Information processing device, information processing method, and program

Abstract

To provide a technique that can generate explanations for data. [Solution] An information processing device according to one aspect of the present disclosure has a selection unit that selects a type of explanation to be generated for data related to 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 equipment, a prompt creation unit that creates a prompt that instructs the generation of the explanation based on the data and the domain knowledge, and an explanation generation unit that generates information representing the explanation 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 device, an information processing method, and a program. [Background technology]

[0002] There are known methods for determining an optimal operation plan for equipment such as various plants (e.g., power plants, steel plants, chemical plants, petroleum plants, energy plants, etc.) by solving optimization problems. For example, Patent Document 1 discloses a method for calculating an optimal operation plan for a heat source system. Also, for example, Patent Document 2 discloses a method for creating an optimal production plan for production equipment. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6810597 [Patent Document 2] Patent No. 7349608 Summary of the Invention [Problem 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, a technology is required to generate an explanation for data representing the operation plan. This is not limited to data representing an operation plan obtained by solving an optimization problem, but also applies to data representing operation results, for example.

[0005] The present disclosure has been made in consideration of the above points, and aims to provide a technology that can generate explanations for data. [Means for solving the problem]

[0006] An information processing device according to one aspect of the present disclosure has a selection unit that selects a type of explanation to be generated for data related to 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 equipment, a prompt creation unit that creates a prompt that instructs the generation of the explanation based on the data and the domain knowledge, and an explanation generation unit that generates information representing the explanation based on the prompt and a generation AI realized by a machine learning model including a large-scale language model. Effect of the Invention

[0007] Explanations can be generated for the data. [Brief description of the drawings]

[0008] [Figure 1] FIG. 2 is a diagram illustrating an example of a configuration of a target facility. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of the data explanation device according to the present embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of a functional configuration of the data explanation device according to the present embodiment. [Figure 4] 13 is a flowchart illustrating an example of a data explanation process according to the embodiment. [Diagram 5] FIG. 13 is a diagram showing an example of driving performance data in an array format. [Figure 6] FIG. 11 is a diagram showing an example of optimal operation plan data in an array format. [Figure 7] FIG. 1 illustrates an example of domain knowledge. [Figure 8] FIG. 13 is a diagram showing an example (part 1) of a prompt template. [Figure 9] FIG. 13 is a diagram showing an example (part 2) of a prompt template. [Figure 10] FIG. 13 is a diagram showing an example (part 1) of a prompt. [Figure 11] FIG. 13 is a diagram showing an example (part 2) of a prompt. [Figure 12] FIG. 13 is a diagram showing an example (part 1) of data explanation information. [Figure 13] FIG. 13 is a diagram showing an example (part 2) of data explanation information. [Figure 14] FIG. 13 is a diagram showing an example (part 3) of data explanation information. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] An embodiment of the present invention will be described in detail below with reference to the drawings. In the following embodiment, a data explanation device 10 capable of generating an explanation for data related to a certain predetermined facility (hereinafter referred to as "target facility") will be described. Examples of the target facility include various plants such as power plants, steel plants, chemical plants, petroleum plants, and energy plants. Examples of the data related to the target facility include data showing the operation record of the target facility (hereinafter referred to as "operation record data") and data showing an optimal operation plan for the target facility (hereinafter referred to as "optimal operation plan data"). The optimal operation plan data is, for example, data obtained by solving an optimization problem for determining an optimal operation plan for the target facility.

[0010] The format of the optimization problem for obtaining the optimal operation plan data is not limited to a specific format, and it is possible to use optimal operation plan data obtained by solving an optimization problem of any format. That is, the optimal operation plan data may be, for example, data obtained by solving a continuous optimization problem, or data obtained by solving a discrete optimization problem (also called a "combinatorial optimization problem" or the like). In addition, various methods (e.g., metaheuristics, reinforcement learning, other existing methods, etc.) can be used to solve the optimization problem depending on the problem. In the following, as an example, it is assumed that the optimal operation plan data is data obtained by solving a continuous optimization problem.

[0011] Furthermore, targeting data related to facilities is just one example, and it is also possible to target data related to devices, data related to systems, etc.

