Information providing method and information providing device

Abstract

By utilizing generative AI, we provide an information provision method that enables highly accurate estimation of the processing price of processed products. [Solution] The information providing method executed by the information providing device 3 includes a question receiving process that receives question information D1, which is drawing information including drawing data related to a processed product; a prompt generation process that generates prompt information D3 that instructs the generative artificial intelligence model 20 to output answer information D4, which is estimate result information including estimate data that is the result of an estimate regarding the processing price of the processed product, based on the question information D1; and an answer providing process that provides answer information D4 output from the generative artificial intelligence model 20 by inputting the prompt information D3 into the generative artificial intelligence model 20.

Description

[Technical Field]

[0001] The present invention relates to an information providing method and an information providing device. [Background technology]

[0002] In recent years, generative artificial intelligence models, known as generative AI or generative AI, have been utilized for a variety of purposes and applications (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2025-074722 Summary of the Invention [Problem to be solved by the invention]

[0004] The system disclosed in Patent Document 1 uses generative AI to set efficient reminders. However, the use of generative AI is not limited to the efficiency of general desk work as in the system disclosed in Patent Document 1, and is also required in a wider variety of fields.

[0005] The present invention has been made in consideration of the above-mentioned problems, and aims to provide an information provision method and information provision device that utilizes generation AI to enable highly accurate estimation of the processing price of processed products. [Means for solving the problem]

[0006] In order to achieve the above object, an information providing method according to one aspect of the present invention comprises: An information providing method for providing information by a computer, comprising: a prompt generation process for generating prompt information that instructs a generative artificial intelligence model to output answer information based on the question information; an answer providing process for providing the answer information output from the generative artificial intelligence model by inputting the prompt information into the generative artificial intelligence model; The question information is Drawing information including drawing data relating to the processed product, The response information is The estimate result information includes estimate data that is the result of an estimate regarding the processing price of the processed product. [Effects of the Invention]

[0007] According to an information providing method of one embodiment of the present invention, by utilizing a generating AI, it is possible to estimate the processing price of a processed product with high accuracy.

[0008] Problems, configurations, and effects other than those described above will become apparent from the detailed description of the invention that follows. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is an overall view showing an example of an information providing system 1. FIG. [Figure 2] FIG. 2 is a block diagram showing an example of an information providing device 3. [Figure 3] FIG. 9 is a hardware configuration diagram showing an example of a computer 900 that constitutes each device. [Figure 4] 1 is a flowchart showing an example of the operation (one stage) of the information providing system 1. [Figure 5] 10 is a flowchart showing an example of the operation (two stages) of the information providing system 1. [Figure 6] 10 is a flowchart showing an example of the operation (three stages) of the information providing system 1. [Figure 7] 10 is a flowchart showing an example of the operation (four stages) of the information providing system 1. [Figure 8] FIG. 10 is a diagram illustrating an example of drawing data. [Figure 9] FIG. 10 is a diagram illustrating an example of a display screen. DETAILED DESCRIPTION OF THE INVENTION

[0010] <Common embodiment: Generated AI> Before proceeding to a detailed description of the present invention, a general description will be given below with reference to the drawings of the behavior common to generative AIs and the basic concepts, configurations, and operations related to their use. This will provide a deeper understanding of the specific embodiments for implementing the present invention, which will be described later. Note that the omitted portions of the description will be based on publicly known technology. The following will show a schematic representation of the scope necessary for the explanation of achieving the objectives of the present invention, and will mainly explain the scope necessary to explain the relevant parts of the present invention. The omitted portions of the description will be based on publicly known technology.

[0011] (System Overview) FIG. 1 is an overall diagram showing an example of an information provision system 1. The information provision system 1 comprises, as its main components, a generative AI device 2, an information provision device 3 that operates in cooperation with the generative AI device 2, a user terminal device 4 used by a user U, and a database device 5 in which various information is stored. Each of the devices 2 to 5 is configured, for example, as a general-purpose or dedicated computer (see FIG. 3 described below), and is connected to a wired or wireless network 6 so as to be able to transmit and receive various types of data to and from each other. Note that the number of the devices 2 to 5 and the connection configuration of the network 6 are not limited to the example of FIG. 1 and may be changed as appropriate.

[0012] The generative AI device 2 is configured, for example, by a server-type computer or a cloud-type computer. The generative AI device 2 includes a generative artificial intelligence model 20, which is called, for example, a generative AI or generative AI. When given instructions by prompt information D3, the generative artificial intelligence model 20 generates answer information D4 in response to the instructions.

[0013] Generative artificial intelligence model 20 is a trained model constructed using a huge training data set and deep learning technology, and may be a base model (for example, a large-scale language model), a multimodal model, etc. Note that generative artificial intelligence model 20 may be provided as a service by an external business operator, in which case generative AI device 2 may be omitted from the components of information provision system 1.

[0014] The information providing device 3 is configured, for example, by a server-type computer or a cloud-type computer. When the information providing device 3 receives question information D1 from the user terminal device 4, it generates prompt information D3 for the generative artificial intelligence model 20 and transmits it to the generative AI device 2. Furthermore, when the information providing device 3 receives answer information D4 by the generative artificial intelligence model 20 from the generative AI device 2, it provides the answer information D4 to the user terminal device 4.

[0015] The user terminal device 4 is configured, for example, as a desktop computer or a portable computer. Programs such as applications and browsers are installed on the user terminal device 4, and the user terminal device 4 accepts various input operations and outputs various information via a display screen or audio. The user terminal device 4 displays a display screen for accepting input operations to input question information D1 and outputting answer information D4, etc., and transmits and receives various data such as question information D1 and answer information D4 to and from the information providing device 3.

[0016] The database device 5 is configured, for example, by a server-type computer or a cloud-type computer. The database device 5 includes a reference information management database 50 (described later). The reference information management database 50 stores reference information D2. The reference information management database 50 can be referenced by each of the devices 2 to 4, and is referenced, for example, when the generative artificial intelligence model 20 generates answer information D4. Furthermore, editing operations such as addition, deletion, and modification are performed on the reference information management database 50 via the information providing device 3 and the user terminal device 4.

[0017] (Summary of each information) Question information D1 is data relating to questions, instructions, or situations related to a specific task or purpose, and is used to prompt the generative artificial intelligence model 20 to generate answer information D4. Question information D1 may be text data in a natural language, image data, audio data, numerical data, structured data, or a combination of these, and is not limited to these, as long as it can be interpreted by the generative artificial intelligence model 20.

[0018] The reference information D2 is information searched and acquired from an external database, knowledge base, or other information source and used as part of the prompt information D3 to enhance the accuracy, comprehensiveness, or specificity (specialization) of the answer information D4 generated by the generative artificial intelligence model 20. The reference information D2 may be dynamically searched and acquired by a search module within the information providing system 1 or an external database search function based on the question information D1 or intermediate answer information D4 generated by the generative artificial intelligence model 20 in a search augmentation generation (RAG) mechanism, or may be provided by being directly included in the question information D1. The reference information D2 may be, but is not limited to, natural language text data (e.g., documents, articles, papers), structured data (e.g., tabular data, JSON data), or a specific data structure such as a knowledge graph, as long as it is available to the generative artificial intelligence model 20.

[0019] Prompt information D3 is information that is input to generative artificial intelligence model 20 in the form of question information D1, instructions, constraints, and / or reference information D2 in order to cause generative artificial intelligence model 20 to perform a specific task or generate answer information D4 in a specific format. Prompt information D3 may mainly be text data in a natural language, and is not limited to this as long as it is compatible with the input format of generative artificial intelligence model 20.

[0020] Answer information D4 is data generated by generative artificial intelligence model 20 based on input question information D1, and is information that provides content that solves the problem or contributes to the purpose indicated by question information D1, or that provides new knowledge or creative works. Answer information D4 is expected to take various forms depending on the function and purpose of use of generative artificial intelligence model 20, such as text data in natural language (e.g., sentences, summaries, codes), image data, audio data, video data, or structured data (e.g., JSON data, XML data), but is not limited to these as long as it can be generated by generative artificial intelligence model 20.

[0021] (Configuration of information providing device 3) 2 is a block diagram showing an example of the information providing device 3. The information providing device 3 includes a control unit 30 configured with a processor or the like, a storage unit 31 configured with an HDD, an SSD, a memory or the like, a communication unit 32 that is a communication interface with the network 6, an input unit 33 configured with a keyboard, a mouse or the like, and a display unit 34 configured with a display or the like. Note that the input unit 33 and the display unit 34 may be omitted.

[0022] The storage unit 31 stores prompt syntax data 310 and an information processing program 311, as well as an operating system, other programs, various types of data, and the like.

[0023] The prompt syntax data 310 is used when generating prompt information D3 from question information D1 and includes multiple syntaxes. Each syntax specifies reference information D2 to be referenced when generating answer information D4, and specifies a task to be assigned to the generative artificial intelligence model 20.

[0024] The control unit 30 executes an information processing program 311 stored in the storage unit 31, thereby functioning as a question receiving unit 300, a prompt generating unit 301, and an answer providing unit 302. Each unit 300 to 302 of the control unit 30 transmits display information for displaying various display screens on the user terminal device 4 to the user terminal device 4, and receives various input operations via the display screens, thereby functioning as a user interface with the user U.

[0025] The question receiving unit 300 performs a question receiving process for receiving question information D1.

[0026] The prompt generation unit 301 performs a prompt generation process to generate prompt information D3 that instructs the generative artificial intelligence model 20 to output answer information D4 while referring to reference information D2, based on question information D1.

[0027] The answer providing unit 302 performs an answer providing process of inputting prompt information D3 to the generative artificial intelligence model 20 and providing answer information D4 output from the generative artificial intelligence model 20.

