Program, method, information processing device, and system

Abstract

By automating everything from design drawing analysis to cost estimation, work efficiency is improved and highly accurate cost estimation is achieved. [Solution] The program is a program to be executed by a computer having a processor and a memory, and the program causes the processor to execute the following steps: accepting information about a design drawing; selecting a tool to be used by inputting a first prompt containing information about the design drawing and an instruction to execute the estimation process to a generation AI configured to execute an estimation process using a first tool and a second tool based on the information about the design drawing; when the first tool is selected, identifying an area included in the information about the design drawing using the first tool; and when the second tool is selected, calculating the quantity of components included in the identified area using the second tool.

Description

[Technical Field]

[0001] The present disclosure relates to a program, a method, an information processing device, and a system. [Background technology]

[0002] In the construction industry, cost estimation is an essential process for estimating the cost of a construction project. Conventionally, this work has been done manually, resulting in low work efficiency and issues with estimation accuracy.

[0003] In response to this, Patent Document 1 discloses a technology that uses machine learning with artificial intelligence to create measurement line data based on architectural drawing image data using image recognition processing, and then creates quantitative data based on the created measurement line data. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-070582 Summary of the Invention [Problem to be solved by the invention]

[0005] However, Patent Document 1 has an insufficient mechanism for autonomously selecting the most appropriate tool for a design drawing and for processing each tool in a coordinated manner, which means that the automation and efficiency of the entire estimation work has not been fully achieved.

[0006] The purpose of the present disclosure is to improve work efficiency and achieve highly accurate estimation by automating processes from design drawing analysis to estimation. [Means for solving the problem]

[0007] In order to solve the above problem, one embodiment of the program of the present disclosure is a program to be executed by a computer having a processor and a memory, the program causing the processor to execute the following steps: accepting information about a design drawing; selecting a tool to be used by inputting a first prompt including information about the design drawing and an instruction to execute the estimation process to a generation AI configured to execute an estimation process using a first tool and a second tool based on the information about the design drawing; if the first tool is selected, identifying an area included in the information about the design drawing using the first tool; and if the second tool is selected, calculating the quantity of components included in the identified area using the second tool. [Effects of the Invention]

[0008] According to the present disclosure, by automating the process from design drawing analysis to cost estimation, work efficiency can be improved and highly accurate cost estimation can be achieved. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing an example of the overall configuration of a system 1. FIG. [Figure 2] 2 is a diagram illustrating an example of a functional configuration of a user terminal 10 shown in FIG. [Figure 3] 2 is a diagram illustrating an example of a functional configuration of a server 20 shown in FIG. [Figure 4] FIG. 2 is a diagram showing an example of the data structure of a user information table 2021. [Figure 5] FIG. 10 is a diagram showing an example of the data structure of a design drawing information table 2022. [Figure 6] FIG. 10 illustrates an example of the data structure of a tool information table 2023. [Figure 7] 10 is a diagram showing an example of the data structure of an area specification information table 2024. FIG. [Figure 8] FIG. 10 is a diagram showing an example of the data structure of a quantity calculation table 2025. [Figure 9] 10 is a flowchart illustrating an example of an accumulation processing operation. [Figure 10] 10 is a flowchart illustrating an example of an area identification processing operation. [Figure 11] 10 is a flowchart illustrating an example of a quantity calculation processing operation. [Figure 12] 1 is a schematic diagram illustrating an example of a display screen of a display 141 of a user terminal 10. FIG. [Figure 13] 1 is a schematic diagram illustrating an example of a display screen of a display 141 of a user terminal 10. FIG. [Figure 14] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings describing the embodiments, common components are designated by the same reference numerals, and repeated description will be omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each drawing is a schematic diagram and is not necessarily a precise illustration.

[0011] In the following description, a "processor" refers to one or more processors. The at least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may also be another type of processor such as a GPU (Graphics Processing Unit). The at least one processor may be single-core or multi-core.

[0012] Furthermore, the at least one processor may be a processor in the broad sense, such as a hardware circuit (for example, a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC)) that performs part or all of the processing.

[0013] In the following explanation, information that produces an output for an input may be described using expressions such as "xxx table," but this information may be data of any structure, or may be a learning model such as a neural network that produces an output for an input. Therefore, an "xxx table" may be referred to as "xxx information."

[0014] Furthermore, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0015] In addition, in the following explanation, processing may be described using the "program" as the subject, but since a program is executed by a processor to perform specified processing while appropriately using a memory unit and / or an interface unit, etc., the subject of the processing may also be the processor (or a device such as a controller that has that processor).

[0016] The program may be installed in a device such as a computer, or may be stored in, for example, a program distribution server or a computer-readable (e.g., non-transitory) recording medium. Also, in the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0017] Furthermore, in the following description, identification numbers are used as identification information for various objects, but other types of identification information (for example, identifiers including alphabetic characters or symbols) may also be used.

[0018] In addition, in the following description, when describing elements of the same type without distinguishing between them, reference symbols (or common symbols among the reference symbols) may be used, and when describing elements of the same type with distinction between them, the identification numbers (or reference symbols) of the elements may be used.

[0019] In the following description, the control lines and information lines are those that are considered necessary for the description, and do not necessarily represent all the control lines and information lines in the product. All components may be interconnected.

[0020] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the user terminal 10 and the server 20, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.

[0021] <1. Overview> The system according to this embodiment is a cost estimation system in which an AI agent autonomously selects an appropriate tool to perform cost estimation after analyzing a blueprint. This system accepts a blueprint and, based on information about the blueprint, selects a tool to be used by inputting a user prompt (first prompt) containing information about the blueprint and instructions for executing the cost estimation process to a generation AI (AI agent) configured to use a first tool (image recognition tool) and a second tool (quantity calculation tool). When the first tool is selected, the first tool identifies an area included in the information about the blueprint. When the second tool is selected, the second tool calculates the quantity of components included in the identified area. This automates and streamlines the entire cost estimation process, improving work efficiency and achieving highly accurate cost estimation.

[0022] <2. Overall system configuration> Fig. 1 is a block diagram showing an example of the overall configuration of system 1. System 1 shown in Fig. 1 includes, for example, a user terminal 10, a server 20, and a generation AI system 30. The user terminal 10, the server 20, and the generation AI system 30 are communicatively connected via, for example, a network 80.

[0023] 1 shows an example in which the system 1 includes one user terminal 10, the number of user terminals 10 included in the system 1 is not limited to one. The number of user terminals 10 included in the system 1 may be two or more.

