Large model planning simulation agent implementation method based on wind, light and hydrogen storage

Abstract

The invention provides a wind, light and hydrogen storage-based large model planning simulation agent implementation method, which comprises the following steps of: according to planning simulation demand information, acquiring a parameter set corresponding to a wind, light and hydrogen storage low-carbon energy system; performing language conversion processing on the parameter set by adopting a LangChain programming framework, and taking the converted natural language description information as a cue word prompt; inputting the prompt word prompt into the large model to generate an input parameter; the planning simulation tool is controlled to call an application programming interface API, a low-carbon energy system planning simulation algorithm is adopted to perform planning processing and simulation processing on the input parameters and the parameter set, and a planning simulation result is returned to the large model; the planning simulation result is displayed through the large model, and the technical problems that in the prior art, due to artificial planning simulation of the low-carbon energy system, the planning simulation efficiency of the low-carbon energy system is low, and the planning simulation accuracy is poor are solved.

Description

Technical Field

[0001] The present application relates to the technical field of large language models, and in particular to a method for realizing a large model planning simulation intelligent agent based on wind, solar, and hydrogen storage. Background Art

[0002] The rapid development of low-carbon energy systems in recent years has enabled energy conservation and reduced carbon dioxide emissions. Low-carbon energy systems, for example, can integrate multiple low-carbon technologies and measures to reduce carbon emissions. When planning low-carbon energy systems, users can employ complex drag-and-drop methods and wiring to achieve this goal. However, manual planning and simulation of low-carbon energy systems results in low efficiency and poor accuracy. Summary of the Invention

[0003] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0004] To this end, the first purpose of this application is to propose a large-model planning simulation intelligent agent implementation method based on wind, solar, and hydrogen storage, which can reduce the steps of planning simulation, realize planning simulation in the low-carbon energy field with large models as the core, and improve the efficiency and accuracy of planning simulation.

[0005] The second purpose of this application is to propose a large-scale model planning simulation intelligent agent implementation device based on wind, solar and hydrogen storage.

[0006] The third objective of this application is to provide a server.

[0007] The fourth object of this application is to provide a computer-readable storage medium.

[0008] A fifth object of this application is to provide a computer program product.

[0009] To achieve the above objectives, the first embodiment of the present application proposes a large-scale model planning simulation intelligent agent implementation method based on wind, solar, and hydrogen storage, including:

[0010] According to the planning simulation demand information, obtain the parameter set corresponding to the low-carbon energy system of wind, solar, hydrogen and storage;

[0011] The LangChain programming framework is used to perform language conversion processing on the parameter set, and the converted natural language description information is used as the prompt word;

[0012] Input the prompt word prompt into the large model to generate input parameters;

[0013] The control planning simulation tool calls an application programming interface (API), uses a low-carbon energy system planning simulation algorithm to perform planning processing and simulation processing on the input parameters and the parameter set, and returns planning simulation results to the large model;

[0014] The planning simulation results are displayed through the large model.

[0015] According to some embodiments, the method further comprises:

[0016] In the case where the parameter set is a list parameter set, obtaining parameter category information corresponding to the list parameter set;

[0017] When the category complexity corresponding to the parameter category information is greater than the complexity threshold, category identification is performed on the parameters of each list total in the list type parameter set to obtain the input category of the parameters of each list total.

[0018] According to some embodiments, the control planning simulation tool calls an application programming interface (API) and uses a low-carbon energy system planning simulation algorithm to perform planning and simulation processing on the input parameters and the parameter set to obtain planning simulation results, including:

[0019] Controlling the planning simulation tool to initialize the parameter set using the input parameters, and obtaining the parameter set and converting it into JSON format information;

[0020] The planning simulation tool is controlled to call an application programming interface (API), and a low-carbon energy system planning simulation algorithm is used to perform planning processing and simulation processing on the JSON format information to obtain a planning simulation result.

[0021] According to some embodiments, obtaining a parameter set corresponding to a low-carbon energy system of wind, solar, hydrogen and storage includes:

[0022] Determine the input structure corresponding to the planning simulation demand information of the low-carbon energy system of wind, solar, hydrogen and storage;

[0023] Determining, according to the input structure, parameter names corresponding to the wind, solar, hydrogen and storage low-carbon energy system;

[0024] According to the parameter name, obtain a parameter set corresponding to the wind, solar, hydrogen and storage low-carbon energy system.