[0012] Here, the data explanation device 10 according to the present embodiment generates an explanation for data related to the target equipment using domain knowledge of the target equipment and generation AI (Artificial Intelligence). As a result, even a user who does not have specialized knowledge about the target equipment can, for example, grasp problems in the current operation from the operation record and verify the validity of the optimal operation plan by referring to the explanation of the data related to the target equipment. In addition, it is also possible to confirm improvement measures for problems in 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 decision-making when a user makes some decision regarding the target equipment (for example, deciding whether or not to actually apply the optimal operation plan). Here, the domain knowledge refers to specialized knowledge in the industry or field to which the target equipment belongs.

[0013] The data explanation device 10 according to the present embodiment is realized, for example, by 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, and a tablet terminal.

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

[0015] <Example of target equipment configuration> Below, the energy plant shown in Figure 1 will be taken as an example of the target facility. The energy plant shown in Figure 1 is composed 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) is composed of a gas turbine that generates electricity from city gas, and an exhaust gas boiler that outputs steam from the gas exhausted from the gas turbine. The once-through boiler outputs steam from city gas. The turbo chiller outputs cold energy using the electricity generated by the gas turbine and purchased electricity as needed. The steam absorption chiller outputs cold energy using the steam output from the exhaust gas boiler and the steam output from the once-through boiler. The electricity, cold energy, and steam output from the energy plant are used for the power load, heat load, and steam load, respectively.

[0016] The configuration of the energy plant shown in FIG. 1 is just an example, and the present invention is not limited to this.

[0017] <Example of hardware configuration of data explanation device 10> An example of the hardware configuration of the data explanation device 10 according to this embodiment is shown in Fig. 2. As shown in Fig. 2, the data explanation device 10 according to this embodiment has 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 pieces of hardware is connected to each other via a bus 109 so as to be able to communicate with each other.

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

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

[0020] The communication I / F 104 is an interface for connecting to a communication network. The RAM 105 is a volatile semiconductor memory (storage device) that temporarily stores programs and data. The ROM 106 is a non-volatile semiconductor memory (storage device) that can store programs and data even when the power is turned off. The auxiliary storage device 107 is a non-volatile storage device such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory. The processor 108 is an arithmetic device such as a central processing unit (CPU) or a graphic processing unit (GPU).

[0021] 2 is an 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 and multiple processors 108, may not have some of the hardware shown in the figure, or may have various hardware other than the hardware shown in the figure.

[0022] <Example of functional configuration of data explanation device 10> An example of the functional configuration of the data explanation device 10 according to this embodiment is shown in Fig. 3. As shown in Fig. 3, the data explanation device 10 according to this embodiment has 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. In addition, the data explanation device 10 according to this embodiment has a data storage unit 301, a domain knowledge storage unit 302, and a template storage unit 303.

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

[0024] The data storage unit 301, the domain knowledge storage unit 302, and the template storage unit 303 are realized, for example, by a storage area of ​​the auxiliary storage device 107. At least one of these units may be realized by a storage area of ​​a storage device (e.g., a storage device provided in a database server) communicably connected to the data explanation device 10.

[0025] The explanation type selection unit 201 selects one or more explanation types for which the user wants to receive an explanation from one or more predetermined explanation types. An explanation type refers to a type of explanation for data related to the target equipment. As an example, two explanation types are assumed below: "problems with current operation" and "reason for optimization result." Here, "problems with current operation" is an explanation type for the case where an explanation is desired regarding problems with the current operation of the target equipment. On the other hand, "reason for optimization result" is an explanation type for the case where an explanation is desired regarding the reason for the optimal operation plan for the target equipment.

[0026] In addition to "problems with current operation" and "reason for optimization result", other explanation types may include, for example, "measures to remedy the problems" and "comparison and consideration of current operation and optimization result". "Measures to remedy the problems" is an explanation type for when an explanation is desired regarding solutions to problems with the current operation of the target equipment. "Comparison and consideration of current operation and optimization result" is an explanation type for when an explanation is desired regarding comparison and consideration of the current operation of the target equipment with the optimal operation plan.

[0027] The data acquisition unit 202 acquires at least one of the driving record data and the optimal operation plan data from the data storage unit 301 according to the explanation type selected by the explanation type selection unit 201. Here, for example, when the explanation type selected by the explanation type selection unit 201 is "problems with the current operation", the data acquisition unit 202 acquires driving record data from the data storage unit 301, and when the explanation type is "reason for optimization result", the data acquisition unit 202 acquires optimal operation plan data from the data storage unit 301. Note that when the explanation type is "measures to remedy the problem", the driving record data is acquired from the data storage unit 301, and when the explanation type is "comparison and consideration between the current operation and the optimization result", the driving record data and the optimal operation plan data are acquired from the data storage unit 301.