[0024] In this embodiment, a collection of multiple devices may be considered as one server. The allocation of multiple functions required to realize the server 20 according to this embodiment to one or more pieces of hardware can be determined appropriately in consideration of the processing capacity of each piece of hardware and / or the specifications required for the server 20.

[0025] The user terminal 10 is, for example, an information processing device operated by a user performing an estimating task. The user terminal 10 accepts various information and instructions from the user and transmits the input information to the server 20. The user terminal 10 displays the estimating results and the like presented by the server 20. The user terminal 10 is realized, for example, by a desktop personal computer (PC), a laptop PC, or the like. The user terminal 10 may also be realized by a mobile terminal such as a smartphone or a tablet.

[0026] The user terminal 10 includes a communication IF (Interface) 12, an input device 13, an output device 14, a memory 15, a storage 16, and a processor 19. The input device 13 is a device for receiving input operations from a user (for example, a touch panel, a touch pad, a pointing device such as a mouse, a keyboard, etc.). The output device 14 is a device for presenting information to a user (a display, a speaker, etc.).

[0027] The server 20 is, for example, an information processing device that provides services for managing and operating the estimation system, and is realized by a computer connected to the network 80. The server 20 controls, for example, the transmission and reception of necessary information between the user terminal 10 and the generation AI system 30.

[0028] The server 20 includes a communication IF 22, an input / output IF 23, a memory 25, a storage 26, and a processor 29. The input / output IF 23 functions as an interface for an input device for receiving input operations from the administrator of the estimating system, and an output device for outputting information to the administrator.

[0029] The generative AI system 30 is, for example, a cloud server having a large-scale language model (LLM). The number of LLMs included in the generative AI system 30 may be one or more.

[0030] LLM is a single-modal natural language model constructed by learning from large amounts of text data, and is used in many NLG (Natural Language Generation) tasks, such as generating answers to specific questions, automatically generating sentences, and summarizing text. LLM is an example of a generative AI model. Examples of LLMs include: OpenAI: GPT-4 Google: Gemini 1.5 Flash ·Anthropic: Claude 3.5 Sonnet

[0031] The generative AI system 30 has, for example, an LLM, and autonomously controls the overall flow of the estimating work (tool selection, procedure planning, result generation, etc.) and the generation of response contents (selected tool, area identification result, quantity calculation result, etc.) based on a preset system prompt (second prompt). When a user prompt (first prompt) including instructions from the user, design drawing data, and various information related to the design drawing is input from the server 20, the generative AI system 30 comprehensively interprets these and the internal system prompt, generates a response corresponding to the next step in the estimating work, and transmits it to the server 20.

[0032] The system prompts include detailed instructions (such as the role of the AI ​​agent, the logic for progressing each phase of the estimation work, the perspectives and check items for collecting information on estimation items, work progress rules, completion requirements, evaluation criteria, and response formats) that the generative AI system 30 uses to autonomously control the estimation work. The system prompts are set in advance inside the generative AI system 30 or stored in the memory unit 202 of the server 20, and are provided to the generative AI system 30 when the estimation work starts or as needed.

[0033] The generation AI system 30 autonomously generates results such as tool selection, area identification, and quantity calculation based on user prompts sent from the server 20 and system prompts that it references internally, and outputs them to the server 20. The system prompts include various instructions for achieving smooth estimation work and collecting and providing appropriate information, and their main components include role instructions, answer generation instructions, reference information specification, user prompt specification, and output format instructions.

[0034] The role instruction includes text that indicates the role (position) that the LLM will play when generating an answer. In this embodiment, the role instruction is defined in the system prompt in the form of, for example, "You are an AI agent who is an expert in architectural quantity estimating. Accurately analyze the provided design drawings and the user's instructions, and autonomously select the most appropriate tools to perform a highly accurate quantity estimate. If you have any questions, please ask the user for additional information," and specifies an appropriate persona for the AI ​​agent.

[0035] The answer generation instructions include text instructing the LLM on what kind of answer to generate. In this embodiment, the answer generation instructions vary greatly in content depending on the associated estimation phase (e.g., tool selection, area identification, quantity calculation) in the system prompt. For example, in the tool selection phase, the system may ask, "Based on the content of the provided design drawing and the user's request, we will select the first tool (image recognition tool) or the second tool (quantity calculation) to be used." In the area identification phase, instructions such as "Accurately identify the area and outline of the rooms included in the blueprint, and output the results in association with the room names" may be included. In the quantity calculation phase, instructions such as "Accurately calculate the quantity of materials (floors, ceilings, walls, baseboards, etc.) within the identified area, and output the data in tabular format in the units required for calculation" may be included.

[0036] The reference information specification includes instructions for using information extracted from the tool information table 2023 or the like, or a placeholder indicating where to insert the extracted information. A general format or instructions for using such external information may be defined in the system prompt. This is mainly used when performing processing in accordance with the functions of available tools in each phase of the estimation work. For example, it may be in the format "Please refer to the tool information below and select the most appropriate tool. Tool information: {Tool information}."

[0037] The user prompt specification includes instructions for the LLM to recognize and use the content of the input information (user prompt) from the user, or a placeholder that indicates where the input information string should be inserted. The user prompt specification may also define general guidelines for how to interpret the user prompt from the user and use it to generate a response in the system prompt. For example, it may be in the format "Please proceed with the process based on the following instruction text and design data from the user. User instruction: '{user instruction text}', Design data: '{path to the design file or data summary}'."

[0038] The output format instructions include instructions regarding the output format (template), structure, style, or elements to be included in the answer generated by the LLM. In this embodiment, the output format instructions are specified in detail in a system prompt, and, for example, instruct the entire response from the generative AI system 30 to be in JSON format and to include specific key-value pairs. Examples of specific keys that may be included in this JSON-formatted response include "tool_selection" (selected tool), "identified_areas" (identified areas), and "calculated_quantities" (calculated quantities).

[0039] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For the user terminal 10 and the server 20, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.

[0040] <2-1. Functional configuration of user terminal> Fig. 2 is a diagram showing an example of the functional configuration of the user terminal 10 shown in Fig. 1. As shown in Fig. 2, the user terminal 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a storage unit 180, and a control unit 190. The blocks included in the user terminal 10 are electrically connected by, for example, a bus or the like.