[0028] (Hardware configuration of each device) 3 is a hardware configuration diagram showing an example of a computer 900 constituting each device. Each of the devices 2 to 5 in the information providing system 1 is constituted by a general-purpose or dedicated computer 900.

[0029] 3, the computer 900 includes, as its main components, a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I / F (interface) unit 922, an external device I / F unit 924, an I / O (input / output) device I / F unit 926, and a media input / output unit 928. Note that the above components may be omitted as appropriate depending on the application of the computer 900.

[0030] The processor 912 is composed of one or more arithmetic processing devices (such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), DSP (Digital Signal Processor), GPU (Graphics Processing Unit), or NPU (Neural Processing Unit)), and operates as a control unit that controls the entire computer 900. The memory 914 stores various data and programs 930, and is composed of, for example, a volatile memory (such as a DRAM or SRAM) that functions as a main memory, a non-volatile memory (ROM), a flash memory, etc.

[0031] The input device 916 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The output device 917 is composed of, for example, a sound (audio) output device, a vibration device, etc., and functions as an output unit. The display device 918 is composed of, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit. The input device 916 and the display device 918 may be integrated into one device, such as a touch panel display. The storage device 920 is composed of, for example, an HDD, an SSD, etc., and functions as a storage unit. The storage device 920 stores various data necessary for executing the operating system and the program 930.

[0032] The communication I / F unit 922 is connected to a network 940 such as the Internet or an intranet (which may be the same as network 6 in FIG. 1) via a wired or wireless connection and functions as a communication unit that transmits and receives data to and from other computers in accordance with a predetermined communication protocol. The external device I / F unit 924 is connected to an external device 950 such as a camera, printer, scanner, or reader / writer via a wired or wireless connection and functions as a communication unit that transmits and receives data to and from the external device 950 in accordance with a predetermined communication protocol. The I / O device I / F unit 926 is connected to an I / O device 960 such as various sensors and actuators and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, to and from the I / O device 960. The media input / output unit 928 is composed of a drive device such as a DVD drive or CD drive, a memory card slot, and a USB connector, and reads and writes data from and to media (non-transitory storage media) 970 such as a DVD, CD, memory card, or USB memory.

[0033] In the computer 900 having the above configuration, the processor 912 loads a program 930 stored in the storage device 920 into the memory 914, executes the program, and controls each unit of the computer 900 via the bus 910. The program 930 may be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded on the medium 970 in an installable file format or an executable file format and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by being downloaded via the communication I / F unit 922 over the network 940. Furthermore, the computer 900 may implement various functions realized by the processor 912 executing the program 930 using hardware such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0034] The computer 900 is an electronic device of any type, such as a desktop computer or a portable computer. The computer 900 may be a client computer, a server computer, a cloud computer, or an embedded computer such as a control panel or a controller (including a microcomputer, a programmable logic controller, or a sequencer).

[0035] (Operation of information provision system 1) The following describes a series of operations performed by the information provision system 1. The series of operations is performed by cooperation between the units 300 to 302 of the information provision device 3 (each process of the information provision method executed by the information processing program 311), the generative AI device 2, the user terminal device 4, and the database device 5.

[0036] (for one-step prompt) 4 is a flowchart showing an example of the operation (first stage) of the information providing system 1. In the following, it is assumed that the reference information D2 is registered in the reference information management database 50.

[0037] First, in step S100, the user terminal device 4 transmits to the information providing device 3 question information D1 based on an input operation by the user U on the display screen.

[0038] Next, in step S110 (question reception process), the question reception unit 300 of the information providing device 3 receives the question information D1 transmitted in step S100, thereby accepting the question information D1.

[0039] Next, in step S200 (prompt generation process), the prompt generation unit 301 generates prompt information D3 that instructs the generative artificial intelligence model 20 to output answer information D4 while referring to reference information D2, based on the question information D1 received in step S110.

[0040] Next, in step S210 (answer providing process), the answer providing unit 302 inputs the prompt information D3 generated in step S200 into the generative artificial intelligence model 20, thereby generating answer information D4 as an output result from the generative artificial intelligence model 20.

[0041] Next, in step S220 (answer providing process), the answer providing unit 302 transmits display screen information for displaying the answer information D4 generated in step S210 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the prompt information D3 generated in step S200.

[0042] Next, in step S230, upon receiving the display screen information transmitted in step S220, the user terminal device 4 displays a display screen including the answer information D4 based on the display screen information.

[0043] By carrying out the above series of processes, answer information D4 to the question information D1 is provided to the user U. When the user U inputs new question information D1, the above series of processes is carried out in the same manner.

[0044] (for two-step prompt) Fig. 5 is a flowchart showing an example of the operation (two stages) of the information providing system 1. The flow shown in Fig. 5 differs from the flow shown in Fig. 4 in that a multi-stage prompt (two stages) is used. The following description will be given assuming that reference information D2 is registered in the reference information management database 50.

[0045] 5, prompt information D3 refers to either first prompt information D3A or second prompt information D3B, answer information D4 refers to either first answer information D4A or second answer information D4B, and reference information D2 refers to either first reference information D2A or second reference information D2B.

[0046] The first answer information D4A is the first output result obtained from the generative artificial intelligence model 20. The first prompt information D3A is information that instructs the generative artificial intelligence model 20 to output the first answer information D4A based on the question information D1 while referring to the first reference information D2A.

[0047] The second answer information D4B is a second output result obtained from the generative artificial intelligence model 20 and is the final answer to the question information D1. The second prompt information D3B is information that instructs the generative artificial intelligence model 20 to output the second answer information D4B based on the first answer information D4A while referring to the second reference information D2B.

[0048] First, in step S100, the user terminal device 4 transmits to the information providing device 3 question information D1 based on an input operation by the user U on the display screen.

[0049] Next, in step S110 (question reception process), the question reception unit 300 of the information providing device 3 receives the question information D1 transmitted in step S100, thereby accepting the question information D1.

[0050] Next, in step S200 (first prompt generation process), the prompt generation unit 301 generates first prompt information D3A that instructs the generative artificial intelligence model 20 to output first answer information D4A while referring to the first reference information D2A, based on the question information D1 received in step S110.

[0051] Next, in step S210 (first answer providing process), the answer providing unit 302 inputs the first prompt information D3A generated in step S200 into the generative artificial intelligence model 20, thereby generating first answer information D4A as an output result from the generative artificial intelligence model 20.

[0052] Next, in step S220 (first answer providing process), the answer providing unit 302 transmits display screen information for displaying the first answer information D4A generated in step S210 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the first prompt information D3A generated in step S200.

[0053] Next, in step S230, upon receiving the display screen information transmitted in step S220, the user terminal device 4 displays a display screen including the first response information D4A based on the display screen information.

[0054] Next, in step S240 (second prompt generation process), the prompt generation unit 301 generates second prompt information D3B based on the first answer information D4A generated in step S210, which instructs the generative artificial intelligence model 20 to output second answer information D4B while referring to the second reference information D2B.

[0055] Next, in step S250 (second answer providing process), the answer providing unit 302 inputs the second prompt information D3B generated in step S240 into the generative artificial intelligence model 20, thereby generating second answer information D4B as an output result from the generative artificial intelligence model 20.

[0056] Next, in step S260 (second answer providing process), the answer providing unit 302 transmits display screen information for displaying the second answer information D4B generated in step S250 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the second prompt information D3B generated in step S240.

[0057] Next, in step S270, upon receiving the display screen information transmitted in step S260, the user terminal device 4 displays a display screen including the second answer information D4B based on the display screen information.

[0058] By performing the above series of processes, second answer information D4B, which is the final answer to the question information D1, is provided to the user U. Note that when the user U inputs new question information D1, the above series of processes is performed in the same manner.

[0059] (Three-step prompt) Fig. 6 is a flowchart showing an example of the operation (three stages) of the information providing system 1. The flow shown in Fig. 6 differs from the flows shown in Figs. 4 and 5 in that it uses a multi-stage prompt (three stages). The following description will be given assuming that reference information D2 is registered in the reference information management database 50.

[0060] 6, prompt information D3 refers to any one of first prompt information D3A, second prompt information D3B, or third prompt information D3C. Answer information D4 refers to any one of first answer information D4A, second answer information D4B, or third answer information D4C. Reference information D2 refers to any one of first reference information D2A, second reference information D2B, or third reference information D2C.

[0061] The first answer information D4A is the first output result obtained from the generative artificial intelligence model 20. The first prompt information D3A is information that instructs the generative artificial intelligence model 20 to output the first answer information D4A based on the question information D1 while referring to the first reference information D2A.

[0062] The second answer information D4B is a second output result obtained from the generative artificial intelligence model 20, and is an intermediate answer to the question information D1. The second prompt information D3B is information that instructs the generative artificial intelligence model 20 to output the second answer information D4B based on the first answer information D4A while referring to the second reference information D2B.

[0063] The third answer information D4C is the third output result obtained from the generative artificial intelligence model 20 and is the final answer to the question information D1. The third prompt information D3C is information that instructs the generative artificial intelligence model 20 to output the third answer information D4C based on the second answer information D4B and with reference to the third reference information D2C.

[0064] First, in step S100, the user terminal device 4 transmits to the information providing device 3 question information D1 based on an input operation by the user U on the display screen.

[0065] Next, in step S110 (question reception process), the question reception unit 300 of the information providing device 3 receives the question information D1 transmitted in step S100, thereby accepting the question information D1.

[0066] Next, in step S200 (first prompt generation process), the prompt generation unit 301 generates first prompt information D3A that instructs the generative artificial intelligence model 20 to output first answer information D4A while referring to the first reference information D2A, based on the question information D1 received in step S110.

[0067] Next, in step S210 (first answer providing process), the answer providing unit 302 inputs the first prompt information D3A generated in step S200 into the generative artificial intelligence model 20, thereby generating first answer information D4A as an output result from the generative artificial intelligence model 20.

