Information processing device, information processing method, and program

Abstract

To provide technology that can generate explanations for data. [Solution] An information processing device according to one aspect of the present disclosure includes: a selection unit for selecting a type of description to be generated for data relating to equipment; a data acquisition unit for acquiring the data according to the selected type; a domain knowledge acquisition unit for acquiring domain knowledge of the equipment; a prompt creation unit for creating a prompt that instructs the generation of the description based on the data and the domain knowledge; and an explanation generation unit for generating information representing the description based on the prompt and a generation AI realized by a machine learning model including a large-scale language model.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] There is known a method of determining an optimal operation plan for facilities such as various plants (e.g., power generation plants, steel plants, chemical plants, oil plants, energy plants, etc.) by solving an optimization problem. For example, Patent Document 1 discloses a method of calculating an optimal operation plan for a heat source system. Also, for example, Patent Document 2 discloses a method of creating an optimal production plan for production facilities.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, since it is generally difficult to confirm the correctness of an operation plan obtained by solving an optimization problem, there is a need for a technique for generating an explanation for data representing the operation plan. This is not limited to data representing an operation plan obtained by solving an optimization problem, and is the same for, for example, data representing operation results.

[0005] The present disclosure has been made in view of the above points, and an object thereof is to provide a technique capable of generating an explanation for data.

Means for Solving the Problems

[0006] An information processing device according to one aspect of the present disclosure includes: a selection unit for selecting a type of description to be generated for data relating to equipment; a data acquisition unit for acquiring the data according to the selected type; a domain knowledge acquisition unit for acquiring domain knowledge of the equipment; a prompt creation unit for creating a prompt that instructs the generation of the description based on the data and the domain knowledge; and an explanation generation unit for generating information representing the description based on the prompt and a generation AI realized by a machine learning model including a large-scale language model. [Effects of the Invention]

[0007] It is possible to generate explanations for the data. [Brief explanation of the drawing]

[0008] [Figure 1] This diagram shows an example of the configuration of the target equipment. [Figure 2] This figure shows an example of the hardware configuration of the data explanation device according to this embodiment. [Figure 3] This figure shows an example of the functional configuration of the data explanation device according to this embodiment. [Figure 4] This flowchart shows an example of the data description process according to this embodiment. [Figure 5] This figure shows an example of operation history data in array format. [Figure 6] This figure shows an example of optimal driving plan data in array format. [Figure 7] This figure shows an example of domain knowledge. [Figure 8] This figure shows an example of a prompt template (part 1). [Figure 9] This figure shows an example of a prompt template (part 2). [Figure 10] This figure shows an example of a prompt (part 1). [Figure 11] This figure shows an example of a prompt (part 2). [Figure 12] This figure shows an example of data explanation information (part 1). [Figure 13] This figure shows an example of data explanation information (part 2). [Figure 14] This figure shows an example of data explanation information (part 3). [Modes for carrying out the invention]

[0009] Hereinafter, one embodiment of the present invention will be described in detail with reference to the drawings. In the following embodiment, a data explanation device 10 capable of generating explanations for data relating to a certain predetermined piece of equipment (hereinafter referred to as "target equipment") will be described. Examples of target equipment include various plants such as power plants, steel plants, chemical plants, oil plants, and energy plants. Examples of data relating to the target equipment include data representing the operating performance of the target equipment (hereinafter referred to as "operating performance data") and data representing the optimal operating plan of the target equipment (hereinafter referred to as "optimal operating plan data"). Optimal operating plan data is, for example, data obtained by solving an optimization problem to find the optimal operating plan for the target equipment.

[0010] Furthermore, the format of the optimization problem used to obtain optimal operation plan data is not limited to a specific format; it is possible to use optimal operation plan data obtained by solving an optimization problem of any format. In other words, the optimal operation plan data may be data obtained by solving a continuous optimization problem, or data obtained by solving a discrete optimization problem (also known as a "combinatorial optimization problem"). Also, various methods (e.g., metaheuristics, reinforcement learning, and other existing methods) can be used to solve the optimization problem, depending on the problem. In the following example, we will assume that the optimal operation plan data is data obtained by solving a continuous optimization problem.