[0041] The communication unit 120 performs processes such as modulation and demodulation for the user terminal 10 to communicate with other devices. The communication unit 120 performs transmission processing on signals generated by the control unit 190 and transmits them to the outside (for example, the server 20). The communication unit 120 performs reception processing on signals received from the outside and outputs them to the control unit 190. As a result, the design drawings and various instructions input by the user are transmitted to the server 20, and the user terminal 10 receives the calculation results and the like from the server 20.

[0042] The input device 13 is a device for inputting instructions or information by a user operating the user terminal 10. The input device 13 is realized, for example, by a touch-sensitive device 131 or the like, which inputs instructions by touching the operation surface. If the user terminal 10 is a PC or the like, the input device 13 may be realized by a reader, keyboard, mouse, or the like. The input device 13 converts instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may also include, for example, a receiving port that receives electrical signals input from an external input device.

[0043] The output device 14 is a device for presenting information to a user operating the user terminal 10. The output device 14 is realized, for example, by a display 141 or the like. The display 141 displays data according to the control of the control unit 190. The display 141 is realized, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display or the like.

[0044] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of an audio signal. The audio processing unit 17 converts a signal provided from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is realized, for example, by a processor for audio processing. The microphone 171 receives an audio input and provides an audio signal corresponding to the audio input to the audio processing unit 17. The speaker 172 converts the audio signal provided from the audio processing unit 17 into audio and outputs the audio to the outside of the user terminal 10. In this embodiment, these audio-related components can be used when a user inputs instructions by voice or receives an integration result by voice.

[0045] The storage unit 180 is realized by, for example, the memory 15 and the storage 16, and stores data and programs used by the user terminal 10. The storage unit 180 stores, for example, user basic information 181, application programs for using the estimating system, setting information, etc.

[0046] The user basic information 181 includes, for example, information about the user who uses the user terminal 10. The information about the user includes, for example, the user's name, age, sex, date of birth, telephone number, and the like.

[0047] The control unit 190 is realized by the processor 19 reading a program stored in the storage unit 180 and executing instructions included in the program. The control unit 190 controls the operation of the user terminal 10. The control unit 190 functions as an operation reception unit 191, a transmission / reception unit 192, and a presentation control unit 193 by operating in accordance with the program.

[0048] The operation reception unit 191 performs processing for receiving instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 can receive instructions input from the touch-sensitive device 131 or the like, or information related to the estimation system, such as an instruction to upload a blueprint or an instruction to execute estimation.

[0049] The operation reception unit 191 also receives voice instructions input from the microphone 171. Specifically, for example, the operation reception unit 191 receives a voice signal that is input from the microphone 171 and converted into a digital signal by the voice processing unit 17. This allows the user to interact with the estimation system by voice.

[0050] The transmitting / receiving unit 192 performs processing for the user terminal 10 to transmit and receive data to and from external devices such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 transmits design drawings and various instructions input by the user to the server 20. The transmitting / receiving unit 192 also receives cost estimates and the like provided by the server 20.

[0051] The presentation control unit 193 controls the output device 14 to present information provided from the server 20 to the user. Specifically, for example, the presentation control unit 193 causes the display 141 to display various information related to the estimating system, such as the estimating result, the area identification result, and the quantity calculation result, transmitted from the server 20. The presentation control unit 193 also causes the speaker 172 to output the information transmitted from the server 20.

[0052] <2-2. Functional configuration of the server> Fig. 3 is a diagram showing an example of the functional configuration of the server 20 shown in Fig. 1. As shown in Fig. 3, the server 20 performs the functions of a communication unit 201, a storage unit 202, and a control unit 203.

[0053] The communication unit 201 performs processing for the server 20 to communicate with an external device, such as the user terminal 10 or the generation AI system 30.

[0054] The storage unit 202 is realized by the memory 25 and the storage 26, and stores data and programs used by the server 20 to provide the estimation system. The storage unit 202 stores, for example, a user information table 2021, a design drawing information table 2022, a tool information table 2023, an area identification information table 2024, and a quantity calculation table 2025. The databases and trained models stored in the storage unit 202 are not limited to these. The storage unit 202 also stores an image recognition tool 2026 that functions as a first tool, and a quantity calculation tool 2027 that functions as a second tool.

[0055] The user information table 2021 is a database that stores data about users, including information such as the user's name, age, sex, date of birth, phone number, etc. Details will be described later.

[0056] The blueprint information table 2022 is a database that stores information about blueprints received from users, including items such as blueprint ID, upload date, file format, blueprint, etc. Details will be described later.

[0057] The tool information table 2023 is a database that stores information about tools that can be used in the system, including items such as tool ID, tool name, function, input data, output data, etc. Details will be described later.

[0058] The area identification information table 2024 is a database that stores information about areas identified from blueprints, including items such as area identification ID, blueprint ID, execution date, and result. Details will be described later.

[0059] The quantity calculation table 2025 is a database that stores information about the results of calculating the quantity of components included in a specified area, including items such as quantity calculation ID, area specification ID, execution date, and result. Details will be described later.

[0060] The image recognition tool 2026 functions as a first tool and is used to identify areas included in a blueprint. The blueprint includes, for example, a floor plan and an elevation. The image recognition tool 2026, for example, identifies the areas and outlines of multiple rooms included in the blueprint. The image recognition tool 2026 may be an image recognition model that is trained to input a blueprint, identify areas included in the blueprint, and output a blueprint with the identified areas. The image recognition tool 2026 is trained using accumulated information about the blueprints as learning data. The information about the blueprints includes, for example, information about the blueprints (floor plan and elevation), the identified room areas, the outlines of the areas, and each dimension.

[0061] The quantity calculation tool 2027 functions as a second tool and is used to calculate (take off) the quantities of components included in the identified area. The quantity calculation tool 2027 calculates, for example, the areas of the floor, ceiling, and walls of each room, as well as the length of baseboards, which are necessary for estimation. The quantity calculation tool 2027 may be an image recognition model that has been trained to calculate and output the quantities of components included in the identified area when a design drawing whose area has been identified by the first tool is input.

[0062] The control unit 203 is realized by the processor 29 reading a program stored in the storage unit 202 and executing instructions included in the program. The control unit 203 controls the operation of the server 20. By operating in accordance with the read program, the control unit 203 can fulfill the functions of a reception control module 2031, a transmission control module 2032, a service processing module 2033, and a presentation control module 2034.