[0025] According to some embodiments, returning the planning simulation results to the large model includes:

[0026] According to the planning simulation requirement information of the wind, solar, hydrogen and storage low-carbon energy system, obtaining display format information corresponding to the planning simulation result;

[0027] The display format information and the planning simulation result are returned to the large model, wherein the display format information is used to instruct the large model to use the display format information to display the planning simulation result.

[0028] According to some embodiments, the method further comprises:

[0029] Obtaining a modified planning simulation result according to a modification instruction for the planning simulation result;

[0030] The modified planning simulation result is used to fine-tune the large model to obtain an adjusted large model.

[0031] To achieve the above objectives, the second embodiment of the present application proposes a large-scale model planning simulation intelligent agent implementation device based on wind, solar, and hydrogen storage, including:

[0032] A set acquisition unit is used to acquire a parameter set corresponding to the low-carbon energy system of wind, solar, hydrogen and storage according to the planning simulation demand information;

[0033] A set conversion unit, configured to perform language conversion processing on the parameter set using the LangChain programming framework, and use the converted natural language description information as a prompt word;

[0034] A parameter generating unit, configured to input the prompt word prompt into the large model to generate input parameters;

[0035] A result returning unit is used to control the planning simulation tool to call the application programming interface API, use the low-carbon energy system planning simulation algorithm to perform planning processing and simulation processing on the input parameters and the parameter set, and return the planning simulation results to the large model;

[0036] The result returning unit is further used to display the planning simulation result through the large model.

[0037] To achieve the above-mentioned purpose, a third embodiment of the present application provides a server, comprising: a processor, and a memory communicatively connected to the processor;

[0038] The memory stores computer-executable instructions;

[0039] The processor executes the computer-executable instructions stored in the memory to implement the method as described in the first aspect above.

[0040] To achieve the above-mentioned purpose, the fourth embodiment of the present application proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect above.

[0041] To achieve the above-mentioned purpose, the fifth embodiment of the present application proposes a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0042] The present application provides a large-scale model planning simulation intelligent agent implementation method based on wind, solar, hydrogen and storage. The method obtains a parameter set corresponding to a low-carbon energy system of wind, solar, hydrogen and storage according to planning simulation requirement information; uses the LangChain programming framework to perform language conversion processing on the parameter set, and uses the converted natural language description information as a prompt word; inputs the prompt word prompt into the large-scale model to generate input parameters; controls the planning simulation tool to call the application programming interface (API), uses the low-carbon energy system planning simulation algorithm to perform planning and simulation processing on the input parameters and the parameter set, and returns the planning simulation results to the large-scale model; and displays the planning simulation results. This method solves the problem that manual planning and simulation of low-carbon energy systems results in low planning and simulation efficiency and poor planning simulation accuracy. The LangChain programming framework can directly perform planning simulation based on the obtained parameters and planning simulation tool results, without manual participation, reducing the requirement for manual professional background knowledge, and eliminating the need for tedious and complex dragging and wiring. This can lower the application threshold of planning simulation, reduce the steps of planning simulation, and realize planning simulation in the low-carbon energy field with large models as the core, thereby improving the efficiency and accuracy of planning simulation.

[0043] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0045] Figure 1 A flow chart of a method for implementing a large-scale model planning simulation agent based on wind, solar, and hydrogen storage provided in an embodiment of the present application;

[0046] Figure 2 A flow chart of another method for implementing a large-scale model planning simulation agent based on wind, solar, and hydrogen storage provided in an embodiment of the present application;

[0047] Figure 3 This is a schematic diagram illustrating an implementation method of a large-scale model planning simulation intelligent agent based on wind, solar, and hydrogen storage according to an embodiment of the present application; and

[0048] Figure 4This is a structural diagram of a large-scale model planning simulation intelligent agent implementation device based on wind, solar, and hydrogen storage in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0050] The following describes the implementation method and device of the large-scale model planning simulation intelligent agent based on wind, solar, hydrogen and storage in the embodiment of the present application with reference to the accompanying drawings.