[0011] Furthermore, targeting data related to equipment is just one example; it is also possible to target data related to machinery, system data, etc.

[0012] Here, the data explanation device 10 according to the present embodiment generates an explanation for data related to the target facility by using the domain knowledge of the target facility and generative AI (Artificial Intelligence). As a result, even a user who does not have specialized knowledge about the target facility can, by referring to the explanation of the data related to the target facility, for example, grasp the problems of the current operation from the operation results, verify the validity of the optimal operation plan, etc. It is also possible to further confirm improvement measures for the problems of the current operation and compare the current operation with the optimal operation plan. Therefore, by using the data explanation device 10 according to the present embodiment, it is possible to support the user's decision-making (e.g., deciding whether to actually apply the optimal operation plan) when making a decision regarding the target facility. Here, the domain knowledge is the specialized knowledge in the industry or field to which the target facility belongs.

[0013] Note that the data explanation device 10 according to the present embodiment is realized by, for example, an information processing device (computer) or an information processing system (computer system) composed of one or more information processing devices. Specific examples of the information processing device include a personal computer, a general-purpose server, a smartphone, a tablet terminal, and the like.

[0014] Generative AI is a technology or mechanism that generates content such as natural language sentences or images that satisfy the given instructions or questions (these instructions or questions are called "prompts", etc.). Generative AI is generally realized by a machine learning model including, for example, large language models (LLMs: Large Language Models).

[0015] <Configuration example of the target facility> The following example of target equipment is the energy plant shown in Figure 1. The energy plant shown in Figure 1 consists of a gas turbine (+ exhaust gas boiler), a once-through boiler, N turbo chillers, and N steam absorption chillers. The gas turbine (+ exhaust gas boiler) consists of a gas turbine that generates electricity from city gas and an exhaust gas boiler that outputs steam from the gas discharged from the gas turbine. The once-through boiler outputs steam from city gas. The turbo chillers output cooling using electricity generated by the gas turbine and electricity purchased as needed. The steam absorption chillers output cooling using steam output from the exhaust gas boiler and steam output from the once-through boiler. The electricity, cooling, and steam output from the energy plant are used as power load, heat load, and steam load, respectively.

[0016] Note that the configuration of the energy plant shown in Figure 1 is just one example and is not limited to this configuration.

[0017] <Example hardware configuration of data explanation device 10> Figure 2 shows an example of the hardware configuration of the data explanation device 10 according to this embodiment. As shown in Figure 2, the data explanation device 10 according to this embodiment includes an input device 101, a display device 102, an external I / F 103, a communication I / F 104, a RAM (Random Access Memory) 105, a ROM (Read Only Memory) 106, an auxiliary storage device 107, and a processor 108. Each of these hardware components is connected to each other via a bus 109 so as to be able to communicate.

[0018] The input device 101 is, for example, a keyboard, mouse, touch panel, or physical button. The display device 102 is, for example, a display or display panel. The data explanation device 10 does not necessarily have to have at least one of the input device 101 and the display device 102.

[0019] External I / F 103 is an interface with external devices such as recording media 103a. Examples of recording media 103a include CD (Compact Disc), DVD (Digital Versatile Disk), SD memory card (Secure Digital memory card), and USB (Universal Serial Bus) memory card.

[0020] The communication interface 104 is an interface for connecting to a communication network. The RAM 105 is a volatile semiconductor memory (storage device) that temporarily holds programs and data. The ROM 106 is a non-volatile semiconductor memory (storage device) that can retain programs and data even when the power is turned off. The auxiliary storage device 107 is a non-volatile storage device such as an HDD (Hard Disk Drive), SSD (Solid State Drive), or flash memory. The processor 108 is a processing unit such as a CPU (Central Processing Unit) or GPU (Graphic Processing Unit).

[0021] Note that the hardware configuration shown in Figure 2 is just one example, and the hardware configuration of the data explanation device 10 is not limited to this. For example, the data explanation device 10 may have multiple auxiliary storage devices 107 or multiple processors 108, it may not have some of the hardware shown, or it may have various other hardware components besides the hardware shown.