[0063] The reception control module 2031 controls the process by which the server 20 receives signals from external devices in accordance with a communication protocol. For example, it receives user prompts including operation information such as design drawing data and estimation execution instructions from the user terminal 10. The reception control module 2031 also receives responses (tool selection results, area identification results, quantity calculation results, etc.) output from the generation AI system 30. The received information is passed to other related modules (mainly the service processing module 2033).

[0064] The transmission control module 2032 controls the process in which the server 20 transmits signals to external devices in accordance with a communication protocol. The transmission control module 2032 executes a process of transmitting user prompts including operation information such as design drawing data and estimation execution instructions to the generation AI system 30, for example, based on instructions from the service processing module 2033. The transmission control module 2032 also executes a process of transmitting responses (e.g., estimation results) from the generation AI system 30 to the user terminal 10, for example, based on instructions from the presentation control module 2034.

[0065] The service processing module 2033 serves as the main communication interface with the generation AI system 30. Specifically, it formats the design drawing data and other necessary information received from the user terminal 10 via the reception control module 2031 as user prompts and inputs them to the generation AI system 30 via the transmission control module 2032. It also acquires responses (tool selection results, area identification results, quantity calculation results, etc.) output from the generation AI system 30 via the reception control module 2031. The acquired response data is passed to the presentation control module 2034 and processed for output to the user terminal 10.

[0066] The presentation control module 2034 formats the output contents (accumulation results, area identification results, quantity calculation results, etc.) of the generation AI system 30 received from the service processing module 2033 into a format suitable for the user interface used by the user (display screen of the user terminal 10, etc.), and transmits them to the user terminal 10 via the transmission control module 2032 for presentation.

[0067] <3. Data Structure> 4 to 7 are diagrams showing the data structures of databases stored in server 20. Note that Figures 4 to 7 are merely examples and do not exclude data that is not listed. Furthermore, even data that is listed in the same database may be stored in separate storage areas in storage unit 202.

[0068] 4 is a diagram showing an example of the data structure of the user information table 2021. The user information table 2021 is a database that stores data related to users. Here, the user information table 2021 is a database that uses a user ID as a key and has columns such as name, age, sex, date of birth, and telephone number.

[0069] The item "user ID" is an item for storing an identifier for uniquely identifying a user.

[0070] The item "Name" is an item for storing the name of the user.

[0071] The item "age" is an item for storing the age of the user.

[0072] The item "gender" is an item for storing the gender of the user.

[0073] The item "Date of Birth" is an item for storing the user's date of birth.

[0074] The item "telephone number" is an item for storing the user's telephone number.

[0075] 5 is a diagram showing an example of the data structure of the blueprint information table 2022. The blueprint information table 2022 is a database that stores information about blueprints of buildings and the like received from users. In this example, the blueprint information table 2022 is a database that uses the blueprint ID as a key and has columns such as upload date, file format, and type.

[0076] The item "design drawing ID" is an item for storing an identifier for uniquely identifying a design drawing.

[0077] The item "upload date" is an item for storing the date when the design drawing was uploaded to the system by the user.

[0078] The item "file format" is an item for storing the file format of the design drawing. The item "file format" may store, for example, a file format such as PDF, DXF, or CAD file.

[0079] The "Blueprint" item is an item that stores image data of a blueprint. The "Blueprint" item may store, for example, a plan view or an elevation view as a blueprint. The "Blueprint" item may store, for example, various information included in the blueprint. The various information may include, for example, information such as dimensions, materials, and notes written on the blueprint.

[0080] 6 is a diagram showing an example of the data structure of the tool information table 2023. The tool information table 2023 stores information about tools available in the system. In this example, the tool information table 2023 is a database having columns such as tool name, function, input data, and output data, with the tool ID as a key.

[0081] The item "tool ID" is an item for storing an identifier for uniquely identifying a tool.

[0082] The item "tool name" is an item for storing the name of a tool. Here, the item "tool name" includes, for example, an image recognition tool and a quantity calculation tool.

[0083] The item "function" is an item for storing the function of the tool. Here, the item "function" includes, for example, function information such as area identification and quantity calculation.

[0084] The item "input data" is an item for storing input data to be input to a tool. Each tool functions when the input data is input.

[0085] The item "output data" is an item for storing the output data output by the tools. Each tool executes a function according to input data and outputs output data.

[0086] 7 is a diagram showing an example of the data structure of the area identification information table 2024. The area identification information table 2024 is a database that stores information about areas identified from design drawings. That is, the area identification information table 2024 stores the output results of the first tool. Here, the area identification information table 2024 is a database that uses an area identification ID as a key and has columns such as a design drawing ID, execution date, and result.

[0087] The item "area identification ID" is an item for storing an identifier for uniquely identifying the area identification result.

[0088] The item "design drawing ID" is an item for storing the ID of the design drawing whose area is identified. The item "design drawing ID" corresponds to the item "design drawing ID" shown in FIG.

[0089] The item "execution date" is an item for storing the date when the area identification of the design drawing was executed by the first tool.

[0090] The item "result" is an item for storing image data etc. that is the result of the area being identified. The item "result" includes, for example, a blueprint image etc. in which the area and outline of the room have been identified.

[0091] 8 is a diagram showing an example of the data structure of the quantity calculation table 2025. The quantity calculation table 2025 is a database that stores, for example, information related to the quantity calculation results of components included in a specified area. In other words, the quantity calculation table 2025 stores the output results of the second tool. The quantity calculation table 2025 is a database that uses the quantity calculation ID as a key and has columns such as an area specification ID, execution date, and result.

[0092] The item "quantity calculation ID" is an item for storing an identifier for uniquely identifying the quantity calculation result.

[0093] The item "area identification ID" is an item for storing the ID of the area that is the target of the quantity calculation. The item "area identification ID" corresponds to the item "area identification ID" shown in FIG.

[0094] The item "Date of Execution" is an item for storing the date on which the quantity calculation was executed.

[0095] The item "Result" is an item for storing the calculated quantity of components, such as the area of ​​the floor, ceiling, and walls of each area, and the length of the baseboard.

[0096] <4. Example of operation> <4-1. Accumulation processing operation> The operation of the system 1 in this embodiment will be described below with reference to a flowchart of FIG.

[0097] First, a user performing an estimation operation accesses the server 20 that provides an estimation system. The user operates the user terminal 10, for example, and enters their user ID and password to log in to the estimation system provided by the server 20. The server 20 receives a request from the user to execute estimation processing.