[0051] According to some embodiments, the present application provides a large-scale model planning simulation intelligent agent implementation method based on wind, solar, and hydrogen storage, which can reduce the steps of planning simulation, realize planning simulation in the low-carbon energy field with a large model as the core, and improve the efficiency and accuracy of planning simulation, such as Figure 1 As shown, the large-scale model planning simulation agent implementation method based on wind, solar and hydrogen storage includes the following steps:

[0052] Step 101: Obtain a parameter set corresponding to a low-carbon energy system of wind, solar, hydrogen and storage based on planning simulation demand information;

[0053] According to some embodiments, the execution entity of the technical solution of the present embodiment may be, for example, a server. The server does not specifically refer to a fixed server. For example, when the server identifier changes, the server may also change accordingly. For example, when the server structure changes, the server may also change accordingly. The server may be, for example, a single server or a server cluster, which is not limited in the present embodiment.

[0054] In some embodiments, the planning simulation requirement information may be, for example, information for planning and simulating a current low-carbon energy system. The planning simulation requirement information does not specifically refer to fixed information. For example, when corresponding parameters in the planning simulation requirement information change, the planning simulation requirement information may also change accordingly. For example, when the time point at which the planning simulation requirement information is received changes, the planning simulation requirement information may also change accordingly.

[0055] In some embodiments, a low-carbon energy system may be a system that operates using low-carbon energy, which may be a type of energy with low or zero emissions. The low-carbon energy in the embodiments of the present application may be, for example, wind, solar, and hydrogen storage energy.

[0056] According to some embodiments, a wind-solar-hydrogen-storage low-carbon energy system refers to a system that utilizes renewable energy technologies such as wind power and photovoltaics to convert electricity into hydrogen and store it in hydrogen storage tanks. This wind-solar-hydrogen-storage low-carbon energy system is not specific to a fixed system. For example, if the corresponding renewable energy source in the wind-solar-hydrogen-storage low-carbon energy system changes, the wind-solar-hydrogen-storage low-carbon energy system can also change accordingly.

[0057] In some embodiments, a parameter set may be, for example, a collection of at least one parameter. The parameter set is not specifically a fixed set. For example, when a parameter in the parameter set changes, the parameter set may also change accordingly. For example, when the number of parameters corresponding to the parameter set changes, the parameter set may also change accordingly. For example, when the type of parameter corresponding to the parameter set changes, the parameter set may also change accordingly.

[0058] In some embodiments, a parameter set corresponding to a low-carbon energy system of wind, solar, hydrogen and storage is obtained based on the planning simulation requirement information. For example, different planning simulation requirement information may correspond to different parameter sets.

[0059] Step 102: Using the LangChain programming framework to perform language conversion on the parameter set, and using the converted natural language description information as a prompt;

[0060] According to some embodiments, the language conversion process may be, for example, a process of converting the acquired parameter set into a target language description, wherein the target language description may be, for example, a natural language description.

[0061] In some embodiments, the prompt word may refer to text input into the macro model, and the prompt word prompt is not specifically a fixed prompt word prompt. For example, when the method for generating the prompt word prompt changes, the prompt word prompt may also change accordingly. For example, when the parameter set changes, the prompt word prompt may also change accordingly.

[0062] In some embodiments, for example, the LangChain programming framework may be used to perform language conversion processing on the parameter set, and the converted natural language description information may be used as a prompt word.

[0063] Step 103: input the prompt word prompt into the large model to generate input parameters;

[0064] According to some embodiments, the large model may also be referred to as a large language model. For example, the large model may be a trained model that can be used to process the prompt word. The large model does not specifically refer to a fixed model; for example, when the model parameters corresponding to the large model change, the large model may also change accordingly. For example, when the specific model type corresponding to the large model changes, the large model may also change accordingly.

[0065] In some embodiments, input parameters may refer to parameters input to a called tool. These input parameters are not necessarily fixed parameters. For example, when the called tool changes, the input parameters may also change accordingly. For example, when the method for generating input parameters changes, such as when the macro model changes, the input parameters may also change accordingly.

[0066] In some embodiments, the prompt word prompt is input into a large model to generate input parameters.