[0068] Next, in step S220 (first answer providing process), the answer providing unit 302 transmits display screen information for displaying the first answer information D4A generated in step S210 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the first prompt information D3A generated in step S200.

[0069] Next, in step S230, upon receiving the display screen information transmitted in step S220, the user terminal device 4 displays a display screen including the first response information D4A based on the display screen information.

[0070] Next, in step S240 (second prompt generation process), the prompt generation unit 301 generates second prompt information D3B based on the first answer information D4A generated in step S210, which instructs the generative artificial intelligence model 20 to output second answer information D4B while referring to the second reference information D2B.

[0071] Next, in step S250 (second answer providing process), the answer providing unit 302 inputs the second prompt information D3B generated in step S240 into the generative artificial intelligence model 20, thereby generating second answer information D4B as an output result from the generative artificial intelligence model 20.

[0072] Next, in step S260 (second answer providing process), the answer providing unit 302 transmits display screen information for displaying the second answer information D4B generated in step S250 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the second prompt information D3B generated in step S240.

[0073] Next, in step S270, upon receiving the display screen information transmitted in step S260, the user terminal device 4 displays a display screen including the second answer information D4B based on the display screen information.

[0074] Next, in step S300 (third prompt generation process), the prompt generation unit 301 generates third prompt information D3C based on the second answer information D4B generated in step S250, which instructs the generative artificial intelligence model 20 to output the third answer information D4C while referring to the third reference information D2C.

[0075] Next, in step S310 (third answer providing process), the answer providing unit 302 inputs the third prompt information D3C generated in step S300 into the generative artificial intelligence model 20, thereby generating third answer information D4C as an output result from the generative artificial intelligence model 20.

[0076] Next, in step S320 (third answer providing process), the answer providing unit 302 transmits display screen information for displaying the third answer information D4C generated in step S310 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the third prompt information D3C generated in step S300.

[0077] Next, in step S330, upon receiving the display screen information transmitted in step S320, the user terminal device 4 displays a display screen including the third answer information D4C based on the display screen information.

[0078] By performing the above series of processes, third answer information D4C, which is the final answer to the question information D1, is provided to the user U. Note that when the user U inputs new question information D1, the above series of processes is performed in the same manner.

[0079] (Four-step prompt) Fig. 7 is a flowchart showing an example of the operation (four stages) of the information providing system 1. The flow shown in Fig. 7 differs from the flows shown in Figs. 4, 5, and 6 in that it uses multi-stage prompts (four stages). The following description will be given assuming that reference information D2 is registered in the reference information management database 50.

[0080] 7, prompt information D3 refers to any one of first prompt information D3A, second prompt information D3B, third prompt information D3C, or fourth prompt information D3D. Answer information D4 refers to any one of first answer information D4A, second answer information D4B, third answer information D4C, or fourth answer information D4D. Reference information D2 refers to any one of first reference information D2A, second reference information D2B, third reference information D2C, or fourth reference information D2D.

[0081] The first answer information D4A is the first output result obtained from the generative artificial intelligence model 20. The first prompt information D3A is information that instructs the generative artificial intelligence model 20 to output the first answer information D4A based on the question information D1 while referring to the first reference information D2A.

[0082] The second answer information D4B is a second output result obtained from the generative artificial intelligence model 20, and is an intermediate answer to the question information D1. The second prompt information D3B is information that instructs the generative artificial intelligence model 20 to output the second answer information D4B based on the first answer information D4A while referring to the second reference information D2B.

[0083] The third answer information D4C is a third output result obtained from the generative artificial intelligence model 20, and is an intermediate answer to the question information D1. The third prompt information D3C is information that instructs the generative artificial intelligence model 20 to output the third answer information D4C based on the second answer information D4B and with reference to the third reference information D2C.

[0084] The fourth answer information D4D is the fourth output result obtained from the generative artificial intelligence model 20 and is the final answer to the question information D1. The fourth prompt information D3D is information that instructs the generative artificial intelligence model 20 to output the fourth answer information D4D based on the third answer information D4C and with reference to the fourth reference information D2D.

[0085] First, in step S100, the user terminal device 4 transmits to the information providing device 3 question information D1 based on an input operation by the user U on the display screen.

[0086] Next, in step S110 (question reception process), the question reception unit 300 of the information providing device 3 receives the question information D1 transmitted in step S100, thereby accepting the question information D1.

[0087] Next, in step S200 (first prompt generation process), the prompt generation unit 301 generates first prompt information D3A that instructs the generative artificial intelligence model 20 to output first answer information D4A while referring to the first reference information D2A, based on the question information D1 received in step S110.

[0088] Next, in step S210 (first answer providing process), the answer providing unit 302 inputs the first prompt information D3A generated in step S200 into the generative artificial intelligence model 20, thereby generating first answer information D4A as an output result from the generative artificial intelligence model 20.

[0089] Next, in step S220 (first answer providing process), the answer providing unit 302 transmits display screen information for displaying the first answer information D4A generated in step S210 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the first prompt information D3A generated in step S200.

[0090] Next, in step S230, upon receiving the display screen information transmitted in step S220, the user terminal device 4 displays a display screen including the first response information D4A based on the display screen information.

[0091] Next, in step S240 (second prompt generation process), the prompt generation unit 301 generates second prompt information D3B based on the first answer information D4A generated in step S210, which instructs the generative artificial intelligence model 20 to output second answer information D4B while referring to the second reference information D2B.

[0092] Next, in step S250 (second answer providing process), the answer providing unit 302 inputs the second prompt information D3B generated in step S240 into the generative artificial intelligence model 20, thereby generating second answer information D4B as an output result from the generative artificial intelligence model 20.

[0093] Next, in step S260 (second answer providing process), the answer providing unit 302 transmits display screen information for displaying the second answer information D4B generated in step S250 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the second prompt information D3B generated in step S240.

[0094] Next, in step S270, upon receiving the display screen information transmitted in step S260, the user terminal device 4 displays a display screen including the second answer information D4B based on the display screen information.

[0095] Next, in step S300 (third prompt generation process), the prompt generation unit 301 generates third prompt information D3C based on the second answer information D4B generated in step S250, which instructs the generative artificial intelligence model 20 to output the third answer information D4C while referring to the third reference information D2C.

[0096] Next, in step S310 (third answer providing process), the answer providing unit 302 inputs the third prompt information D3C generated in step S300 into the generative artificial intelligence model 20, thereby generating third answer information D4C as an output result from the generative artificial intelligence model 20.

[0097] Next, in step S320 (third answer providing process), the answer providing unit 302 transmits display screen information for displaying the third answer information D4C generated in step S310 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the third prompt information D3C generated in step S300.

[0098] Next, in step S330, upon receiving the display screen information transmitted in step S320, the user terminal device 4 displays a display screen including the third answer information D4C based on the display screen information.

[0099] Next, in step S340 (fourth prompt generation process), the prompt generation unit 301 generates fourth prompt information D3D based on the third answer information D4C generated in step S310, which instructs the generative artificial intelligence model 20 to output fourth answer information D4D while referring to the fourth reference information D2D.

[0100] Next, in step S350 (fourth answer providing process), the answer providing unit 302 inputs the fourth prompt information D3D generated in step S340 into the generative artificial intelligence model 20, thereby generating fourth answer information D4D as an output result from the generative artificial intelligence model 20.

[0101] Next, in step S360 (fourth answer providing process), the answer providing unit 302 transmits display screen information for displaying the fourth answer information D4D generated in step S350 to the user terminal device 4 that is the sender of the question information D1. At this time, the display screen information may include the fourth prompt information D3D generated in step S340.

[0102] Next, in step S370, upon receiving the display screen information transmitted in step S360, the user terminal device 4 displays a display screen including the fourth answer information D4D based on the display screen information.

[0103] By performing the above series of processes, fourth answer information D4D, which is the final answer to the question information D1, is provided to the user U. Note that when the user U inputs new question information D1, the above series of processes is performed in the same manner.

[0104] In the following first to fourth embodiments, the explanation will be focused on the case where, when an intermediary (user) using a user terminal device 4 receives a request for an estimate for the target drawing data from an ordering party, the information providing device 3 makes an estimate, generates estimate result information including estimate data that is the result of the estimate, and provides the estimate result information to the user.

[0105] First Embodiment Next, a first embodiment for carrying out the present invention will be described with reference to the drawings of the common embodiment described above. Note that detailed descriptions of the functions and connections of each component in the system, various data handled by each component, the configuration and operation of each part in each device, various data handled by each device, and the operation and configuration in the flowcharts that are the same as those of the common embodiment will be omitted.

[0106] (Overview of the system according to the first embodiment) The information providing system 1 functions as a system that provides information related to drawing data that includes drawing elements related to processed products.

[0107] The drawing data handled by the information providing system 1 is, for example, any drawing recorded as digital data, such as mechanical drawings such as assembly drawings and parts drawings, architectural drawings, electrical circuit drawings, pneumatic circuit drawings, hydraulic circuit drawings, apparel drawings, etc. In this case, the drawing data may be vector format data or raster format data. For example, the drawing data may be CAD data (an example of vector format) output by various CAD software, or image data (an example of raster format) output by scanning a drawing printed on paper media with a scanner or the like. The drawing data may be drawn using any projection method, and may also be a three-dimensional drawing.

[0108] (Outline of each piece of information according to the first embodiment) The question information D1 is drawing information including drawing data related to the processed product. The drawing information may include text data in which text representing information related to the drawing from the user is recorded along with the drawing data. The drawing data may be input as a file in which the drawing data is recorded in any data format, or as a reference file name for referencing the file in which the drawing data is recorded.