[0022] <Example of the functional configuration of the data explanation device 10> Figure 3 shows an example of the functional configuration of the data explanation device 10 according to this embodiment. As shown in Figure 3, the data explanation device 10 according to this embodiment includes an explanation type selection unit 201, a data acquisition unit 202, an information organization unit 203, a domain knowledge acquisition unit 204, a prompt creation unit 205, an explanation generation unit 206, an explanation output unit 207, and a user input acquisition unit 208. The data explanation device 10 according to this embodiment also includes a data storage unit 301, a domain knowledge storage unit 302, and a template storage unit 303.

[0023] The explanation type selection unit 201, data acquisition unit 202, information organization unit 203, domain knowledge acquisition unit 204, prompt creation unit 205, explanation generation unit 206, explanation output unit 207, and user input acquisition unit 208 are implemented, for example, by a process executed by one or more programs installed on the data explanation device 10 on the processor 108, etc. At least one of these units may be implemented, for example, by a process executed by an external cloud server, etc.

[0024] Furthermore, the data storage unit 301, the domain knowledge storage unit 302, and the template storage unit 303 are implemented by storage areas such as the auxiliary storage device 107. At least one of these units may be implemented by the storage area of ​​a storage device (e.g., a storage device provided by a database server) that is communicably connected to the data explanation device 10.

[0025] The explanation type selection unit 201 selects one or more explanation types from one or more predetermined explanation types for which the user wishes to obtain an explanation. An explanation type is the type of explanation for data related to the target equipment. As an example, two explanation types are assumed below: "Problems with current operation" and "Reasons for optimization results." Here, "Problems with current operation" is the explanation type for when the user wishes to obtain an explanation about problems with the current operation of the target equipment. On the other hand, "Reasons for optimization results" is the explanation type for when the user wishes to obtain an explanation about the reasons for the optimal operation plan of the target equipment.

[0026] In addition to "Problems with the current operation" and "Reasons for the optimization results," other explanation types may include, for example, "Measures to improve the problems" and "Comparison and consideration of the current operation and the optimization results." "Measures to improve the problems" is the explanation type used when you want an explanation about solutions to the problems with the current operation of the equipment in question. "Comparison and consideration of the current operation and the optimization results" is the explanation type used when you want an explanation about a comparison and consideration of the current operation of the equipment in question with the optimal operation plan.

[0027] The data acquisition unit 202 acquires at least one of the driving performance data and the optimal driving plan data from the data storage unit 301, according to the explanation type selected by the explanation type selection unit 201. For example, if the explanation type selected by the explanation type selection unit 201 is "Problems with current operation", the data acquisition unit 202 acquires the driving performance data from the data storage unit 301, and if the explanation type is "Reasons for optimization results", it acquires the optimal driving plan data from the data storage unit 301. If the explanation type is "Measures to improve the problems", the driving performance data is acquired from the data storage unit 301, and if the explanation type is "Comparison and consideration of current operation and optimization results", both the driving performance data and the optimal driving plan data are acquired from the data storage unit 301.

[0028] The information organization unit 203 organizes or converts the data acquired by the data acquisition unit 202 (driving performance data or optimal driving plan data or both) into a predetermined format (e.g., array format) that can be input into the generating AI.

[0029] The domain knowledge acquisition unit 204 acquires domain knowledge of the target equipment from the domain knowledge storage unit 302. Domain knowledge may include information such as the operating characteristics of the target equipment, the operating schedule of the target equipment (e.g., start time, stop time, maintenance time, etc.), the input / output of the equipment or facilities constituting the target equipment and their upper and lower limit constraints, the input / output characteristics of the equipment or facilities constituting the target equipment, the input / output relationships between the equipment or facilities constituting the target equipment, the costs required to operate the target equipment (e.g., unit prices of purchased electricity, city gas, etc.), and the normal / abnormal range of the output of the equipment or facilities constituting the target equipment. Domain knowledge may be created in advance by, for example, a user.