[0067] Step 104: the control planning simulation tool calls an application programming interface (API), uses a low-carbon energy system planning simulation algorithm to perform planning and simulation processing on the input parameters and the parameter set, and returns planning simulation results to the large model;

[0068] In some embodiments, the API may be, for example, an interface corresponding to a corresponding tool. The API does not specifically refer to a fixed interface. For example, when the tool changes, the API may also change accordingly.

[0069] In some embodiments, the low-carbon energy system planning simulation algorithm may be, for example, a predetermined algorithm that can be used for planning and simulation processing. The low-carbon energy system planning simulation algorithm does not specifically refer to a fixed algorithm. For example, when the algorithm type corresponding to the low-carbon energy system planning simulation algorithm changes, the low-carbon energy system planning simulation algorithm may also change accordingly. For example, when the algorithm parameters corresponding to the low-carbon energy system planning simulation algorithm change, the low-carbon energy system planning simulation algorithm may also change accordingly.

[0070] In some embodiments, the planning simulation result may be, for example, a result corresponding to a parameter set and planning simulation requirement information. The planning simulation result is not specifically a fixed result. For example, when the parameter set or planning simulation requirement information changes, the planning simulation result may also change accordingly. For example, when the low-carbon energy system planning simulation algorithm changes, the planning simulation result may also change accordingly.

[0071] In some embodiments, for example, the planning simulation tool can be controlled to call the application programming interface API, use the low-carbon energy system planning simulation algorithm to perform planning and simulation processing on the input parameters and the parameter set, and return the planning simulation results to the large model.

[0072] Step 105: Display the planning simulation results through the large model.

[0073] In some embodiments, the planning simulation results may be displayed via the large model.

[0074] The present application provides a large-scale model planning simulation intelligent agent implementation method based on wind, solar, hydrogen and storage. The method obtains a parameter set corresponding to a low-carbon energy system of wind, solar, hydrogen and storage according to planning simulation requirement information; uses the LangChain programming framework to perform language conversion processing on the parameter set, and uses the converted natural language description information as a prompt word; inputs the prompt word prompt into the large-scale model to generate input parameters; controls the planning simulation tool to call the application programming interface (API), uses the low-carbon energy system planning simulation algorithm to perform planning and simulation processing on the input parameters and the parameter set, and returns the planning simulation results to the large-scale model; and displays the planning simulation results. This method solves the problem that manual planning and simulation of low-carbon energy systems results in low planning and simulation efficiency and poor planning simulation accuracy. The LangChain programming framework can directly perform planning simulation based on the obtained parameters and planning simulation tool results, without manual participation, reducing the requirement for manual professional background knowledge, and eliminating the need for tedious and complex dragging and wiring. This can lower the application threshold of planning simulation, reduce the steps of planning simulation, and realize planning simulation in the low-carbon energy field with large models as the core, thereby improving the efficiency and accuracy of planning simulation.

[0075] This embodiment provides another large-scale model planning simulation intelligent agent implementation method based on wind, solar, and hydrogen storage, such as Figure 2 As shown, the large-scale model planning simulation intelligent agent implementation method based on wind, solar and hydrogen storage may include the following steps:

[0076] Step 201, determining an input structure corresponding to planning simulation demand information of a low-carbon energy system of wind, solar, hydrogen and storage;

[0077] Among them, the relevant descriptions have been mentioned above and will not be repeated here.

[0078] According to some embodiments, the execution entity of the technical solution of the present embodiment may be, for example, a server. The server does not specifically refer to a fixed server. For example, when the server identifier changes, the server may also change accordingly. For example, when the server structure changes, the server may also change accordingly. The server may be, for example, a single server or a server cluster, which is not limited in the present embodiment.

[0079] Among them, this embodiment provides an example schematic diagram of a large model planning simulation intelligent agent implementation method based on wind, solar, and hydrogen storage, such as Figure 3 As shown, it can specifically include a client, a large language model, a planning simulation tool based on wind, solar, hydrogen and storage, and a planning simulation API. The specific implementation process of each part is described below and will not be repeated here.

[0080] Different low-carbon energy systems, including wind, solar, and hydrogen storage, can correspond to different planning and simulation requirements, which in turn can correspond to different input structures. The input structure indicates the structure of input parameters. The input structure determines the parameter input order, input names, and related settings. This input structure is not a fixed structure. For example, if the input order of the corresponding parameters changes, the input structure can also change accordingly.