[0098] In step S11, the server 20 accepts information about blueprints from the user. Specifically, the user operates, for example, the user terminal 10 to upload information about blueprints of a building for which they wish to request a cost estimate to the system. The reception control module 2031 accepts the blueprints uploaded by the user and links to the service processing module 2033. Blueprints include, for example, floor plans and elevations. Blueprints may be in any file format (PDF, DXF, CAD file, image file, etc.).

[0099] When estimating work is performed for the first time on an uploaded blueprint, the information about the blueprint is expected to include, for example, only the blueprint (plan view and elevation view) before processing. The blueprint before processing is, for example, a blueprint that the user holds in advance before processing by the estimating system (for example, the first tool) in this embodiment. The blueprint before processing may include, for example, rough dimensional information and material information of components. On the other hand, if estimating work has previously been performed up to area identification (for example, if it has been interrupted), the information about the blueprint includes, for example, the blueprint with the identified area and outline, and information about each added dimension.

[0100] The user may also send specific instructions regarding cost estimation to the server 20 together with information regarding the blueprint. For example, instructions such as "Please calculate only the floor area of ​​the first floor of this blueprint," additional information such as "The wall material of a specific room (e.g., a conference room) is ____, so please calculate taking that material cost into consideration," or output requests such as "Please output a detailed breakdown of the cost estimation results for each room" may be provided by text input.

[0101] In step S12, the server 20 inputs information about the design drawing to the generation AI system 30. The service processing module 2033 inputs the received information about the design drawing and an instruction statement for executing cost estimation processing for the design drawing to the generation AI system 30 as a user prompt (first prompt). At this time, the service processing module 2033 may, for example, analyze the received information about the design drawing and the instruction statement for executing cost estimation processing for the design drawing, and extract and input information, etc., necessary for the generation AI system 30 to execute the cost estimation processing.

[0102] The service processing module 2033 may also input a system prompt (second prompt) to the generative AI system 30 to control the behavior of the generative AI system 30. The system prompt includes detailed information about a group of instructions used by the generative AI system 30 to autonomously control the estimating work, such as instructions about the role of the AI ​​agent, the progress logic for each phase of the estimating work, perspectives and check items for collecting information about estimating items, work progress rules, completion requirements, evaluation criteria, response formats, etc. Specifically, the role instructions include text such as, "You are an AI agent who is an expert in architectural estimating. Accurately analyze the provided blueprints and user instructions, and autonomously select the most appropriate tools to perform a highly accurate estimating work. If you have any questions, please ask the user for additional information." The answer generation instructions may include, for example, instructions such as, "Based on the content of the provided blueprint and the user's request, determine which first tool (image recognition tool) or second tool (quantity calculation tool) should be used, and output the selection result along with the rationale for your decision," "Accurately identify the area and outline of the room included in the blueprint, and output the corresponding information in association with the room name," or "Accurately calculate the quantity of materials (floor, ceiling, wall, baseboard, etc.) within the identified area, and output the data in tabular format in the units required for calculation." Furthermore, the system prompt includes key components such as, for example, a reference information specification, a user prompt specification, and an output format specification. The generative AI system 30 comprehensively interprets the user prompt and the system prompt and autonomously executes its operations.

[0103] In step S13, the server 20 causes the generative AI system 30 to plan the procedures for the tools to be used. Specifically, the generative AI system 30 autonomously plans the optimal procedures (workflow) for the tools (such as the first tool and the second tool) to be used to perform the estimation work based on the input user prompts and system prompts. The planned procedures are, for example, a series of steps such as "first, identify the area of ​​the room with the first tool, and then calculate the quantity of each component with the second tool." Furthermore, if the area of ​​the room has been identified in advance, the planned procedures may be, for example, simply "calculate the quantity of each component with the second tool."

[0104] In step S14, the server 20 presents the plan. Specifically, the service processing module 2033, for example, causes the display 141 of the user terminal 10 to display the procedure of the tool planned by the generation AI system 30 via the presentation control module 2034. For example, the procedure is presented on the screen in the form of "Estimation flow plan: 1. Automatically recognize the area of ​​the room from the design drawing. 2. Calculate the area of ​​the floor, ceiling, and walls, and the length of the baseboard from the recognized area. Is this procedure correct?"

[0105] In step S15, the server 20 receives approval for the plan. Specifically, the reception control module 2031 receives approval from the user (e.g., by clicking an "Approve" button on the screen) and links to the service processing module 2033. If the user does not approve the plan, the user may request a revision. The revision request may include, for example, an instruction to exclude a specific room from the accrual or to manually revise the area. When the service processing module 2033 receives the revision request, it may, for example, instruct the generation AI system 30 to recreate the plan.

[0106] Furthermore, if the design drawing lacks dimensional information necessary for cost estimation (for example, ceiling height, length of a specific component), the server 20 may automatically detect this lack using the generation AI system 30 and request the user to input additional information via the user terminal 10. For example, if the floor plan uploaded by the user does not include information about the ceiling height, the server 20 may display a message such as "The ceiling height is unknown. Please input it" on the user terminal 10 to prompt the user to input it.

[0107] In step S16, the server 20 causes the generation AI system 30 to select a tool to use. The tool selection is determined, for example, based on the rules of the system prompt input to the generation AI system 30. Furthermore, the generation AI system 30, which is fine-tuned using information about the blueprint, makes a more precise determination. The system prompt includes, for example, an instruction statement instructing the system to select and use the first tool or the second tool depending on the input information. For example, if the input information is "blueprint data before processing," the generation AI determines that "area identification is required first" and selects the first tool (image recognition tool 2026). On the other hand, if the input information is "blueprint data whose area has been identified by the first tool," the generation AI determines that "quantity calculation is required next" and selects the second tool (quantity calculation tool 2027). Figures 10 and 11 (described later) illustrate an example in which the first tool is first selected to identify the area of ​​the blueprint, and then the second tool is selected to perform quantity calculation processing for the blueprint whose area has been identified.

[0108] In step S17, the server 20 performs an estimating process. Specifically, after the second tool selected by the generation AI system 30 in step S16 executes the quantity calculation process, the server 20 executes the estimating process from the output result. That is, the server 20 executes the estimating process based on the calculated quantities of components and the unit prices of the components. For example, after the second tool calculates the floor area, wall area, ceiling area, and baseboard length, the server 20 multiplies these calculated quantities by the preset unit price information for each component. As a result, a specific estimating amount is calculated, such as "The cost of flooring for conference room 1 is XX yen, and the cost of wallpaper is XX yen," and this is presented as the final estimating result (estimate result). <4-2. Area specific processing operation>

[0109] 10 is a flowchart showing an example of the area identification processing operation, in which the first tool is selected in step S16 of FIG.