[0109] The drawing information may also include additional information to supplement the information about the processed product, such as the shape category, dimensions, geometric tolerance, material, hardness, processing quantity, drawing number, customer name, and delivery date of the processed product, but is not limited to these, and may also be tabular information, remarks, handwritten information, etc.

[0110] The shape category is a classification of the outer shape of a material before processing or the outer shape of a processed product after processing. Examples of shape categories include, but are not limited to, "plate," "rod," and "pipe."

[0111] Dimensions are expressions of the outer shape of a material before processing or the outer shape of a processed product using two or more variables. Dimensions may be expressed using, for example, three variables (width x length x thickness), three variables (outer diameter x inner diameter x length), or two variables (outer diameter x length), but are not limited to these. Different dimension expressions may also be used depending on the shape category. For example, if the shape category is "plate," the dimension may be expressed using three variables (width x length x thickness), and if the shape category is "rod" or "tube," the dimension may be expressed using three variables (outer diameter x inner diameter x length).

[0112] The material refers to the material of the raw material before processing. The material may be specified by either the formal name or the abbreviated name.

[0113] 8 is a diagram showing an example of drawing data. The drawing area 10 of the drawing data corresponds to the entire area of ​​the paper when the drawing data is printed on a paper medium. In the drawing area 10 of the drawing data, for example, a shape area 11, a title block 12, a header block 13, a footer block 14, and a memo area 15 are arranged as drawing elements. Note that drawing elements other than those mentioned above may also be arranged in the drawing area 10.

[0114] The shape region 11 is an area where the shape and dimensions of an assembly or part are described using lines, characters (including symbols), figures, etc. Shape lines defining the shape and structure of an assembly or part, such as outline lines, dimension lines, hidden lines, center lines, and imaginary lines, are described in the shape region 11. Characters indicating dimensions, tolerances, part numbers, etc. are also described in the shape region 11. An attribute called a drawing feature is assigned to the shape region 11, and vector data representing the features of the shape region 11 as a fixed-length numerical array is acquired as the attribute value through feature recognition processing. The shape region 11 is not limited to a six-sided drawing based on an orthographic projection, but may represent other types of drawings, such as a cross-sectional view, a perspective view, or an exploded view. While the example of FIG. 8 shows two shape regions 11, the number may be one or three or more.

[0115] The title block 12 is a type of table included in the drawing data. The table has vertical and horizontal lines and boxes 120 separated by the lines. Each box 120 is assigned the attributes of the characters written in the box 120, and the characters written in the box 120 are acquired as attribute values ​​through character recognition processing. As shown in FIG. 8 , the attributes of each box 120 in the title block 12 include, for example, company name, draftsman, drafting method, scale, quantity, material, part name, and part number. The entire title block 12 may be treated as a single drawing element, or each of the multiple boxes 120 in the title block 12 may be treated as a single drawing element. Note that the type of table included in the drawing data is not limited to the title block 12 and may be, for example, a parts list or other type of table. The arrangement and number of boxes 120 constituting the table may be changed as appropriate depending on the type of table, and the attributes assigned to each box 120 are not limited to the above example.

[0116] The header field 13 is an area located at the top of the paper, and any information related to the drawing data is entered in the header field 13. The header field 13 is assigned an attribute called a header, and characters entered in the header field 13 are acquired as attribute values ​​through character recognition processing. In the example of FIG. 8, the header field 13 contains information about the fax sender, but this is not limiting. Also, although there is one header field 13 in the example of FIG. 8, there may be two or more.

[0117] The footer field 14 is an area located at the bottom of the page, and any information related to the drawing data is entered in the footer field 14. The footer field 14 is assigned an attribute called a footer, and characters entered in the footer field 14 are acquired as attribute values ​​through character recognition processing. In the example of FIG. 8, the footer field 14 contains information about the fax recipient, but this is not limiting. Also, although there is one footer field 14 in the example of FIG. 8, there may be two or more.

[0118] The memo area 15 is an area where any characters written by hand are arranged. An attribute called a handwritten memo is assigned to the memo area 15, and the characters written by hand are acquired as attribute values ​​by character recognition processing. Note that, although there are two memo areas 15 in the example of FIG. 8, there may be one, or three or more.

[0119] The reference information D2 is estimate generation information that contributes to generating an estimate based on drawing data. The estimate generation information includes, for example, drawing processing information, similar drawing search information, process prediction information, estimate calculation information, evaluation information, and custom information.

[0120] The drawing processing information is information used by the generative artificial intelligence model 20 to handle input drawing data. Specifically, using a technology known as Function Calling, the information includes function definition specifications for calling external functions, etc., to search for similar drawings, and information defining the format of structured instruction information for instructing the generative artificial intelligence model 20 to execute such functions. This enables the generative artificial intelligence model 20 to instruct an external program to perform appropriate processing according to the contents of the drawing data.

[0121] Similar drawing search information is information used to search for existing drawing data stored in a database that has similar characteristics to newly input drawing data. The similar drawing search information includes, for example, the name of a tool (external function) for performing a vector search that vectorizes the characteristics of the drawing data and evaluates the similarity, and a specification definition for calling that function.

[0122] Process prediction information is know-how used to predict the specific machining steps and machining time when machining a processed product based on drawing data. Process prediction information includes empirical rules and calculation logic based on past machining results, such as an increase or decrease in the number of setups depending on the number of cutting surfaces required for machining, changes in machining speed due to the hardness and properties of the material, or the standard time required for a specific machining shape (for example, drilling a hole of a specific diameter).

[0123] The estimate calculation information is information for specifically calculating the processing price based on the predicted processing steps and materials to be used. The estimate calculation information includes a basic calculation formula for calculating the total estimated price based on the processing cost, material cost, and other costs, a coefficient to multiply the processing cost according to a specific material list, and rules regarding safety margins for adjusting the price according to the difficulty of processing.

[0124] Evaluation information is used to verify the validity and accuracy of generated estimates. It includes, for example, items for verifying the accuracy of dimensions and materials recognized from drawing data, criteria for comparing and verifying whether there are significant discrepancies between past processing results for existing drawing data similar to the target drawing data and the predicted process and processing time, and evaluation logic for verifying whether the price has significantly changed from previous estimates in the case of repeat products. Evaluation information, for example, consists of a set of rules that set thresholds for similarity and acceptable differences, defining criteria such as "the difference in estimated price for drawings with a similarity of 95% should be within 5%" or "the processing process should be completely consistent for drawings with a similarity of 100%." ​​It may also include information for comparing the estimated price with the results of past similar projects to assess whether it is within a market-competitive price range.

[0125] Custom information is information that reflects the unique know-how of a specific user or company. Custom information includes process prediction rules that correspond to special processing patterns unique to a company, which differ from standard calculation logic, and unique estimate calculation formulas, and is used to customize the estimate generation process by the information providing device 3.

[0126] The response information D4 is estimate result information including estimate data that is the result of an estimate on the processing price of the processed product when the processed product is processed based on the drawing data. Attributes included in the estimate data include, for example, the estimate date and time, the estimated price, the response delivery date, and the estimate expiration date.

[0127] The estimate date and time is the date and time when the intermediary used the information providing device 3 to estimate the processing price of the processed product based on the drawing data. The replied delivery date is the intermediary's reply to the desired delivery date presented by the client. The estimate expiration date is the deadline during which the estimate result created by the intermediary using the information providing device 3 is valid.

[0128] The estimated price is the total cost required to process the processed product shown in the drawing data. The estimated price is calculated by adding up multiple cost items such as material costs, processing costs, and management costs.

[0129] The material cost is calculated by multiplying the weight and volume of the processed product, which are calculated based on the material and shape dimensions specified in the drawing information, by the material unit price stored in advance in the reference information management database 50.

[0130] Processing costs are calculated by analyzing the characteristics of the processed product from the drawing data (for example, complexity of shape, dimensional tolerance, surface roughness, etc.), and multiplying the estimated processing time based on past similar cases and a predetermined calculation logic by the processing cost per hour, including equipment and labor costs. In addition, if special processes such as heat treatment or surface treatment are required, the processing costs will also be included.

[0131] The management fee includes overhead costs and profits, and is calculated by, for example, multiplying the total of material costs and processing costs by a predetermined rate. The information providing device 3 calculates and adds up each of these cost items to determine the final estimated price.

[0132] The response information D4 may include, in addition to the estimate result information, estimate basis information regarding the basis of the estimate. The estimate basis information is information regarding the basis of the estimate. The estimate basis information is, for example, a description in natural language of the difference between the target drawing data and other drawing data similar to the target drawing data, the reason for estimating the processing type (described below), the reason for estimating the processing time (described below), etc. The estimate basis information may also include the result of determining whether there is an error in the estimate result.

[0133] (Operation of the information providing system 1 according to the first embodiment) The information provision system according to the first embodiment operates in accordance with the flowchart shown in Fig. 4. In this embodiment, the case where prompt information D3 is generated based on question information D1 while referencing reference information D2 has been described, but if it is desired to quickly obtain answer information D4 from the generative artificial intelligence model 20, prompt information D3 may be generated based on question information D1 without referencing reference information D2.

[0134] As described above, according to the information providing device 3 and information providing method of the first embodiment, when prompt information D3 generated based on question information D1 while referencing reference information D2 is input to the generative artificial intelligence model 20, answer information D4 is output from the generative artificial intelligence model 20. Therefore, the processing price of a processed product can be estimated with high accuracy. Furthermore, when prompt information D3 is generated based on question information D1 without referencing reference information D2, answer information D4 can be efficiently obtained from the generative artificial intelligence model 20.

[0135] <Second embodiment> Next, a second embodiment for carrying out the present invention will be described with reference to the drawings of the common embodiment described above. Note that detailed descriptions of the functions and connections of each component in the system, various data handled by each component, the configuration and operation of each part in each device, various data handled by each device, and the operation and configuration in the flowcharts that are the same as those of the common embodiment or the first embodiment will be omitted.