[0081] In some embodiments, for example, an input structure corresponding to planning simulation requirement information for a low-carbon energy system including wind, solar, hydrogen, and storage can be determined. For example, the input structure can be obtained from a corresponding table of the relationship between planning simulation requirement information and input structures, or the input structure can be determined based on a determination instruction. This is not limited to the embodiments of the present application.

[0082] Step 202: Determine the parameter name corresponding to the wind, solar, hydrogen and storage low-carbon energy system according to the input structure;

[0083] Among them, the relevant descriptions have been mentioned above and will not be repeated here.

[0084] In some embodiments, the parameter name may refer to at least one parameter name, which may be a name corresponding to the current planning simulation information. When the planning simulation information changes, the input structure may also change accordingly, and the input name may also change accordingly.

[0085] In some embodiments, the parameter name corresponding to the wind, solar, hydrogen and storage low-carbon energy system is determined based on the input structure.

[0086] Step 203: Acquire a parameter set corresponding to the wind, solar, hydrogen and storage low-carbon energy system according to the parameter name;

[0087] Among them, the relevant descriptions have been mentioned above and will not be repeated here.

[0088] For example, a class can be implemented to define the input structure (schema) of the planning simulation tool. The parameter set may include, for example, a time scale, a start date, longitude and latitude, multiple photovoltaic settings, multiple wind turbine settings, multiple battery settings, multiple grid settings, multiple load settings, multiple electrolyzer settings, and multiple hydrogen storage tank settings. For example, each row may define the variable name, variable type (single value or list, integer or floating point, etc.), a text description of the variable (as a prompt to help the model understand the variable's meaning), and a default value. Specific parameter sets may include, for example, a time scale, a time resolution, a start date, longitude and latitude, a photovoltaic list, a wind turbine list, a battery list, a grid list, a load list, an electrolyzer list, a hydrogen storage tank list, and the like.

[0089] Step 204: Using the LangChain programming framework to perform language conversion on the parameter set, and using the converted natural language description information as a prompt;

[0090] Among them, the relevant descriptions have been mentioned above and will not be repeated here.

[0091] Step 205: input the prompt word prompt into the large model to generate input parameters;

[0092] Among them, the relevant descriptions have been mentioned above and will not be repeated here.

[0093] In some embodiments, the large model can be used, for example, to identify user intent.

[0094] According to some embodiments, LangChain can be controlled to convert all parameters into natural language descriptions as prompts to input into the large model.

[0095] Step 206: The control planning simulation tool calls an application programming interface (API), uses a low-carbon energy system planning simulation algorithm to perform planning and simulation processing on the input parameters and the parameter set, and returns planning simulation results to the large model.

[0096] Among them, the relevant descriptions have been mentioned above and will not be repeated here.

[0097] According to some embodiments, the application programming interface API may be, for example, a planning simulation application programming interface API.

[0098] According to some embodiments, returning the planning simulation results to the large model includes:

[0099] According to the planning simulation requirement information of the wind, solar, hydrogen and storage low-carbon energy system, obtaining display format information corresponding to the planning simulation result;

[0100] The display format information and the planning simulation results are returned to the large model, wherein the display format information is used to instruct the large model to display the planning simulation results using the display format information. Therefore, the display format information corresponding to the planning simulation information can be used for display, thereby improving the accuracy and convenience of displaying the planning simulation results.

[0101] The display format information may include, for example, text descriptions, web page links with text and images, and the like.

[0102] According to some embodiments, the method further comprises:

[0103] Obtaining a modified planning simulation result according to a modification instruction for the planning simulation result;

[0104] The modified planning simulation results are used to fine-tune the large model to obtain the adjusted large model. Therefore, the accuracy of obtaining the large model and the accuracy of obtaining the planning simulation results can be improved.

[0105] Step 207: Display the planning simulation results through the large model.

[0106] Among them, the relevant descriptions have been mentioned above and will not be repeated here.

[0107] According to some embodiments, the method further comprises:

[0108] In the case where the parameter set is a list parameter set, obtaining parameter category information corresponding to the list parameter set;

[0109] When the category complexity corresponding to the parameter category information is greater than the complexity threshold, category identification is performed on the parameters of each list total in the list type parameter set to obtain the input category of the parameters of each list total.