[0030] The prompt creation unit 205 obtains a prompt template from the template storage unit 303 according to the explanation type selected by the explanation type selection unit 201. The prompt creation unit 205 also creates a prompt from the prompt template using the data organized or converted by the information organization unit 203 and the domain knowledge acquired by the domain knowledge acquisition unit 204. For example, the prompt creation unit 205 creates a prompt that instructs the generation of an explanation for the data by setting the data organized or converted by the information organization unit 203 and the information contained in the domain knowledge acquired by the domain knowledge acquisition unit 204 into the prompt template. A prompt template is a template for a prompt. Prompt templates are created in advance, for example, by a user.

[0031] The explanation generation unit 206 generates data explanation information representing an explanation for the data acquired by the data acquisition unit 202, using the prompt created by the prompt creation unit 205 and the generation AI. That is, the explanation generation unit 206 generates data explanation information by inputting the prompt created by the prompt creation unit 205 into the generation AI. The explanation generation unit 206 may use a generation AI provided as an external service, a generation AI possessed by the data explanation device 10, or any other generation AI. Since the large-scale language model that implements the generation AI also acquires various domain knowledge during training, when data explanation information is generated by the generation AI, it can be expected that the generation of data explanation information will utilize domain knowledge that combines the domain knowledge acquired by the domain knowledge acquisition unit 204 and the domain knowledge acquired by the large-scale language model that implements the generation AI during training.

[0032] Furthermore, the explanation generation unit 206 inputs user input information, described later, as a prompt to the generation AI, which then generates new data explanation information. This new data explanation information may include, for example, information representing additional explanations for the previously generated data explanation information by the generation AI, information representing a summary of the previously generated data explanation information by the generation AI, or information representing answers to any questions or instructions regarding the previously generated data explanation information by the generation AI.

[0033] The explanation output unit 207 outputs the data explanation information generated by the explanation generation unit 206 to a predetermined output destination. Examples of predetermined output destinations include a display device 102 such as a display, a storage area such as an auxiliary storage device 107, and other devices or equipment connected via communication.

[0034] The user input acquisition unit 208 inputs information such as natural language sentences entered by the user (hereinafter also referred to as "user input information"). Examples of user input information include information representing natural language sentences requesting additional explanations for data description information, information representing natural language sentences requesting summaries of data description information, information representing natural language sentences such as standardized questions about data description information, and information representing natural language sentences that mean some kind of question or instruction about other data description information.

[0035] The data storage unit 301 stores data related to the target equipment (such as operational performance data and optimal operation plan data). Operational performance data is collected from the target equipment (more precisely, collected from sensors installed on the target equipment or its constituent devices or equipment). On the other hand, optimal operation plan data is obtained by solving an optimization problem to determine the optimal operation plan for the target equipment. The entity that solves the optimization problem may be the data explanation device 10, or it may be a server (e.g., a cloud server) that is communicatively connected to the data explanation device 10. When the data explanation device 10 solves the optimization problem, the data explanation device 10 may have a functional unit for solving the optimization problem, for example, called an "optimization calculation unit".

[0036] The domain knowledge storage unit 302 stores the domain knowledge of the target equipment.

[0037] The template storage unit 303 stores a prompt template corresponding to each explanation type.

[0038] <Example of data explanation processing> An example of the data explanation processing according to this embodiment will be described with reference to Figure 4. For example, steps S101 to S107 in Figure 4 are executed whenever data explanation information is needed, and steps S108 to S110 are executed one or more times as needed after the data explanation information has been obtained.

[0039] The explanation type selection unit 201 selects one or more explanation types from one or more predetermined explanation types for which the user wishes to receive an explanation (step S101). For example, the explanation type selection unit 201 may select the explanation type specified by the user from one or more predetermined explanation types. In the following explanation, as an example, we will assume that "Problems with current operation" or "Reasons for optimization results" are selected as the explanation type.

[0040] The data acquisition unit 202 acquires at least one of the operation performance data and the optimal operation plan data from the data storage unit 301 according to the explanation type selected in step S101 above (step S102). For example, if "Problems with current operation" is selected as the explanation type in step S101 above, the data acquisition unit 202 acquires the operation performance data from the data storage unit 301. On the other hand, for example, if "Reasons for optimization results" is selected as the explanation type in step S101 above, the data acquisition unit 202 acquires the optimal operation plan data from the data storage unit 301.