[0136] (Overview of the system according to the second embodiment) The database device 5 includes a drawing database 51 (not shown). The drawing database 51 stores drawing data, order source data, processed product characteristic data, processing estimation data, estimate data, and processing performance data in association with each piece of drawing data. The drawing database 51 can be referenced by each of the devices 2 to 4, and is referenced, for example, when the generative artificial intelligence model 20 generates response information D4. Furthermore, the drawing database 51 is subjected to editing operations such as addition, deletion, and modification via the information providing device 3 and the user terminal device 4.

[0137] The orderer data is data related to the orderer of the estimate in the drawing data. Attributes included in the orderer data include the estimate request date and time, the orderer's company name, the person in charge, and the desired delivery date. The orderer's company name and person in charge are selected from an orderer list in which multiple company names and people are registered in advance, and for example, an identifier uniquely assigned to each company name and person in charge is registered. Note that orderer's company names and people in charge that are not registered in the orderer list are newly registered in the orderer list.

[0138] The processed product characteristic data is data relating to the characteristics of the processed product in the drawing data. The processed product characteristic data is acquired from shape lines, characters, symbols, etc. included in the shape area 11, and characters included in the title column 12, header column 13, footer column 14, and memo area 15. Examples of attributes included in the processed product characteristic data include, but are not limited to, company name, draftsman, drawing method, scale, quantity, material, part name, part number, shape, maximum dimension, surface treatment, welding, hole processing, drawing feature, header (not shown), footer (not shown), handwritten memo (not shown), etc.

[0139] For each attribute included in the processed product characteristic data, an attribute value in a data format corresponding to the attribute is registered. For attributes related to the company name, drafter, part name, and part number, a character string is registered as the attribute value. For attributes related to the drafting method, scale, material, shape, surface treatment, and welding, a value selected from multiple options prepared in advance is registered as the attribute value. For the shape, for example, "circle" may be selected and registered from options such as plate, bar, pipe, and circle. For attributes related to the quantity, maximum dimension, and hole drilling, a numerical value is registered as the attribute value. For example, the numerical value "60" may be registered as the maximum dimension. For attributes related to hole drilling, for example, multiple attributes combining the hole diameter and the drilling method (e.g., drilling, countersinking, countersinking, etc.) are listed, but this is not limited to these. For attributes related to drawing features, vector data is registered as the attribute value.

[0140] The processing estimation data is data relating to the estimated results of processing when a processed product is processed based on drawing data. Attributes included in the processing estimation data define the details of the processing, such as the processing type, processing step, and processing time. For example, if three processing steps, "rough processing," "finishing processing," and "inspection," are performed, the estimated results of the processing time for each processing step may be registered.

[0141] The processing type is defined as a classification of the combination and sequence of processing steps by pattern. For example, if there are two patterns of a series of processing steps, "setup → CAD → CAM → machining → finishing → inspection → packaging," and "setup → CAD → CAM → router processing → finishing → inspection → packaging," these can be defined as processing types, "machining processing" and "router processing," respectively. The classification of processing types may not only be defined based on the processing equipment or manual labor used in the processing steps, but may also be defined by other methods. For example, processing types may be defined based on the processing method, such as "molding processing," "removal processing," or "additive processing." If a processed product is processed through multiple processing steps, the processing time may be the processing time for each processing step.

[0142] The processing performance data is data relating to the results of processing when a processed product is processed based on drawing data. The attributes included in the processing performance data define the details of the processing, such as processing date and time, client, actual processing type, processing device, processing worker, actual processing step, actual processing time, actual processing price, result calculation formula, actual value, etc.

[0143] The actual processing price is the price of the processing actually performed on the processed product. The actual calculation formula is the calculation formula actually used when calculating the actual processing price. The actual calculation formula is a formula including one or more variables. The actual value is a real number substituted for the variable included in the actual calculation formula. For example, the actual calculation formula for a processing step called "rough processing" is expressed as the product of "labor cost" and "processing time", and the numerical values ​​"250" and "6" may be registered as the attribute values ​​of the actual value substituted for the variables "labor cost" and "processing time" of the actual calculation formula, respectively. Note that the actual calculation formula is not limited to a two-variable function, but may also be a constant or a multi-variable function, and is not limited to these.

[0144] The request destination is selected from a request destination list in which a plurality of request destinations are registered in advance, and for example, a uniquely assigned identifier is registered for each request destination. The processing device is selected from a processing device list in which a plurality of processing devices are registered in advance, and for example, a uniquely assigned identifier is registered for each processing device. The processing device list stores, for example, the identifier, device name, and device performance of the processing device in list form. The device performance is categorized into multiple levels, for example, low, medium, and high. The processing worker is selected from a processing worker list in which a plurality of processing workers are registered in advance, and for example, a uniquely assigned identifier is registered for each processing worker. The processing worker list stores, for example, the identifier, worker name, and skill level of the processing worker in list form. The skill level is categorized into multiple levels, for example, low, medium, and high.

[0145] The drawing database 210 may be configured to allow data other than those described above to be registered, and the data formats of the attributes and attribute values ​​included in each data item are not limited to the above examples.

[0146] (Outline of each piece of information according to the second embodiment) In the second embodiment, prompt information D3 refers to either first prompt information D3A or second prompt information D3B. Answer information D4 refers to either first answer information D4A or second answer information D4B. Reference information D2 refers to either first reference information D2A or second reference information D2B. First answer information D4A is similar drawing information that is existing drawing data stored in a database and includes existing drawing data whose processed product features are similar to those of the target drawing data. First prompt information D3A is information that instructs generative artificial intelligence model 20 to output first answer information D4A based on question information D1.

[0147] The second response information D4B is estimate result information including estimate data that is the result of an estimate regarding the processing price of the processed product, and the second prompt information D3B is information that instructs the generative AI model 20 to output the second response information D4B based on the first response information D4A. Specifically, the second prompt information D3B instructs the generative AI model 20 to compare the target drawing data included in the question information D1 with similar existing drawing data included in the first response information D4A (and the associated processed product characteristic data, processing estimation data, estimate data, and processing performance data, etc.), and to generate an estimate of the processing price for the target drawing data by taking into account the differences (e.g., differences in dimensions, material, and processing quantity). This generates highly accurate estimate result information for the new target drawing data based on the performance of past estimates.

[0148] The question information D1 is drawing information. Note that the drawing information is the same as the drawing information in the first embodiment, so a detailed description will be omitted (see paragraphs 0108-0109).

[0149] The first reference information D2A is similar drawing search information. Note that the similar drawing search information is the same as the similar drawing search information in the first embodiment, so a detailed description thereof will be omitted (see paragraph 0121).

[0150] The second reference information D2B is estimate generation information that contributes to generating an estimate based on drawing data. The estimate generation information includes, for example, drawing processing information, process prediction information, estimate calculation information, evaluation information, and custom information. The drawing processing information, process prediction information, estimate calculation information, evaluation information, and custom information are the same as the drawing processing information, process prediction information, estimate calculation information, evaluation information, and custom information in the first embodiment, respectively, and therefore detailed description thereof will be omitted (see paragraphs 0120 and 0122-0125).

[0151] The first response information D4A is similar drawing information that includes existing drawing data stored in the drawing database 51 and that has characteristics of a processed product similar to those of the target drawing data. The existing drawing data similar to the target drawing data may be one existing drawing data with the highest similarity, or multiple existing drawing data with similarities up to a predetermined ranking.

[0152] The second response information D4B is estimate result information. Note that the estimate result information is the same as the estimate result information in the first embodiment, so a detailed description will be omitted (see paragraphs 0126-0132).

[0153] (Operation of the information providing system 1 according to the second embodiment) The information providing system according to the second embodiment operates according to the flowchart shown in Fig. 5. However, it is assumed that the drawing database 51 stores a plurality of existing drawing data.

[0154] In this embodiment, we have described a case where the second prompt information D3B is generated based on the first answer information D4A while referring to the second reference information D2B, but the second prompt information D3B may also be generated based on the question information D1 and the first answer information D4A.

[0155] In this embodiment, the first prompt information D3A is generated based on question information D1 while referencing first reference information D2A, but if it is desired to quickly obtain first answer information D4A from generative artificial intelligence model 20, the first prompt information D3A may be generated based on question information D1 without referencing first reference information D2A. In addition, in this embodiment, the second prompt information D3B is generated based on first answer information D4A while referencing second reference information D2B, but if it is desired to quickly obtain second answer information D4B from generative artificial intelligence model 20, the second prompt information D3B may be generated based on first answer information D4A without referencing second reference information D2B.

[0156] As described above, according to the information providing device 3 and information providing method of the second embodiment, when first prompt information D3A generated based on question information D1 while referring to first reference information D2A is input to the generative AI model 20, first answer information D4A is output from the generative AI model 20. When second prompt information D3B generated based on the first answer information D4A while referring to second reference information D2B is input to the generative AI model 20, second answer information D4B is output from the generative AI model 20. Therefore, the processing price of a processed product can be estimated with higher accuracy. Furthermore, when the first prompt information D3A or the second prompt information D3B is generated without referring to the reference information D2, answer information D4 can be efficiently obtained from the generative AI model 20.

[0157] <Third embodiment> Next, a third embodiment for carrying out the present invention will be described with reference to the drawings of the common embodiment described above. Note that detailed descriptions of the functions and connections of each component in the system, various data handled by each component, the configuration and operation of each part in each device, various data handled by each device, and the operation and configuration in the flowcharts that are the same as those of the common embodiment, the first embodiment, or the second embodiment will be omitted.