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

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

[0030] The prompt creation unit 205 acquires 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. The prompt creation unit 205 creates a prompt that instructs the generation of an explanation for the data by setting, for example, the data organized or converted by the information organization unit 203 and each piece of information included in the domain knowledge acquired by the domain knowledge acquisition unit 204 in the prompt template. A prompt template is a model (template) of a prompt. The prompt template is, for example, created in advance by a user or the like.

[0031] The explanation generating unit 206 generates data explanation information representing an explanation for the data acquired by the data acquiring unit 202, using the prompt created by the prompt creating unit 205 and the generating AI. That is, the explanation generating unit 206 generates data explanation information by the generating AI by inputting the prompt created by the prompt creating unit 205 to the generating AI. The explanation generating unit 206 may use a generating AI provided as an external service, may use a generating AI possessed by the data explanation device 10, or may use other generating AI. Note that since the large-scale language model realizing the generating AI also acquires various domain knowledge during learning, when the data explanation information is generated by the generating AI, it is expected that the data explanation information will be generated using domain knowledge that combines the domain knowledge acquired by the domain knowledge acquiring unit 204 and the domain knowledge acquired by the large-scale language model realizing the generating AI during learning.

[0032] Furthermore, the explanation generating unit 206 generates new data explanation information by the generation AI by inputting user input information, which will be described later, as a prompt to the generation AI. This new data explanation information is, for example, information that represents an additional explanation for the data explanation information previously generated by the generation AI, information that represents a summary of the data explanation information previously generated by the generation AI, information that represents a response to some question or instruction for the data explanation information previously generated by the generation AI, etc.

[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 the predetermined output destination include the display device 102 such as a display, a storage area such as the auxiliary storage device 107, other devices or equipment connected in a communicable manner, and the like.

[0034] The user input acquisition unit 208 inputs information such as a natural language sentence input by a user (hereinafter, also referred to as "user input information"). Examples of the user input information include information expressing a natural language sentence requesting additional explanation for the data explanatory information, information expressing a natural language sentence requesting a summary of the data explanatory information, information expressing a natural language sentence such as a standard question for the data explanatory information, and information expressing a natural language sentence meaning some kind of question or instruction for other data explanatory information.

[0035] The data storage unit 301 stores data (operation performance data, optimal operation plan data, etc.) related to the target facility. The operation performance data is collected from the target facility (more precisely, collected from sensors, etc. installed in the target facility or the devices or equipment constituting the target facility). On the other hand, the optimal operation plan data is obtained by solving an optimization problem for obtaining an optimal operation plan for the target facility. The subject that solves the optimization problem may be the data explanation device 10, or may be a server (e.g., a cloud server) that is communicably 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 called, for example, an "optimization calculation unit" as a functional unit for solving the optimization problem.

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

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

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

[0039] The explanation type selection unit 201 selects one or more explanation types for which the user wants to receive an explanation from one or more predetermined explanation types (step S101). Note that the explanation type selection unit 201 may select, for example, an explanation type designated by the user from one or more predetermined explanation types. In the following, as an example, it is assumed that "problems with the current operation" or "reason for the optimization result" is selected as the explanation type.

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

[0041] Here, the operation record data and the optimal operation plan data are expressed as time-series data of data (hereinafter referred to as "state data") consisting of one or more variables (when the target facility is a plant or the like, these variables are also called "state variables" or the like). When the target facility is the energy plant shown in Fig. 1, examples of the state variables include the amount of electricity purchased, the amount of city gas purchased, the amount of city gas consumed by the gas turbine, the power output of the gas turbine, the steam output of the exhaust gas boiler, the amount of electricity consumed by the turbo chiller, the heat output of the turbo chiller, the amount of steam consumed by the steam absorption chiller, the heat output of the steam absorption chiller, the amount of city gas consumed 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] When the operating performance data is acquired in step S102, the data acquisition unit 202 may, for example, sequentially acquire the status data constituting the operating performance data from the target equipment in real time.