[0041] Here, the operational performance data and the optimal operation plan data are represented as time-series data of data (hereinafter referred to as "state data") composed of one or more variables (when the target equipment is a plant, these variables are also called "state variables," etc.). When the target equipment is the energy plant shown in Figure 1, examples of state variables include the amount of electricity purchased, the amount of city gas purchased, the amount of city gas used by the gas turbine, the power output of the gas turbine, the steam output of the exhaust gas boiler, the amount of electricity used by the turbo chiller, the heat output of the turbo chiller, the amount of steam used by the steam absorption chiller, the heat output of the steam absorption chiller, the amount of city gas used by the once-through boiler, the steam output of the once-through boiler, the surplus steam of the once-through boiler, the power load, the heat load, the steam load, etc.

[0042] In addition, if operational performance data is acquired in step S102 above, the data acquisition unit 202 may, for example, acquire status data constituting the operational performance data sequentially in real time from the target equipment.

[0043] The information organization unit 203 organizes or converts the data acquired in step S102 (operational performance data or optimal operation plan data or both) into a predetermined format (e.g., array format) that can be input to the generating AI (step S103). As an example, Figure 5 shows the operational performance data organized or converted into array format for the energy plant shown in Figure 1 as the target facility. Similarly, Figure 6 shows the optimal operation plan data organized or converted into array format for the energy plant shown in Figure 1 as the target facility. Figures 5 and 6 show examples of how the time-series data of each state variable is represented as an array. In Figures 5 and 6, each row represents one array, and each array contains the name of the state variable corresponding to that array and the unit of the value set for that state variable. In addition, each array stores the time-series data of the state variable from time s=1 to time s=t.

[0044] Furthermore, if the data acquired in step S102 above (driving performance data, optimal driving plan data, or both) is in a format that can be input into the generating AI, step S103 above does not need to be performed.

[0045] The domain knowledge acquisition unit 204 acquires the domain knowledge of the target equipment from the domain knowledge storage unit 302 (step S104). As an example, Figure 7 shows the domain knowledge when the energy plant shown in Figure 1 is the target equipment. The domain knowledge 1100 shown in Figure 7 contains a description of the energy plant shown in Figure 1 and the characteristics of the various equipment that make up the energy plant, written in natural language. Note that the domain knowledge 1100 shown in Figure 7 is just an example and is not limited to this.

[0046] The prompt creation unit 205 obtains a prompt template from the template storage unit 303 according to the explanation type selected in step S101 above (step S105). For example, if "Problems with current operation" is selected as the explanation type in step S101 above, the prompt creation unit 205 obtains the prompt template 2100 shown in Figure 8 from the template storage unit 303. On the other hand, for example, if "Reasons for optimization results" is selected as the explanation type in step S101 above, the prompt creation unit 205 obtains the prompt template 2200 shown in Figure 9 from the template storage unit 303.

[0047] The prompt template 2100 shown in Figure 8 is a prompt template for generating an explanation of the current operational problems of the target equipment as an explanation for the operational performance data. On the other hand, the prompt template 2200 shown in Figure 9 is a prompt template for generating an explanation of the reasons for the optimal operational plan of the target equipment as an explanation for the optimal operational plan data. Here, in the prompt template 2100 shown in Figure 8, the variable part is represented by "****". Similarly, in the prompt template 2200 shown in Figure 9, the variable part is represented by "****". The variable part is the part where data (operational performance data or optimal operational plan data or both) and domain knowledge are set. By setting data and domain knowledge in the variable part included in the prompt template, a prompt is created that instructs the generation of an explanation for that data.

[0048] Note that the prompt template 2100 shown in Figure 8 and the prompt template 2200 shown in Figure 9 are just examples and are not the only ones that can be used. Various prompt templates can be used as prompt templates that instruct the generation of explanations for data (i.e., prompts that include a variable portion). Hereafter, the data and information set in the variable portion included in the prompt template will be referred to as "configuration information".