[0158] (Outline of each piece of information according to the third embodiment) In the third embodiment, prompt information D3 refers to any one of first prompt information D3A, second prompt information D3B, or third prompt information D3C. Answer information D4 refers to any one of first answer information D4A, second answer information D4B, or third answer information D4C. Reference information D2 refers to any one of first reference information D2A, second reference information D2B, or third reference information D2C. First answer information D4A is similar drawing information that is existing drawing data stored in a database and includes existing drawing data that has similar characteristics to the target drawing data, and first prompt information D3A is information that instructs generative artificial intelligence model 20 to output first answer information D4A based on question information D1.

[0159] The second answer information D4B is processing estimation information related to the estimated results of processing when a processed product is processed based on the drawing data, and the second prompt information D3B is information that instructs the generative artificial intelligence model 20 to output the second answer information D4B based on the first answer information D4A. Specifically, the second prompt information D3B instructs the generative artificial intelligence model 20 to compare the target drawing data included in the question information D1 with similar existing drawing data included in the first answer information D4A (and the associated product characteristic data, processing estimation data, estimate data, and processing performance data, etc.), and to estimate the processing performance of the target drawing data by taking into account the differences (e.g., differences in dimensions, material, and processing quantity). As a result, highly accurate processing estimation information for new target drawing data is generated based on the performance of past processing.

[0160] The third response information D4C is estimate result information including estimate data that is the result of an estimate regarding the processing price of the processed product, and the third prompt information D3C is information that instructs the generative artificial intelligence model 20 to output the third response information D4C based on the second response information D4B. Specifically, the third prompt information D3C is information that instructs the generative artificial intelligence model 20 to calculate the processing cost by multiplying the time for each processing step included in the processing estimation information obtained as the second response information D4B by the hourly rate included in the estimate calculation information, which is the third reference information D2C, and similarly calculates material costs, management costs, etc. according to instructions in the calculation formula, and then sums these to calculate the final estimate of the processing price of the processed product. As a result, a detailed calculation is performed based on the processing estimation information, and highly accurate estimate result information is generated for the new drawing data to be processed.

[0161] The question information D1 is drawing information including drawing data related to the processed product. Note that the drawing information is the same as the drawing information in the first embodiment, so a detailed description will be omitted (see paragraphs 0108-0109).

[0162] The first reference information D2A is similar drawing search information. Note that the similar drawing search information is the same as the similar drawing search information in the first embodiment, so a detailed description thereof will be omitted (see paragraph 0121).

[0163] The second reference information D2B is process prediction information. Note that the process prediction information is the same as the process prediction information in the first embodiment, so a detailed description will be omitted (see paragraph 0122).

[0164] The third reference information D2C is estimate generation information that contributes to generating an estimate based on drawing data. The estimate generation information includes, for example, drawing processing information, estimate calculation information, evaluation information, and custom information. The drawing processing information, estimate calculation information, evaluation information, and custom information are the same as the drawing processing information, estimate calculation information, evaluation information, and custom information in the first embodiment, respectively, and therefore detailed description thereof will be omitted (see paragraphs 0120 and 0123-0125).

[0165] The first response information D4A is similar drawing information. Note that the process prediction information is the same as the process prediction information in the second embodiment, so a detailed description will be omitted (see paragraph 0151).

[0166] The second response information D4B is processing estimation information relating to the estimated results of processing when the processed product is processed based on the drawing data. The processing estimation information is equivalent to the processing estimation data described above.

[0167] The third response information D4C is estimate result information. Note that the estimate result information is the same as the estimate result information in the first embodiment, and therefore a detailed description thereof will be omitted (see paragraphs 0126-0132).

[0168] (Operation of the information providing system 1 according to the third embodiment) The information providing system according to the third embodiment operates in accordance with the flowchart shown in Fig. 6. However, it is assumed that the drawing database 51 stores a plurality of existing drawing data.

[0169] Although the present embodiment has described a case in which the second prompt information D3B is generated based on the first answer information D4A while referencing the second reference information D2B, the second prompt information D3B may also be generated based on the question information D1 and the first answer information D4A. Furthermore, the present embodiment has described a case in which the third prompt information D3C is generated based on the second answer information D4B while referencing the third reference information D2C, but the third prompt information D3C may also be generated based on the question information D1, the first answer information D4A, and the second answer information D4B.

[0170] In this embodiment, the first prompt information D3A is generated based on question information D1 while referencing first reference information D2A. However, if it is desired to quickly obtain first answer information D4A from the generative artificial intelligence model 20, the first prompt information D3A may be generated based on question information D1 without referencing first reference information D2A. Furthermore, in this embodiment, the second prompt information D3B is generated based on first answer information D4A while referencing second reference information D2B. However, if it is desired to quickly obtain second answer information D4B from the generative artificial intelligence model 20, the second prompt information D3B may be generated based on the first answer information D4A without referencing second reference information D2B. Furthermore, in this embodiment, the third prompt information D3C is generated based on second answer information D4B while referencing third reference information D2C. However, if it is desired to quickly obtain third answer information D4C from the generative artificial intelligence model 20, the third prompt information D3C may be generated based on second answer information D4B without referencing third reference information D2C.

[0171] As described above, according to the information providing device 3 and information providing method of the third embodiment, when first prompt information D3A generated based on question information D1 while referring to first reference information D2A is input to generative artificial intelligence model 20, first answer information D4A is output from generative artificial intelligence model 20, when second prompt information D3B generated based on first answer information D4 while referring to second reference information D2B is input to generative artificial intelligence model 20, second answer information D4B is output from generative artificial intelligence model 20, and when third prompt information D3C generated based on second answer information D4B while referring to third reference information D2C is input to generative artificial intelligence model 20, third answer information D4C is output from generative artificial intelligence model 20. Therefore, it is possible to more accurately estimate the processing price of a processed product. Furthermore, when the first prompt information D3A, the second prompt information D3B, or the third prompt information D3C is generated without referring to the reference information D2, the answer information D4 can be efficiently obtained from the generative artificial intelligence model 20.

[0172] <Fourth embodiment> Next, a fourth embodiment for carrying out the present invention will be described with reference to the drawings of the common embodiment described above. Note that detailed descriptions of the functions and connections of each component in the system, various data handled by each component, the configuration and operation of each part in each device, various data handled by each device, and the operation and configuration in the flowcharts that are the same as those of the common embodiment, the first embodiment, the second embodiment, or the third embodiment will be omitted.

[0173] (Outline of each piece of information according to the fourth embodiment) In the fourth embodiment, prompt information D3 refers to any one of first prompt information D3A, second prompt information D3B, third prompt information D3C, and fourth prompt information D3D. Answer information D4 refers to any one of first answer information D4A, second answer information D4B, third answer information D4C, and fourth answer information D4D. Reference information D2 refers to any one of first reference information D2A, second reference information D2B, third reference information D2C, and fourth reference information D2D. First answer information D4A is similar drawing information that includes existing drawing data stored in a database and includes existing drawing data that has similar characteristics to the target drawing data, and first prompt information D3A is information that instructs the generative artificial intelligence model 20 to output first answer information D4A based on question information D1.

[0174] The second answer information D4B is processing estimation information regarding the estimated results of processing when a processed product is processed based on the target drawing data, and the second prompt information D3B is information that instructs the generative artificial intelligence model 20 to output the second answer information D4B based on the first answer information D4A. Specifically, the second prompt information D3B instructs the generative artificial intelligence model 20 to compare the target drawing data included in the question information D1 with similar existing drawing data included in the first answer information D4A (and the associated product characteristic data, processing estimation data, estimate data, and processing performance data, etc.), and to estimate the processing of the target drawing data taking into account the differences (e.g., differences in dimensions, material, and processing quantity). As a result, highly accurate processing estimation information for the new target drawing data is generated based on the past processing performance.

[0175] The third response information D4C is estimate result information including estimate data that is the result of an estimate regarding the processing price of the processed product, and the third prompt information D3C is information that instructs the generative artificial intelligence model 20 to output the third response information D4C based on the second response information D4B. Specifically, the third prompt information D3C is information that instructs the generative artificial intelligence model 20 to calculate the processing cost by multiplying the time for each processing step included in the processing estimation information obtained as the second response information D4B by the hourly rate included in the estimate calculation information, which is the third reference information D2C, and similarly calculates material costs, management costs, etc. according to instructions in the calculation formula, and then sums these to calculate the final estimate of the processing price of the processed product. As a result, a detailed calculation is performed based on the processing estimation information, and highly accurate estimate result information is generated for the new drawing data to be processed.

[0176] The fourth answer information D4D is estimate basis information regarding the basis for the estimate, and the fourth prompt information D3D is information that instructs the generative artificial intelligence model 20 to output the fourth answer information D4D based on the third answer information D4C. Specifically, the fourth prompt information D3D is information that instructs the generative artificial intelligence model 20 to self-verify the validity of the estimate result (third answer information D4C) calculated in the previous processing using evaluation information (fourth reference information D2D), which is an objective standard, and to report the verification process and results together as the "estimate basis." This not only calculates an estimated price, but also automatically verifies that the price is reasonable in light of the objective standard, thereby significantly improving the reliability and persuasiveness of the estimate result.

[0177] The question information D1 is drawing information including drawing data related to the processed product. Note that the drawing information is the same as the drawing information in the first embodiment, so a detailed description will be omitted (see paragraphs 0108-0109).

[0178] The first reference information D2A is similar drawing search information. Note that the similar drawing search information is the same as the similar drawing search information in the first embodiment, so a detailed description thereof will be omitted (see paragraph 0121).

[0179] The second reference information D2B is process prediction information. Note that the process prediction information is the same as the process prediction information in the first embodiment, so a detailed description will be omitted (see paragraph 0122).