[0110] According to some embodiments, taking photovoltaics as an example, the parameter category information may include photovoltaic rated power, photovoltaic power temperature coefficient, light intensity under photovoltaic standard test conditions, temperature under photovoltaic standard test conditions, and photovoltaic nominal operating temperature, where different categories may correspond to different units.

[0111] According to some embodiments, the control planning simulation tool calls an application programming interface (API) and uses a low-carbon energy system planning simulation algorithm to perform planning and simulation processing on the input parameters and the parameter set to obtain planning simulation results, including:

[0112] Controlling the planning simulation tool to initialize the parameter set using the input parameters, and obtaining the parameter set and converting it into JSON format information;

[0113] The planning simulation tool is controlled to call an application programming interface (API), and a low-carbon energy system planning simulation algorithm is used to perform planning processing and simulation processing on the JSON format information to obtain a planning simulation result.

[0114] According to some embodiments, the planning simulation requirement information and parameter set of the low-carbon energy system can be obtained in the chat box, and the control model can generate the corresponding JSON based on the parameter set, where the key is the variable name in the above class and the value is the parameter value in the parameter set. The planning simulation tool can be controlled to initialize the parameter set based on the JSON generated by the large model, and the parameter set can be converted into JSON and sent to the low-carbon system planning simulation algorithm through an API request. The calculation results can return a text description of the planning and simulation results and a webpage link with text and image results. These results are returned to the large model and presented in the user chat interface.

[0115] In the embodiment of the present application, an input structure corresponding to the planning simulation requirement information of the low-carbon energy system of wind, solar, hydrogen and storage is determined; according to the input structure, the parameter name corresponding to the low-carbon energy system of wind, solar, hydrogen and storage is determined; according to the parameter name, a parameter set corresponding to the low-carbon energy system of wind, solar, hydrogen and storage is obtained. Therefore, the corresponding input parameters can be obtained through the planning simulation requirement information, the inaccurate acquisition of the parameter set is reduced, the accuracy of the acquisition of the parameter set is improved, the application threshold of the planning simulation can be lowered, the steps of the planning simulation can be reduced, and the planning simulation in the low-carbon energy field with a large model as the core can be realized, thereby improving the efficiency and accuracy of the planning simulation.

[0116] In order to implement the above embodiments, the present application also proposes a large-scale model planning simulation intelligent agent implementation device based on wind, solar, and hydrogen storage.

[0117] Figure 4 A structural schematic diagram of a large-scale model planning simulation intelligent agent implementation device based on wind, solar, and hydrogen storage provided in an embodiment of the present application.

[0118] like Figure 4 As shown, the large-scale model planning simulation intelligent agent implementation device based on wind, solar and hydrogen storage includes:

[0119] The set acquisition unit 401 is used to acquire a parameter set corresponding to the low-carbon energy system of wind, solar, hydrogen and storage according to the planning simulation demand information;

[0120] A set conversion unit 402 is configured to perform language conversion processing on the parameter set using the LangChain programming framework, and use the converted natural language description information as a prompt word;

[0121] A parameter generating unit 403 is used to input the prompt word prompt into the large model to generate input parameters;

[0122] A result returning unit 404 is configured to control the planning simulation tool to call an application programming interface (API), perform planning and simulation processing on the input parameters and the parameter set using a low-carbon energy system planning simulation algorithm, and return planning simulation results to the large model;

[0123] The result returning unit 404 is further configured to display the planning simulation result through the large model.

[0124] Furthermore, in a possible implementation of the embodiment of the present application, the result returning unit 404 is further configured to:

[0125] In the case where the parameter set is a list parameter set, obtaining parameter category information corresponding to the list parameter set;

[0126] When the category complexity corresponding to the parameter category information is greater than the complexity threshold, category identification is performed on the parameters of each list total in the list type parameter set to obtain the input category of the parameters of each list total.

[0127] Furthermore, in a possible implementation of the embodiment of the present application, the result returning unit 404 is configured to control the planning simulation tool to call an application programming interface (API), perform planning processing and simulation processing on the input parameters and the parameter set using a low-carbon energy system planning simulation algorithm, and obtain planning simulation results, specifically for:

[0128] Controlling the planning simulation tool to initialize the parameter set using the input parameters, and obtaining the parameter set and converting it into JSON format information;

[0129] The planning simulation tool is controlled to call an application programming interface (API), and a low-carbon energy system planning simulation algorithm is used to perform planning processing and simulation processing on the JSON format information to obtain a planning simulation result.

