290 of the data processing device 12. Fig. 5 is a block diagram showing a schematic functional configuration of the specific processing unit 290 of the data processing device 12.

[0044] As shown in FIG. 5, the specific processing unit 290 includes an acquisition unit 292, a processing unit 294, and an output unit 296.

[0045] The acquisition unit 292 acquires user input received by the smart device 14 as request information 70. Specifically, the acquisition unit 292 acquires user-input data of at least one of the user's text, voice, and image received by the smart device 14. For example, the acquisition unit 292 acquires at least one of the user's text, voice, and image data input into an application such as a chat application as request information 70.

[0046] The processing unit 294 performs a specification process using the search program 58A and the generation AI model 58B. Specifically, as described above, the specification process generates input information to be input to the generation AI model 58B in cooperation with a process of searching the database 24, which has information likely to correspond to the requested information stored in advance, and generates answer information using the output result of the generation AI model 58B.

[0047] The output unit 296 transmits answer information, which is the result of the specific processing, to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. By outputting the result of the specific processing in a form that the user can perceive (for example, voice and / or text), the data is presented to the user in terms of anticipated risks at the construction site and examples of accidents that have occurred in similar construction projects. Visual information such as text and images may be displayed on the display 40A, or voice may be output from the speaker 40B.

[0048] Next, a description will be given of the operation of the data processing system 10. Fig. 6 is a flowchart showing an example of the operational flow of specific processing by the data processing device 12.

[0049] An example of the flow of the identification process will be described with reference to Fig. 6. The flow of the identification process shown in Fig. 6 is an example of a "data processing method" according to the technique of the present disclosure.

[0050] In step S100, the acquisition unit 292 determines whether or not the request information 70 has been input to the smart device 14. If the request information 70 has been input to an application installed in the smart device 14, the determination is affirmative and the process proceeds to step S102, but if an operation other than inputting the request information 70 has been performed, the determination is negative and the specific process is terminated, and processing according to the operation is performed.

[0051] In step S102, the acquisition unit 292 acquires the request information 70 from the smart device 14, and the process proceeds to step S104. That is, the acquisition unit 292 acquires the request information 70 input to the smart device 14, such as "Please tell me the expected risk factors in the following work: concrete pillar erection work."

[0052] In step S104, the processing unit 294 searches and extracts information that is likely to correspond to the request information 70 from the database 24, and proceeds to step S106. For example, from information on past construction work, such as risk assessment implementation reports 24A and accident cases 24B, which are stored in advance in the database 24, information that includes predetermined words contained in the request information 70 is searched and extracted as information that is likely to correspond to the work content.

[0053] In step S106, the processing unit 294 generates a prompt using the request information 70, and the process proceeds to step S108. For example, the processing unit 294 generates a prompt such as "Generate a response to the request information 70 using the information extracted from the database 24."

[0054] In step S108, the processing unit 294 inputs the information extracted from the database 24 and the prompt into the generative AI model 58B, and the process proceeds to step S110.

[0055] In step S110, the processing unit 294 acquires the output result of the generative AI model 58B, and the process proceeds to step S112.

[0056] In step S112, the output unit 296 generates answer information and outputs it to the smart device 14, thereby completing the series of identification processes. For example, as shown in FIG. 4, the output unit 296 generates answer information including anticipated risks and examples of accidents in similar construction projects, such as "The following risks are considered in concrete pillar erection work. Past accident case: In July 2023, a concrete pillar fell during lifting work. The cause of the accident was the use of lifting equipment. Risk reduction measures: In pillar erection work, care must be taken when lifting loads. Double-checking when using lifting equipment is effective." and outputs the generated answer information to the smart device 14.

[0057] By performing this identification process, the smart device 14 displays response information, allowing the user to check anticipated risks at the construction site and examples of accidents in similar construction projects. This makes it possible to take measures against risks that workers have overlooked, and enables safety management without omissions or oversights that is not dependent on the workers' tacit knowledge, thereby enabling safety management suited to the construction site.