[0110] In step S21, the server 20 receives a request to the first tool (image recognition tool 2026). Specifically, when the first tool is selected by the generation AI system 30, the service processing module 2033 receives the request to the first tool from the generation AI system 30 and transmits information about the design drawing (e.g., information about the design drawing before processing) to the first tool.

[0111] In step S22, the first tool identifies areas included in the information related to the blueprint. The first tool automatically identifies the areas of multiple rooms and the contours (boundaries) of those rooms from the blueprint received from the service processing module 2033. The identified areas may be recognized by associating them with the names of the rooms (e.g., conference room 1, office 2, etc.). The first tool, for example, creates a new blueprint with the identified areas.

[0112] In step S23, the server 20 presents the results of the area identification. Specifically, the service processing module 2033, for example, causes the display 141 of the user terminal 10 to display the area identification result information (e.g., image data of the blueprint from which the areas have been identified, coordinate data of each area, room name, etc.) received from the first tool via the presentation control module 2034. Each area may be color-coded, or the room name may be displayed.

[0113] In step S24, the server 20 accepts a correction request. The user checks the area identification results displayed on the screen of the user terminal 10, and if there are any errors or deficiencies in the area recognition (for example, the room boundary is misaligned, or a specific space is not recognized as a room), the user can indicate the parts that need correction and make a correction request. The service processing module 2033 accepts this correction request and provides feedback to the generation AI system 30, prompting it to re-execute the area identification process or make manual adjustments.

[0114] In step S25, the server 20 accepts approval of the area identification result. If the user determines that the presented area identification result is correct, the user operates the user terminal 10 to approve it. If the user approves, the area identification information is confirmed and the process proceeds to the next calculation processing step (e.g., quantity calculation processing using the second tool in Figure 11). At this time, the server 20 inputs, for example, the area identification result using the first tool (such as a design drawing in which the area has been identified) to the generation AI system 30. The generation AI system 30 selects, for example, the second tool depending on the input information. On the other hand, if the area identification result is not approved by the user, the process may return to step S24 again.

[0115] <4-3. Quantity calculation processing operation> 11 is a flowchart showing an example of the quantity calculation process operation, in which the second tool is selected in step S16 of FIG.

[0116] In step S31, the server 20 receives a request to the second tool (quantity calculation tool 2027). Specifically, when the second tool is selected by the generation AI system 30, the service processing module 2033 receives the request to the second tool from the generation AI system 30 and transmits information about the design drawing to the second tool (for example, the result of the area identification of the first tool, i.e., information about the design drawing with the identified area, etc.).

[0117] In step S32, the second tool calculates the quantity of components included in the identified area. The second tool automatically calculates the quantity of components required for estimation based on the identified area information received from the service processing module 2033 (such as the coordinates and outline of the area, the corresponding room name, and dimensional information written on the blueprint or dimensional information supplemented by the user). Specifically, the second tool calculates the floor area, ceiling area, and wall area of ​​each room, as well as the length of the baseboards installed around the room. For example, specific quantities such as "the wall area of ​​conference room 1 is 2.5m x 10m, the ceiling area is 2m x 10m, and the length of the baseboard is 10m" are calculated.

[0118] In step S33, the server 20 presents the calculated quantity results. Specifically, the service processing module 2033 displays, on the display 141 of the user terminal 10, the quantity calculation result information (e.g., quantity calculation data in tabular form) related to the components received from the second tool via, for example, the presentation control module 2034.

[0119] In step S34, the server 20 accepts a correction request. The user checks the quantity calculation results displayed on the screen of the user terminal 10, and if there is an error in the calculation results or adjustments are required (for example, the estimated value for a specific room does not match, or the user wants to adjust the quantity of a specific component), the user can indicate the parts that need to be corrected and make a correction request. The service processing module 2033 accepts this correction request and provides feedback to the generation AI system 30, prompting the user to re-execute the quantity calculation process or make manual adjustments.

[0120] In step S35, the server 20 accepts approval of the calculated quantity result. If the user determines that the presented quantity result is correct, the user operates the user terminal 10 to approve it. If the user approves, the quantity calculation information is confirmed and the quantity calculation process is completed. Then, the process proceeds to step S17, where an accumulation process is performed based on the quantity calculation result. On the other hand, if the user does not approve the area identification result, the process may return to step S34 again.

[0121] <5. Screen example> 12 is a schematic diagram showing an example of a display screen of the display 141 of the user terminal 10. For example, FIG. 12 shows a region identification result presentation screen in step S23 shown in FIG.

[0122] The screen shown in FIG. 12 includes a first area 1411, a second area 1412, a third area 1413, a fourth area 1414, a fifth area 1415, and a sixth area 1416.

[0123] The first area 1411 is an area showing a blueprint in which the areas and contours of rooms have been identified (the result of the area identification). The first area 1411 shows, for example, the areas and contours of each room automatically identified by the first tool, and each area is visually distinguished by color coding or highlighting.

[0124] The second area 1412, the third area 1413, and the fourth area 1414 each show a specific area (for example, a "conference room" and an "office"). By checking these displays, the user can understand which area (room) has been recognized and how.

[0125] A fifth area 1415 is an "Approve" button that the user selects if the result of the area identification is correct, and a sixth area 1416 is a "Modify" button that the user selects if the result of the area identification needs to be corrected.

[0126] By checking the results of this area identification, the user can confirm the results of area identification by the first tool and correct any errors or omissions.

[0127] 13 is a schematic diagram showing an example of a display screen of the display 141 of the user terminal 10. For example, FIG. 13 shows a quantity calculation result presentation screen in step S33 shown in FIG.

[0128] The screen shown in FIG. 13 includes a first area 1421, a second area 1422, and a third area 1423.

[0129] The first area 1421 is an area that displays the results of the quantity calculation in a table format. This table includes columns such as floor number, room name, part (e.g., wall, ceiling, baseboard), unit (e.g., square meter, m), and quantity, and presents a list of the specific calculated quantities for each component in each room.

[0130] The second area 1422 is an "Approve" button that the user selects when the result of the quantity calculation is correct. The third area 1423 is a "Modify" button that the user selects when the result of the quantity calculation needs to be corrected.