[0049] The prompt creation unit 205 uses the data organized or transformed in step S103, the domain knowledge acquired in step S104, and the prompt template acquired in step S105 to create a prompt that instructs the generation of an explanation for the data (step S106). That is, the prompt creation unit 205 creates a prompt that instructs the generation of an explanation for the data by setting the variable portion included in the prompt template acquired in step S105 with the data organized or transformed in step S103 and the information included in the domain knowledge acquired in step S104.

[0050] As an example, Figure 10 shows a prompt created by setting the variable portion of the prompt template 2100 shown in Figure 8 with the operational performance data shown in Figure 5 and the domain knowledge 1100 shown in Figure 7. The prompt 3100 shown in Figure 10 is a prompt for generating data explanation information based on the results of identifying problems in the current operation of the target equipment (i.e., the operational performance data shown in Figure 5) from the perspective of energy cost efficiency. Note that in the prompt 3100 shown in Figure 10, the setting information is shown in bold and underlined.

[0051] As another example, Figure 11 shows a prompt created by setting the optimal operation plan data shown in Figure 6 and the domain knowledge 1100 shown in Figure 7 to the variable portion included in the prompt template 2200 shown in Figure 9. The prompt 3200 shown in Figure 11 is a prompt for generating data explanation information that explains the reason for the optimal solution obtained by mathematical optimization technique (i.e., the optimal operation plan data shown in Figure 6). In the prompt 3200 shown in Figure 11, the setting information is shown in bold and underlined.

[0052] The explanation generation unit 206 uses the prompt created in step S106 and the generation AI to generate data explanation information that represents an explanation for the data acquired in step S102 (step S107). That is, the explanation generation unit 206 inputs the prompt created in step S106 into the generation AI, and the generation AI generates the data explanation information.

[0053] The explanation output unit 207 outputs the data explanation information generated in step S107 to a predetermined output destination (step S108).

[0054] As an example, Figure 12 shows the data description information generated by inputting the prompt 3100 shown in Figure 10 into the generating AI. In the data description information 4100 shown in Figure 12, the current operational problems of the target equipment are explained in natural language from the perspective of energy cost efficiency.

[0055] As another example, Figure 13 shows the data description information generated by inputting the prompt 3200 shown in Figure 11 into the generating AI. In the data description information 4200 shown in Figure 13, the reason why the optimal solution obtained by mathematical optimization technique is optimal is explained in natural language.

[0056] The user input acquisition unit 208 acquires user input information entered by the user (step S109).

[0057] The explanation generation unit 206 generates new data explanation information using the user input information obtained in step S109 and the generation AI (step S110). That is, the explanation generation unit 206 inputs the user input information obtained in step S109 as a prompt to the generation AI, and the generation AI generates new data explanation information.

[0058] The explanation output unit 207 outputs the data explanation information generated in step S110 to a predetermined output destination (step S111).

[0059] As an example, the user input information obtained in step S109 above represents a natural language sentence requesting a summary of the data description information, and the new data description information when the data description information 4100 shown in Figure 12 is generated in step S107 above is shown in Figure 14. The data description information 4300 shown in Figure 14 is data description information that represents a summary of the data description information 4100 shown in Figure 12.

[0060] <Variation> Prompts and their templates are not limited to natural language text; they may also include content such as images, videos, and audio. They may also include mathematical formulas, program code, and other similar elements.

[0061] In particular, when instructing the generating AI to perform any numerical calculations or processes, the mathematical formulas or program code used in those calculations or processes may be included in the prompt. This makes it possible to reduce calculation errors when the generating AI performs numerical calculations.

[0062] <Summary> As described above, the data explanation device 10 according to this embodiment generates and outputs explanations for data relating to the target equipment using domain knowledge of the target equipment and generation AI. This makes it possible for the data explanation device 10 according to this embodiment to generate explanations for data based on domain knowledge of the target equipment. For this reason, even users who do not have specialized knowledge of the target equipment can make various decisions by referring to data explanation information that represents explanations for data relating to the target equipment. For example, it becomes possible to solve problems in current operations by understanding problems in operation from operating results, to verify the validity of the optimal operation plan and decide whether or not to apply that operation plan, and to improve current operations by comparing current operations with the optimal operation plan.