[0058] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0059] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0060] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0061] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0062] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0063] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0064] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[0065] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0066] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0067] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0068] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0069] The following additional notes are provided regarding the above-described embodiments.

[0070] <Appendix 1> an acquisition unit that acquires requirement information that requests anticipated risks for work content at a construction site; a processing unit that extracts information that is likely to correspond to the request information acquired by the acquisition unit from a database that stores information on past construction projects in advance, generates input information to be input to a generation AI model that can generate data according to input data using the extracted information and the request information, and performs a specific process to generate response information for the request information based on the output result of the generation AI model; an output unit that outputs the answer information generated by the processing unit; 2. A data processing device comprising:

[0071] <Appendix 2> The data processing device according to claim 1, wherein the processing unit extracts information that is likely to correspond to the requested information from at least one of accident reports and accident cases as information on the past construction work.

[0072] <Appendix 3> 3. The data processing device according to claim 2, wherein the processing unit extracts information including a predetermined word from the one piece of information.

[0073] <Appendix 4> 4. The data processing device according to claim 1, wherein the processing unit generates, as answer information, risks expected at the construction site and accident cases in similar construction projects.

[0074] <Appendix 5> The computer Obtaining requirements information that requires anticipated risks for work content at the construction site, Extracting information that is likely to correspond to the requested information from a database that stores information on past construction projects in advance; Using the extracted information and the request information, generate input information to be input to a generative AI model capable of generating data according to the input data; A data processing method that generates and outputs response information to the request information based on the output result of the generative AI model.

[0075] <Appendix 6> On the computer, Obtaining requirements information that requires anticipated risks for work content at the construction site, Extracting information that is likely to correspond to the requested information from a database that stores information on past construction projects in advance; Using the extracted information and the request information, generate input information to be input to a generative AI model capable of generating data according to the input data; A program for executing a process of generating and outputting response information to the request information based on the output result of the generation AI model. [Explanation of symbols]

[0076] 10 Data Processing System 12 Data Processing Device 14 Smart Devices 24 databases 24A Risk Assessment Implementation Report 24B Accident Cases 56 Specific Processing Program 58A Search Program 58B Generative AI Model 60 Reception Output Program 70 Request information 72 Extract relevant information 74 Prompt Generation 76 Answer generation 290 Special Processing Department 292 Acquisition Department 294 Processing Section 296 Output Section< / url:>

Claims

1. an acquisition unit that acquires requirement information requesting anticipated risks for work content at a construction site; a processing unit that extracts information that is likely to correspond to the request information acquired by the acquisition unit from a database that stores information on past construction projects in advance, generates input information to be input to a generation AI model that can generate data according to input data using the extracted information and the request information, and performs a specific process to generate response information for the request information based on the output result of the generation AI model; an output unit that outputs the answer information generated by the processing unit; 2. A data processing device comprising:

2. The data processing device according to claim 1 , wherein the processing unit extracts, as the information on the past construction work, information likely to correspond to the requested information from at least one of a risk assessment implementation report and an accident case.

3. 3. The data processing device according to claim 2, wherein the processing unit extracts information including a predetermined word from the one piece of information as information likely to correspond to the requested information.

4. The data processing device according to claim 1 , wherein the processing unit generates, as response information, anticipated risks at the construction site and examples of accidents that have occurred in similar construction projects.

5. The computer Obtaining requirements information that requires anticipated risks for work content at the construction site, Extracting information that is likely to correspond to the requested information from a database that stores information on past construction projects in advance; Using the extracted information and the request information, generate input information to be input to a generative AI model capable of generating data according to the input data; A data processing method that generates and outputs response information to the request information based on the output results of the generation AI model.

6. On the computer, Obtaining requirements information that requires anticipated risks for work content at the construction site, Extracting information that is likely to correspond to the requested information from a database that stores information on past construction projects in advance; Using the extracted information and the request information, generate input information to be input to a generative AI model capable of generating data according to the input data; A program for executing a process of generating and outputting response information to the request information based on the output result of the generation AI model.

Images