[0180] The third reference information D2C is estimate generation information that contributes to generating an estimate based on drawing data. The estimate generation information includes, for example, drawing processing information, estimate calculation information, evaluation information, and custom information. The drawing processing information, estimate calculation information, evaluation information, and custom information are the same as the drawing processing information, estimate calculation information, and custom information in the first embodiment, respectively, and therefore detailed description thereof will be omitted (see paragraphs 0120, 0123, and 0125).

[0181] The fourth reference information D2D is evaluation information. Note that the evaluation information is the same as the evaluation information in the first embodiment, and therefore a detailed description thereof will be omitted (see paragraph 0124).

[0182] The first response information D4A is similar drawing information. Note that the process prediction information is the same as the process prediction information in the second embodiment, so a detailed description will be omitted (see paragraph 0151).

[0183] The second response information D4B is the processed estimated information. Note that the processed estimated information is the same as the processed estimated information in the third embodiment, and therefore a detailed description thereof will be omitted (see paragraph 0166).

[0184] The third response information D4C is estimate result information. Note that the estimate result information is the same as the estimate result information in the first embodiment, so a detailed description will be omitted (see paragraphs 0126-0131).

[0185] The fourth response information D4D is estimate basis information. Note that the estimate basis information is the same as the estimate basis information in the first embodiment, and therefore a detailed description thereof will be omitted (see paragraph 0132).

[0186] (Operation of the information providing system 1 according to the fourth embodiment) The information providing system according to the fourth embodiment operates in accordance with the flowchart shown in Fig. 7. However, it is assumed that the drawing database 51 stores a plurality of existing drawing data.

[0187] Although the present embodiment has described a case in which the second prompt information D3B is generated based on the first answer information D4A while referencing the second reference information D2B, the second prompt information D3B may alternatively be generated based on the question information D1 and the first answer information D4A. Furthermore, the present embodiment has described a case in which the third prompt information D3C is generated based on the second answer information D4B while referencing the third reference information D2C, but the third prompt information D3C may alternatively be generated based on the question information D1, the first answer information D4A, and the second answer information D4B. Furthermore, the present embodiment has described a case in which the fourth prompt information D3D is generated based on the third answer information D4C while referencing the fourth reference information D2D, but the fourth prompt information D3D may alternatively be generated based on the question information D1, the first answer information D4A, the second answer information D4B, and the third answer information D4C.

[0188] In this embodiment, the first prompt information D3A is generated based on question information D1 while referencing first reference information D2A. However, if it is desired to quickly obtain first answer information D4A from the generative artificial intelligence model 20, the first prompt information D3A may be generated based on question information D1 without referencing first reference information D2A. Furthermore, in this embodiment, the second prompt information D3B is generated based on first answer information D4A while referencing second reference information D2B. However, if it is desired to quickly obtain second answer information D4B from the generative artificial intelligence model 20, the second prompt information D3B may be generated based on the first answer information D4A without referencing second reference information D2B. Furthermore, in this embodiment, the third prompt information D3C is generated based on second answer information D4B while referencing third reference information D2C. However, if it is desired to quickly obtain third answer information D4C from the generative artificial intelligence model 20, the third prompt information D3C may be generated based on second answer information D4B without referencing third reference information D2C. In addition, in this embodiment, we have described a case where the fourth prompt information D3D is generated based on the third answer information D4C while referring to the fourth reference information D2D, but if it is desired to quickly obtain the fourth answer information D4D from the generative artificial intelligence model 20, the fourth prompt information D3D may be generated based on the third answer information D4C without referring to the fourth reference information D2D.

[0189] Furthermore, in step S350 (fourth answer providing process), if the fourth reference information D2D (estimation basis information) indicates that there is an error in the third answer information D4C (estimation result information), the second prompt generation process or the third prompt generation process may be performed again depending on the nature of the error.

[0190] FIG. 9 is a diagram illustrating an example of a display screen. Upon receiving the display screen information transmitted from the information providing device 3, the user terminal device 4 displays a display screen including answer information D4 based on the display screen information. In the example of FIG. 9, first answer information D4A (similar drawing information), second answer information D4B (processing estimation information), third answer information D4C (estimate result information), and fourth answer information D4D (estimate basis information) are simultaneously displayed as the answer information D4. Note that while the example of FIG. 9 describes a case in which each answer information D4 is simultaneously displayed, this is not limiting. For example, each answer information may be displayed in stages. Specifically, an interactive interface may be used in which the first answer information D4A is first displayed, and when the user selects a specific similar drawing from the displayed information, second answer information D4B is generated and displayed based on the selection. Furthermore, a configuration may be used in which the display or non-display of each piece of information can be switched, or the layout of the display area can be changed, depending on the user's operation.

[0191] As described above, according to the information providing device 3 and information providing method of the fourth embodiment, when first prompt information D3A generated based on question information D1 while referring to first reference information D2A is input to the generative AI model 20, first answer information D4A is output from the generative AI model 20. When second prompt information D3B generated based on first answer information D4 while referring to second reference information D2B is input to the generative AI model 20, second answer information D4B is output from the generative AI model 20. When third prompt information D3C generated based on second answer information D4B while referring to third reference information D2C is input to the generative AI model 20, third answer information D4C is output from the generative AI model 20. When fourth prompt information D3D generated based on third answer information D4C while referring to fourth reference information D2D is input to the generative AI model 20, fourth answer information D4D is output from the generative AI model 20. Therefore, the processing price of a processed product can be estimated with higher accuracy. Furthermore, when the first prompt information D3A, the second prompt information D3B, the third prompt information D3C, or the fourth prompt information D3D is generated without referring to the reference information D2, the answer information D4 can be efficiently obtained from the generative artificial intelligence model 20.

[0192] <Other embodiments> The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present invention, all of which are included in the technical concept of the present invention.

[0193] In the above embodiment, the functions of each unit of the information providing device 3 are described as being realized by one device, but the functions of each unit may be distributed among multiple devices and realized by multiple devices. Also, the control unit of the user terminal device 4 or the control unit of the database device 5 may function as the information providing device 3 by executing the information processing program 311.

[0194] In the above embodiment, the database device 5 is described as having the reference information management database 50, but part or all of the reference information management database 50 may be stored in an external device (or devices) connectable to the network 6 or in any storage medium. In addition, the reference information management database 50 may be stored in the storage unit 31 of the information providing device 3.

[0195] In the above embodiment, the case where the information providing device 3 operates according to the flowchart shown in Fig. 4 has been described, but the order of execution of the steps may be changed as appropriate, some steps may be omitted, or other steps may be added. For example, when the prompt generation unit 301 generates prompt information D3 in the prompt generation process (step S200), a step may be added in which the prompt information D3 is provided to the user terminal device 4, and an input operation by the user U to change the prompt information D3 is accepted via the display screen of the user terminal device 4, thereby changing the prompt information D3.

[0196] In the above embodiment, the generative artificial intelligence model 20 generates answer information D4 by referencing reference information D2 stored in the reference information management database 50 when prompt information D3 is input. However, the generative artificial intelligence model 20 may use a trained model in which the reference information D2 is systematically incorporated by including the reference information D2 as part of a training data set. In that case, the generative artificial intelligence model 20 generates answer information D4 by referencing the reference information D2 incorporated into the generative artificial intelligence model 20 based on the instructions of the prompt information D3.

[0197] <Example prompt> An example of the first prompt information D3A in the third embodiment is shown below. Note that the prompt shown here is merely an example, and the task definition, agent role, and specific instruction content can be changed as appropriate without departing from the spirit of the present invention. This prompt indicates one specific means for stably obtaining a desired output by providing the generative artificial intelligence model with its role, available tools (each agent), and constraints.

[0198] "You are a coordinator who leads a team of assistants who support the manufacturing industry with quotation work. Your main responsibility will be to work with subagents to perform tasks related to quotation work, such as searching for similar drawings, extracting drawing information, and calculating quotation amounts. Analyze user queries, plan, and communicate with subagents to provide final answers to users. You are in charge of a team of agents: a) blueprint_agent: A specialist agent that handles blueprints. It can extract information from blueprints and search for past quote information. Delegate these tasks to this agent. b)quotation_agent: A specialist agent that calculates quotation amounts. It calculates quotation amounts based on the results of similar drawing searches and dimension extraction. Delegate such tasks to this agent. Also, below is an overview of the company you will work for and the databases available. - Company name: ABC Co., Ltd. - Business type: Precision processing company that processes plastics - Overview of the database: This database stores drawings for which ABC Co., Ltd. has previously made estimates, as well as information linked to those drawings (dimensions, estimated amounts, processing processes, business partners, etc.). Finally, your main duties are: <Task 1: Search for similar drawings> 1. When a search for similar drawings is requested, the target drawing is compared with past similar drawings stored in the database, and highly similar drawings and information associated with those drawings are searched for. 2. Present the search results to the user separately for each drawing. Provide information to users, including the following: - Product name - Quantity - shape - size - Material - List of processing steps and times (quotation information) - List of actual processing steps and times - List of other expenses - unit price - total amount <Task 2: Drawing information extraction> 1. If you are asked to extract drawing information, we will extract the information written on the target drawing from the image. However, please note that it will take about 3 minutes to extract the drawing information, so please inform the user of this. <Task 3: Estimated amount calculation> 1. If you are asked to calculate an estimate, first perform a search for similar drawings. If you have already done so, you can skip this step. 2. Extract the drawing information. However, please note that this process takes approximately 3 minutes, so please inform the user of this. 3. Based on the search results for similar drawings and the results of drawing information extraction, the processing process and time for the target drawing are estimated and the processing costs are calculated. 4. Next, based on the results of the similar drawing search and the drawing information extraction, the material cost is calculated using the material and material dimensions as a reference. 5. Next, other costs are calculated based on the results of the similar drawing search and the drawing information extraction. 6.Then, add up these costs to calculate the unit cost of the part. 7. Next, multiply the unit price by the quantity listed on the drawing to calculate the final amount. 8. Present the final estimated price and its breakdown to the user along with the reasons. In particular, make sure that the basis for processing costs is clearly stated. How to quote Step 1: Estimate processing costs (unit price) Processing costs are the most important element of an estimate. Processing costs are the sum of the costs of multiple processes. The cost of each process is calculated by adding up the processing steps x time x unit price. The factors that affect the cost estimate and the reasons for them are as follows: a) If the dimensions are larger than those of similar drawings, the processing time will increase, and the processing cost will increase. b) If cutting is required from the sides or back as well as the top, the number of setup steps will increase, which will increase processing costs. c) When special machining such as drilling holes is required, the tool must be replaced, which increases the machining cost. Step 2: Estimate material costs (unit prices) Material cost is calculated according to the material and dimensions of the parts, please refer to the similar drawing. Step 3: Estimate other costs (unit price or total quantity) Please estimate other costs by referring to similar drawings. Some other costs increase with the quantity, while others do not. Depending on the cost content, decide whether to estimate a unit price according to the quantity or an estimate for the total quantity. Step 4: Calculate the estimated cost Calculate the estimated amount using the formula: "Processing cost (unit price) + Material cost (unit price) + Other costs (unit price only) x Quantity + Other costs (total quantity)". Step 5: Present a quote Please provide the user with the estimated cost and its breakdown along with the reasons for it. In particular, please make sure that the basis for the processing costs is clearly explained.