[0043] The information organizing unit 203 organizes or converts the data (operation performance data or optimal operation plan data, or both) acquired in the above step S102 into a predetermined format (e.g., array format, etc.) that can be input to the generation AI (step S103). As an example, FIG. 5 shows data in which operation performance data in the case where the energy plant shown in FIG. 1 is the target facility is organized or converted into an array format. Similarly, FIG. 6 shows data in which optimal operation plan data in the case where the energy plant shown in FIG. 1 is the target facility is organized or converted into an array format. FIGS. 5 and 6 show examples in which the time series data of each state variable is expressed as an array. In FIGS. 5 and 6, each row represents one array, and in each array, the name of the state variable corresponding to the array and the unit of the value set for the state variable are set. In addition, in each array, the time series data of the state variables from time s=1 to time s=t is stored.

[0044] In addition, if the data acquired in the above step S102 (operation performance data or optimal operation plan data or both) is in a format that can be input to the generation AI, the above step S103 does not need to be executed.

[0045] The domain knowledge acquisition unit 204 acquires domain knowledge of the target facility from the domain knowledge storage unit 302 (step S104). As an example, domain knowledge in the case where the energy plant shown in FIG. 1 is the target facility is shown in FIG. 7. In the domain knowledge 1100 shown in FIG. 7, an explanation of the energy plant shown in FIG. 1 and characteristics of various facilities constituting the energy plant are written in natural language sentences. Note that the domain knowledge 1100 shown in FIG. 7 is an example and is not limited to this.

[0046] Prompt creation unit 205 acquires a prompt template from template storage unit 303 according to the explanation type selected in step S101 above (step S105). For example, if "problems with current driving" is selected as the explanation type in step S101 above, prompt creation unit 205 acquires prompt template 2100 shown in Fig. 8 from template storage unit 303. On the other hand, if "reason for optimization result" is selected as the explanation type in step S101 above, prompt creation unit 205 acquires prompt template 2200 shown in Fig. 9 from template storage unit 303.

[0047] The prompt template 2100 shown in FIG. 8 is a prompt template for generating an explanation of a problem with the current operation of the target equipment as an explanation for the operation record data. On the other hand, the prompt template 2200 shown in FIG. 9 is a prompt template for generating an explanation of the reason for the optimal operation plan of the target equipment as an explanation for the optimal operation plan data. Here, in the prompt template 2100 shown in FIG. 8, the variable part is represented by "****". Similarly, in the prompt template 2200 shown in FIG. 9, the variable part is represented by "****". The variable part is a part in which data (operation record data or optimal operation plan data or both), domain knowledge, etc. are set. By setting data, domain knowledge, etc. in the variable part included in the prompt template, a prompt that instructs the generation of an explanation for the data is created.

[0048] Note that the prompt template 2100 shown in Fig. 8 and the prompt template 2200 shown in Fig. 9 are both examples and are not limited to these. Various prompt templates can be used as long as they are prompt templates that instruct the generation of an explanation for data (i.e., prompts that include variable parts). Hereinafter, data or information set in variable parts included in a prompt template will be referred to as "setting information".

[0049] Prompt creator 205 creates a prompt that instructs the generation of an explanation for the data, using the data organized or converted in step S103, the domain knowledge acquired in step S104, and the prompt template acquired in step S105 (step S106). That is, prompt creator 205 creates a prompt that instructs the generation of an explanation for the data, by setting the data organized or converted in step S103 and each piece of information included in the domain knowledge acquired in step S104 to the variable portion included in the prompt template acquired in step S105.

[0050] As an example, Fig. 10 shows a prompt created by setting the operation record data shown in Fig. 5 and the domain knowledge 1100 shown in Fig. 7 for the variable portion included in the prompt template 2100 shown in Fig. 8. Prompt 3100 shown in Fig. 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 operation record data shown in Fig. 5) from the perspective of energy cost efficiency. Note that in prompt 3100 shown in Fig. 10, the setting information is shown in bold and underlined.

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

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

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

[0054] As an example, data explanation information generated by inputting the prompt 3100 shown in Fig. 10 into the generation AI is shown in Fig. 12. In the data explanation information 4100 shown in Fig. 12, problems with the current operation of the target equipment are explained in natural language sentences from the perspective of energy cost efficiency.

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

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

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

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

[0059] As an example, the user input information acquired in step S109 above is information representing a natural language sentence requesting a summary of the data description information, and new data description information in the case where data description information 4100 shown in Fig. 12 was generated in step S107 above is shown in Fig. 14. Data description information 4300 shown in Fig. 14 is data description information representing a summary of the data description information 4100 shown in Fig. 12.