[0063] The present invention is not limited to the embodiments specifically disclosed above, and various modifications, changes, and combinations with known technologies are possible without departing from the scope of the claims. [Explanation of symbols]

[0064] 10 Data Explanation Device 101 Input Device 102 Display device 103 External I / F 103a Recording medium 104 Communication I / F 105 RAM 106 ROM 107 Auxiliary storage 108 processors 109 Bus 201 Explanation Type Selection Section 202 Data Acquisition Unit 203 Information Organizing Department 204 Domain Knowledge Acquisition Department 205 Prompt Creation Section 206 Explanation Generation Unit 207 Explanation Output Section 208 User Input Acquisition Unit 301 Data Storage Unit 302 Domain Knowledge Storage Unit 303 Template Storage Unit

Claims

1. A selection unit for selecting the type of explanation to be generated for data related to the equipment, A data acquisition unit that acquires the data according to the selected type, A domain knowledge acquisition unit that acquires domain knowledge of the aforementioned equipment, A prompt generation unit that generates a prompt instructing the generation of the description based on the aforementioned data and the aforementioned domain knowledge, An explanation generation unit generates information representing the explanation based on the aforementioned prompt and a generative AI implemented by a machine learning model including a large-scale language model, An information processing device having

2. The prompt generation unit, Depending on the selected type, a template corresponding to that type is obtained from one or more pre-created templates. The information processing apparatus according to claim 1, which creates the prompt by setting the data and the domain knowledge for the acquired template.

3. The aforementioned categories include categories that represent explanations regarding the reasons for the optimal operating plan of the equipment, The data acquisition unit, The information processing device according to claim 1 or 2, wherein if the selected type is a type that represents an explanation of the reason for the optimal operation plan of the equipment, the device acquires optimal operation plan data representing the optimal operation plan of the equipment obtained by solving a predetermined optimization problem as the data.

4. The aforementioned categories include categories that describe problems with the current operation of the equipment, The data acquisition unit, The information processing device according to claim 3, wherein if the selected type is a type that represents a description of the current operational problems of the equipment, it acquires operational performance data representing the operational performance of the equipment as the data.

5. It has a user input acquisition unit that acquires user input information representing a summary of the information representing the explanation, an instruction for additional explanation of the information representing the explanation, or a question or a predetermined instruction, The explanation generation unit, The information processing apparatus according to claim 1, which generates the summary instruction, the additional explanation instruction, or information that satisfies the question or the predetermined instruction based on the user input information and the generating AI.

6. The information processing apparatus according to claim 1, wherein the domain knowledge includes at least one of the operating characteristics of the equipment, the operating schedule of the equipment, the input / output characteristics of the equipment constituting the equipment, upper and lower limit constraints on the input and output of the equipment constituting the equipment, the input / output relationships of the equipment constituting the equipment, the costs required to operate the equipment, and the normal range and abnormal range of the output of the equipment constituting the equipment.

7. A selection procedure for selecting the type of description to generate for data related to equipment, A data acquisition procedure for acquiring the data according to the selected type, A procedure for acquiring domain knowledge of the aforementioned equipment, A prompt creation procedure that creates a prompt instructing the generation of the description based on the aforementioned data and the aforementioned domain knowledge, An explanation generation procedure that generates information representing the explanation based on the aforementioned prompt and a generative AI implemented by a machine learning model including a large-scale language model, A method of information processing performed by a computer.

8. A selection procedure for selecting the type of description to generate for data related to equipment, A data acquisition procedure for acquiring the data according to the selected type, A procedure for acquiring domain knowledge of the aforementioned equipment, A prompt creation procedure that creates a prompt instructing the generation of the description based on the aforementioned data and the aforementioned domain knowledge, An explanation generation procedure that generates information representing the explanation based on the aforementioned prompt and a generative AI implemented by a machine learning model including a large-scale language model, A program that causes a computer to execute something.

Images