[0199] Although several embodiments of the present disclosure have been illustrated above, these embodiments are presented by way of example only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, etc. can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as set forth in the claims. Furthermore, the above-described embodiments can be implemented in combination with each other. [Explanation of symbols]

[0200] 1... Information provision system, 2... Generative AI device, 3... Information provision device, 4... User terminal device, 5...Database device, 20...Generative artificial intelligence model, 30...control unit, 31...storage unit, 32...communication unit, 33...input unit, 34...display unit, 50...Reference information management database, 300...question receiving unit, 301...prompt generating unit, 302...answer providing unit, 310...Prompt Syntax Data, 311...Information Processing Program

Claims

1. An information providing method for providing information by a computer, comprising: A reception process for receiving question information; a first prompt generation process for generating first prompt information that instructs a generative artificial intelligence model to output first answer information based on the question information; a first answer providing process for providing the first answer information output from the generative artificial intelligence model by inputting the first prompt information into the generative artificial intelligence model; a second prompt generation process for generating second prompt information that instructs a generative artificial intelligence model to output second answer information based on the first answer information; a second answer providing process for providing the second answer information output from the generative artificial intelligence model by inputting the second prompt information into the generative artificial intelligence model; a third prompt generation process for generating third prompt information that instructs a generative artificial intelligence model to output third answer information based on the second answer information; a third answer providing process for providing the third answer information output from the generative artificial intelligence model by inputting the third prompt information into the generative artificial intelligence model; The question information is Drawing information including drawing data relating to the processed product, The first response information is Similar drawing information is existing drawing data stored in a database, the existing drawing data including existing drawing data of the processed product having similar characteristics to the drawing data relating to the processed product; The second response information is processing estimation information relating to an estimated result of processing when the processed product is processed based on drawing data relating to the processed product; The third response information is Estimate result information including estimate data that is a result of an estimate regarding the processing price of the processed product; The first prompt information is The existing drawing data stored in the database includes an instruction to output the existing drawing data as similar drawing information including existing drawing data having similar characteristics to the drawing data relating to the processed product, The second prompt information is The method includes an instruction to estimate a processing step and a processing time based on a comparison between drawing data relating to the target processed product and existing drawing data included in the similar drawing information, The third prompt information is and an instruction to calculate material costs and processing costs for the estimated processing steps and processing times by referring to the similar drawing information and outputting the calculated costs as the estimate result information. Information provision method.

2. An information providing method for providing information by a computer, comprising: A reception process for receiving question information; a first prompt generation process for generating first prompt information that instructs a generative artificial intelligence model to output first answer information based on the question information; a first answer providing process for providing the first answer information output from the generative artificial intelligence model by inputting the first prompt information into the generative artificial intelligence model; a second prompt generation process for generating second prompt information that instructs a generative artificial intelligence model to output second answer information based on the first answer information; a second answer providing process for providing the second answer information output from the generative artificial intelligence model by inputting the second prompt information into the generative artificial intelligence model; a third prompt generation process for generating third prompt information that instructs a generative artificial intelligence model to output third answer information based on the second answer information; a third answer providing process for providing the third answer information output from the generative artificial intelligence model by inputting the third prompt information into the generative artificial intelligence model; a fourth prompt generation process for generating fourth prompt information that instructs a generative artificial intelligence model to output fourth answer information based on the third answer information; a fourth answer providing process for providing the fourth answer information output from the generative artificial intelligence model by inputting the fourth prompt information into the generative artificial intelligence model; The question information is Drawing information including drawing data relating to the processed product, The first response information is Similar drawing information is existing drawing data stored in a database, the existing drawing data including existing drawing data of the processed product having similar characteristics to the drawing data relating to the processed product; The second response information is processing estimation information relating to an estimated result of processing when the processed product is processed based on drawing data relating to the processed product; The third response information is Estimate result information including estimate data that is a result of an estimate regarding the processing price of the processed product; The fourth response information is estimate basis information regarding the basis of the estimate, the first prompt information includes an instruction to output existing drawing data stored in a database as similar drawing information including existing drawing data having similar characteristics to the drawing data relating to the processed product, The second prompt information is The method includes an instruction to estimate a processing step and a processing time based on a comparison between drawing data relating to the target processed product and existing drawing data included in the similar drawing information, The third prompt information is The instruction to calculate material costs and processing costs for the estimated processing steps and processing times by referring to the similar drawing information is included, The fourth prompt information is an instruction to output a verification process of the calculated estimate result as the estimate basis information; Information provision method.

3. An information providing device that provides information by a computer, a reception unit that receives question information; a first prompt generation unit that generates first prompt information that instructs a generative artificial intelligence model to output first answer information based on the question information; a first answer providing unit that provides the first answer information output from the generative artificial intelligence model by inputting the first prompt information into the generative artificial intelligence model; a second prompt generation unit that generates second prompt information that instructs a generative artificial intelligence model to output second answer information based on the first answer information; a second answer providing unit that provides the second answer information output from the generative artificial intelligence model by inputting the second prompt information into the generative artificial intelligence model; a third prompt generation unit that generates third prompt information that instructs a generative artificial intelligence model to output third answer information based on the second answer information; a third answer providing unit that provides the third answer information output from the generative artificial intelligence model by inputting the third prompt information to the generative artificial intelligence model, The question information is Drawing information including drawing data relating to the processed product, The first response information is Similar drawing information is existing drawing data stored in a database, the existing drawing data including existing drawing data of the processed product having similar characteristics to the drawing data relating to the processed product; The second response information is processing estimation information relating to an estimated result of processing when the processed product is processed based on drawing data relating to the processed product; The third response information is Estimate result information including estimate data that is a result of an estimate regarding the processing price of the processed product; The first prompt information is The existing drawing data stored in the database includes an instruction to output the existing drawing data as similar drawing information including existing drawing data having similar characteristics to the drawing data relating to the processed product, The second prompt information is The method includes an instruction to estimate a processing step and a processing time based on a comparison between drawing data relating to the target processed product and existing drawing data included in the similar drawing information, The third prompt information is and an instruction to calculate material costs and processing costs for the estimated processing steps and processing times by referring to the similar drawing information and outputting the calculated costs as the estimate result information. Information providing device.

4. An information providing device that provides information by a computer, a reception unit that receives question information; a first prompt generation unit that generates first prompt information that instructs a generative artificial intelligence model to output first answer information based on the question information; a first answer providing unit that provides the first answer information output from the generative artificial intelligence model by inputting the first prompt information into the generative artificial intelligence model; a second prompt generation unit that generates second prompt information that instructs a generative artificial intelligence model to output second answer information based on the first answer information; a second answer providing unit that provides the second answer information output from the generative artificial intelligence model by inputting the second prompt information into the generative artificial intelligence model; a third prompt generation unit that generates third prompt information that instructs a generative artificial intelligence model to output third answer information based on the second answer information; a third answer providing unit that provides the third answer information output from the generative artificial intelligence model by inputting the third prompt information into the generative artificial intelligence model; a fourth prompt generation unit that generates fourth prompt information that instructs a generative artificial intelligence model to output fourth answer information based on the third answer information; and a fourth answer providing unit that provides the fourth answer information output from the generative artificial intelligence model by inputting the fourth prompt information to the generative artificial intelligence model, The question information is Drawing information including drawing data relating to the processed product, The first response information is Similar drawing information is existing drawing data stored in a database, the existing drawing data including existing drawing data of the processed product having similar characteristics to the drawing data relating to the processed product; The second response information is processing estimation information relating to an estimated result of processing when the processed product is processed based on drawing data relating to the processed product; The third response information is Estimate result information including estimate data that is a result of an estimate regarding the processing price of the processed product; The fourth response information is Estimate basis information regarding the basis of the estimate, The first prompt information is The existing drawing data stored in the database includes an instruction to output the existing drawing data as similar drawing information including existing drawing data having similar characteristics to the drawing data relating to the processed product, The second prompt information is The method includes an instruction to estimate a processing step and a processing time based on a comparison between drawing data relating to the target processed product and existing drawing data included in the similar drawing information, The third prompt information is The instruction to calculate material costs and processing costs for the estimated processing steps and processing times by referring to the similar drawing information is included, The fourth prompt information is an instruction to output a verification process of the calculated estimate result as the estimate basis information; Information providing device.

Images