[0060] <Modification> The prompt and its template are not limited to natural language sentences, and may include content such as images, videos, sounds, etc. Furthermore, they may include mathematical expressions, program codes, etc.

[0061] In particular, when instructing the AI ​​to perform some kind of numerical calculation or processing, the prompt may contain the formula or program code used in the numerical calculation or processing, which makes it possible to reduce calculation errors when the AI ​​performs numerical calculations.

[0062] <Summary> As described above, the data explanation device 10 according to the present embodiment generates and outputs an explanation for data related to the target equipment using the domain knowledge of the target equipment and the generation AI. As a result, the data explanation device 10 according to the present embodiment can generate an explanation for the data based on the domain knowledge of the target equipment. For this reason, even a user who does not have specialized knowledge about the target equipment can make various decisions by referring to data explanation information that represents an explanation of data related to the target equipment. For example, it is possible to solve problems in the current operation by grasping the problems from the operation record, to verify the validity of an optimal operation plan and determine whether the operation plan can be applied, and to improve the current operation by comparing the current operation with the optimal operation plan.

[0063] The present invention is not limited to the above-described embodiments specifically disclosed, and various modifications, changes, combinations with known technologies, etc. 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 media 104 Communication I / F 105 RAM 106 ROM 107 Auxiliary storage 108 processors 109 Bus 201 Explanation Type Selection Section 202 Data Acquisition Department 203 Information Organizing Department 204 Domain Knowledge Acquisition Department 205 Prompt Creation Department 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 section

Claims

1. A selection unit that selects a type of explanation to be generated for data related to the facility; a data acquisition unit that acquires the data according to the selected type; A domain knowledge acquisition unit that acquires domain knowledge of the facility; a prompt generator that generates a prompt that instructs the generation of the explanation based on the data and the domain knowledge; An explanation generation unit that generates information representing the explanation based on the prompt and a generation AI realized by a machine learning model including a large-scale language model; An information processing device having the above configuration.

2. The prompt creation unit is According to the selected type, a template corresponding to the selected type is obtained from one or more pre-created templates; The information processing apparatus according to claim 1 , wherein the prompt is created by setting the data and the domain knowledge for an acquired template.

3. The type includes a type that represents an explanation regarding the reason for the optimal operation plan of the facility, The data acquisition unit is 3. The information processing device according to claim 1, wherein when the selected type is a type representing an explanation regarding the reason for the optimal operation plan of the equipment, optimal operation plan data representing the optimal operation plan of the equipment obtained by solving a predetermined optimization problem is acquired as the data.

4. The types include types that represent explanations of problems with the current operation of the equipment, The data acquisition unit is The information processing apparatus according to claim 3 , wherein when the selected type is a type representing an explanation regarding a problem with a current operation of the facility, operation record data representing an operation record of the facility is acquired as the data.

5. a user input acquisition unit that acquires user input information representing an instruction to summarize the information representing the explanation, an instruction to provide additional explanation to the information representing the explanation, or a question or a predetermined instruction; The explanation generation unit is The information processing device according to claim 1 , further comprising: generating an instruction for the summary, an instruction for additional explanation, or information satisfying the question or the specified instruction based on the user input information and the generation AI.

6. 2. The information processing device according to claim 1, wherein the domain knowledge includes at least one of an operating characteristic of the facility, an operating schedule of the facility, input / output characteristics of devices constituting the facility, upper and lower limit constraints on input / output of the devices constituting the facility, an input / output relationship of the devices constituting the facility, a cost required for operating the facility, and a normal range and an abnormal range of output of the devices constituting the facility.

7. A selection step for selecting a type of explanation to be generated for the data relating to the facility; a data acquisition step of acquiring the data according to the selected type; A domain knowledge acquisition step for acquiring domain knowledge of the equipment; a prompt generation step for generating a prompt based on the data and the domain knowledge to direct the generation of the explanation; an explanation generation step of generating information representing the explanation based on the prompt and a generation AI realized by a machine learning model including a large-scale language model; An information processing method implemented by a computer.

8. A selection step for selecting a type of explanation to be generated for the data relating to the facility; a data acquisition step of acquiring the data according to the selected type; A domain knowledge acquisition step for acquiring domain knowledge of the equipment; a prompt generation step for generating a prompt based on the data and the domain knowledge to direct the generation of the explanation; an explanation generation step of generating information representing the explanation based on the prompt and a generation AI realized by a machine learning model including a large-scale language model; A program that causes a computer to execute the following.

Images