[0131] By checking the results of this quantity calculation, the user can confirm the results of the quantity calculation by the second tool and correct any errors or deficiencies. <5 Variations>

[0132] In the above embodiment, the first tool and the second tool are trained models, but the present embodiment is not limited to this. For example, the image recognition tool 2026 and the quantity calculation tool 2027 may be realized as programs stored in the storage unit 202 of the server 20 or as part of the internal functions of the generation AI system 30.

[0133] In the above embodiment, an example was shown in which the area identification process by the first tool and the quantity calculation process by the second tool were performed consecutively, but the starting point of the process may differ depending on the status of the information such as the input design drawing, etc. For example, if the design drawing has already been processed, such as when a design drawing with a clearly identified area is input, or when the previous work was interrupted up to the area identification stage, the second tool may be selected directly in step S16 without going through the first tool, and the quantity calculation process may be started.

[0134] In addition, in the above embodiment, the results of area identification and quantity calculation are presented on the display 141, but this embodiment is not limited to this. In this embodiment, the results of area identification and quantity calculation may be output as audio or printed matter.

[0135] In this embodiment, the generative AI system 30 may be configured to dynamically change the combination of tools or procedures to be used depending on the type of design drawing (e.g., floor plan, elevation, cross section, etc.) and the purpose of the estimation (e.g., rough estimate, detailed estimate, material cost estimation only, etc.). This allows for more flexible automation of estimation work.

[0136] Furthermore, if a user requests revisions when accepting approval for the plan in step S15, the generation AI system 30 may be configured to learn the details of the revisions and use them to improve the accuracy of future estimation plans.

[0137] <6.Summary> As described above, the server 20 of this embodiment accepts information related to blueprints. Based on the information related to the blueprints, the server 20 inputs a first prompt including information related to the blueprints and an instruction to execute the estimation process to a generation AI configured to execute an estimation process on the information related to the blueprints so that the first and second tools can be used, thereby selecting a tool to be used. When the first tool is selected, the server 20 uses the first tool to identify an area included in the information related to the blueprints. When the second tool is selected, the server 20 uses the second tool to calculate the quantity of components included in the identified area. This automates the process from blueprint analysis to estimation, thereby improving work efficiency and achieving highly accurate estimation.

[0138] Furthermore, according to this embodiment, the first tool is a trained image recognition model, which allows for efficient and highly accurate area identification from a design drawing.

[0139] Furthermore, according to this embodiment, the second tool is a trained quantity calculation model, which allows for efficient and highly accurate calculation of the quantity of components from the identified area.

[0140] Furthermore, according to this embodiment, in the identifying step, the first tool identifies the areas and contours of multiple rooms included in the information related to the blueprint. As a result, even if the blueprint includes multiple rooms, the area and contours of each room can be identified, and highly accurate cost estimation can be performed.

[0141] Furthermore, according to this embodiment, in the calculation step, the second tool calculates the areas of the floor, ceiling, and walls included in the identified area, as well as the length of the baseboard, which allows for comprehensive estimation of major components in the construction cost estimate, thereby increasing the reliability of the estimate.

[0142] Furthermore, according to this embodiment, in the selection step, the generation AI selects the tool to be used by inputting a second prompt including an instruction statement instructing the generation AI to use the first tool or the second tool according to the input information, thereby achieving an autonomous and flexible integration processing flow according to the input information.

[0143] Furthermore, according to this embodiment, in the selection step, if the input information is a design drawing before machining, the first tool is selected, which allows the first tool to be selected autonomously and enables efficient start of cost estimation processing even for the design drawing before machining.

[0144] According to this embodiment, in the selection step, if the input information is a design drawing whose area is identified by the first tool, the second tool is selected. This allows the second tool to be selected autonomously, enabling flexible response to restarting work after an interruption or partial cost estimation work.

[0145] According to this embodiment, in the selection step, a tool to be used is selected by a generation AI that is fine-tuned based on information about the design drawing, thereby further improving the accuracy of tool selection according to input information.

[0146] According to this embodiment, when a first tool is selected, the server 20 receives a first request from the generation AI to the first tool, and in response to the first request, the server 20 identifies an area included in the information related to the blueprint using the first tool. When a second tool is selected, the server 20 receives a second request from the generation AI to the second tool, and in response to the second request, the server 20 calculates the quantity of components included in the identified area using the second tool. This allows the generation AI to work in cooperation with each tool to automatically and efficiently perform a series of estimation tasks.

[0147] According to this embodiment, in the selection step, a first prompt is input to the generation AI to plan the procedures for the first and second tools to be used. The tools to be used are selected according to the user's approval of the plan. This allows the generation AI to autonomously plan the work, while also achieving both improved accuracy and guaranteed reliability through user intervention.

[0148] <7. Basic computer hardware configuration> 14 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 91, a main memory device 92, an auxiliary memory device 93, and a communication IF (interface) 99. These are electrically connected to each other by a bus.

[0149] The processor 91 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0150] The main storage device 92 is used to temporarily store programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0151] The auxiliary storage device 93 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0152] The communication IF 99 is an interface for inputting and outputting signals for communicating with other computers via a network using wired or wireless communication standards.

[0153] A network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, networks include 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, networks also include those that are directly connected using a USB (Universal Serial Bus) cable, etc.

[0154] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration across multiple computers 90 and interconnecting them via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0155] <8. Basic Functional Configuration of Computer 90> A description will be given of the functional configuration of a computer realized by the basic hardware configuration of a computer 90 shown in Fig. 14. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0156] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 interconnected via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

[0157] The control unit is realized by the processor 91 reading various programs stored in the auxiliary storage device 93, expanding them in the main storage device 92, and executing processing in accordance with the programs. The control unit can realize functional units that perform various types of information processing depending on the type of program. In this way, the computer is realized as an information processing device that processes information.

[0158] The storage unit is realized by a main storage device 92 and an auxiliary storage device 93. The storage unit stores data, various programs, and various databases. Furthermore, the processor 91 can allocate a storage area corresponding to the storage unit in the main storage device 92 or the auxiliary storage device 93 in accordance with the programs. Furthermore, the control unit can cause the processor 91 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0159] A database refers to a relational database, which manages data sets called masters and tables in a tabular format structurally defined by rows and columns, by relating them to each other. In a database, a table is called a table, a master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated.

[0160] Normally, each table and each master has a column set as a primary key to uniquely identify a record, but setting a primary key to a column is not essential. The control unit can cause the processor 91 to add, delete, or update records in specific tables and masters stored in the storage unit according to various programs.

[0161] Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0162] Note that the databases and masters in this disclosure may include any data structure (list, dictionary, associative array, object, etc.) in which information is structurally defined. The data structure also includes data that can be considered as a data structure by combining data with functions, classes, methods, etc. written in any programming language.

[0163] The communication unit is realized by the communication IF 99. The communication unit realizes the function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 91 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0164] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that implements the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for providing such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tape, non-volatile memory cards, and ROMs.

[0165] Furthermore, the program code that realizes the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C / C++, perl, Shell, PHP, and Java (registered trademark).

[0166] Furthermore, the program code of the software that realizes the functions of the embodiments may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read and execute the program code stored in the storage means or storage medium.

[0167] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in a memory.

[0168] In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions.

[0169] If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0170] Although several embodiments of the present disclosure have been described above, these embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are intended to be included in the scope of the inventions and their equivalents as defined in the claims, as well as in the scope and spirit of the inventions.

[0171] (Addendum) The matters described in the above embodiments will be supplemented below.

[0172] (Appendix 1) A program to be executed by a computer including a processor and a memory, the program causing the processor to: accepting information regarding the blueprint; a step of selecting a tool to be used by inputting a first prompt including information about the design plan and an instruction for executing the calculation process to a generation AI configured to execute a calculation process on information about the design plan so that the generation AI can use a first tool and a second tool based on the information about the design plan; if the first tool is selected, identifying an area included in the information about the design drawing using the first tool; When the second tool is selected, calculating the quantity of components included in the identified area by the second tool; A program that executes the following.

[0173] (Appendix 2) The first tool is a trained image recognition model. (Appendix 1) describes the program.

[0174] (Appendix 3) The second tool is a trained quantification model. The program described in (Appendix 1) to (Appendix 2).

[0175] (Appendix 4) In the step of identifying, the first tool identifies areas and contours of a plurality of rooms included in the information related to the blueprint. The program described in (Appendix 1) to (Appendix 3).

[0176] (Appendix 5) The program described in (Appendix 1) to (Appendix 4), wherein in the calculating step, the second tool calculates the areas of the floor, ceiling, and walls included in the identified area, as well as the length of the baseboard.

[0177] (Appendix 6) In the selecting step, a second prompt including an instruction sentence instructing the generation AI to use the first tool or the second tool according to the input information is input to the generation AI, thereby selecting the tool to be used. The program described in (Appendix 1) to (Appendix 5).

[0178] (Appendix 7) In the selecting step, if the input information is the accepted design drawing, the first tool is selected. (Appendix 6) The program described in.

[0179] (Appendix 8) In the selecting step, if the input information is the area specified by the first tool, the second tool is selected. (Appendix 6) The program described in.

[0180] (Appendix 9) In the selecting step, a tool to be used is selected by the generation AI that has been fine-tuned based on information about the design drawing. The program described in (Appendix 1) to (Appendix 8).

[0181] (Appendix 10) If the first tool is selected, a first request is sent from the generation AI to the first tool, and in response to the first request, the first tool identifies the area included in the design drawing; When the second tool is selected, a second request is sent from the generation AI to the second tool, and in response to the second request, the second tool calculates the quantity of the component included in the identified area. The program described in (Appendix 1) to (Appendix 9).

[0182] (Appendix 11) In the selecting step, the first prompt is input to the generation AI to plan the procedures of the first tool and the second tool to be used, and the tool to be used is selected according to the user's approval of the plan. The program described in (Appendix 1) to (Appendix 10).

[0183] (Appendix 12) A method executed by a computer having a processor and a memory, wherein the processor executes all of the steps performed in any of the inventions according to (Appendix 1) to (Appendix 11).

[0184] (Appendix 13) An information processing device comprising a control unit and a memory unit, wherein the control unit executes all of the steps executed in the invention according to any one of (Appendix 1) to (Appendix 11).

[0185] (Appendix 14) A system comprising means for executing all steps performed in any of the inventions according to (Appendix 1) to (Appendix 11). [Explanation of symbols]

[0186] 1. System 10...User terminal 12...Communication IF 13...Input device 14...Output device 15...Memory 16…Storage 19...Processor 20...Server 22...Communication IF 23...Input / output interface 25…Memory 26…Storage 29...Processor 30...Generative AI system

Claims

1. A program to be executed by a computer having a processor and a memory, the program causing the processor to: accepting information regarding the blueprint; A step of selecting a tool to be used by inputting a first prompt including information about the design drawing and an instruction to execute the estimation process to a generation AI configured to execute an estimation process using a first tool and a second tool based on information about the design drawing; If the first tool is selected, identifying an area included in the information about the design drawing using the first tool; When the second tool is selected, calculating the quantity of components included in the identified area by the second tool; A program that executes the following.

2. The first tool is a trained image recognition model. The program according to claim 1.

3. The second tool is a trained quantification model. The program according to claim 1.

4. In the step of identifying, the first tool identifies areas and outlines of a plurality of rooms included in the information related to the blueprint. The program according to claim 1.

5. In the calculating step, the second tool calculates the areas of the floor, ceiling, and walls included in the identified area, and the length of the baseboard. The program according to claim 1.

6. In the selecting step, a second prompt including an instruction sentence instructing the generation AI to use the first tool or the second tool according to input information is input to the generation AI, thereby selecting the tool to be used. The program according to claim 1.

7. In the selecting step, when the input information is a design drawing before processing, the first tool is selected. The program according to claim 6.

8. In the selecting step, when the input information is a design drawing in which the area is identified by the first tool, the second tool is selected. The program according to claim 6.

9. In the selecting step, a tool to be used is selected by the fine-tuned generating AI based on information about the design drawing. The program according to claim 1.

10. If the first tool is selected, a first request is received from the generation AI to the first tool, and in response to the first request, the first tool identifies the area included in the information related to the design drawing; When the second tool is selected, a second request is received from the generation AI to the second tool, and in response to the second request, the second tool calculates the quantity of the component included in the specified area. The program according to claim 1.

11. In the selecting step, the first prompt is input to the generating AI to plan the procedures of the first tool and the second tool to be used, and the tool to be used is selected according to the user's approval of the plan. The program according to claim 1.

12. A method implemented on a computer having a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of claims 1 to 11.

13. 12. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps executed in the invention according to any one of claims 1 to 11.

14. A system comprising means for executing all steps performed in any one of the inventions according to claims 1 to 11.

Images