[0130] Furthermore, in a possible implementation of the embodiment of the present application, the set acquisition unit 401 is used to acquire a parameter set corresponding to the low-carbon energy system of wind, solar, hydrogen and storage, specifically to:

[0131] Determine the input structure corresponding to the planning simulation demand information of the low-carbon energy system of wind, solar, hydrogen and storage;

[0132] Determining, according to the input structure, parameter names corresponding to the wind, solar, hydrogen and storage low-carbon energy system;

[0133] According to the parameter name, obtain a parameter set corresponding to the wind, solar, hydrogen and storage low-carbon energy system.

[0134] Furthermore, in a possible implementation of the embodiment of the present application, the result returning unit 404, when used to return the planning simulation result to the large model, is specifically used to:

[0135] According to the planning simulation requirement information of the wind, solar, hydrogen and storage low-carbon energy system, obtaining display format information corresponding to the planning simulation result;

[0136] The display format information and the planning simulation result are returned to the large model, wherein the display format information is used to instruct the large model to use the display format information to display the planning simulation result.

[0137] Furthermore, in a possible implementation of the embodiment of the present application, the result returning unit 404 is further specifically configured to:

[0138] Obtaining a modified planning simulation result according to a modification instruction for the planning simulation result;

[0139] The modified planning simulation result is used to fine-tune the large model to obtain an adjusted large model.

[0140] It should be noted that the above explanation of the embodiment of the large-scale model planning simulation intelligent agent implementation method based on wind, solar, hydrogen and storage is also applicable to the large-scale model planning simulation intelligent agent implementation device based on wind, solar, hydrogen and storage in this embodiment, and will not be repeated here.

[0141] In the embodiment of the present application, a set acquisition unit is used to obtain a parameter set corresponding to a low-carbon energy system of wind, solar, hydrogen and storage according to planning simulation demand information; a set conversion unit is used to perform language conversion processing on the parameter set using the LangChain programming framework, and use the converted natural language description information as a prompt word prompt; a parameter generation unit is used to input the prompt word prompt into the large model to generate input parameters; a result return unit is used to control the planning simulation tool to call the application programming interface API, use the low-carbon energy system planning simulation algorithm to perform planning processing and simulation processing on the input parameters and the parameter set, and return the planning simulation result. The result is returned to the large model; the result return unit is further used to display the planning simulation result through the large model, which solves the problem that manual planning simulation of low-carbon energy systems makes the planning simulation efficiency of low-carbon energy systems low and the planning simulation accuracy poor. Through the LangChain programming framework, planning simulation of planning simulation results can be directly performed according to the acquired parameters and planning simulation tools, without the need for manual participation, reducing the requirements for manual professional background knowledge, and without the need for tedious and complicated dragging and wiring. It can lower the application threshold of planning simulation, reduce the steps of planning simulation, and realize planning simulation in the low-carbon energy field with large models as the core, thereby improving the efficiency and accuracy of planning simulation.

[0142] In order to implement the above embodiments, the present application also proposes a server, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0143] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0144] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0145] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0146] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0147] This application contemplates providing implementations that allow users to selectively block the use or access of personal information data. Specifically, this disclosure contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0148] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0149] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0150] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0151] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0152] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0153] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0154] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0155] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A large-scale model planning simulation intelligent agent implementation method based on wind, solar, and hydrogen storage, characterized in that: include: According to the planning simulation demand information, obtain the parameter set corresponding to the low-carbon energy system of wind, solar, hydrogen and storage; The LangChain programming framework is used to perform language conversion processing on the parameter set, and the converted natural language description information is used as the prompt word; Input the prompt word prompt into the large model to generate input parameters; The control planning simulation tool calls an application programming interface (API), uses a low-carbon energy system planning simulation algorithm to perform planning processing and simulation processing on the input parameters and the parameter set, and returns planning simulation results to the large model; The planning simulation results are displayed through the large model.

2. The method according to claim 1, characterized in that The method further comprises: In the case where the parameter set is a list parameter set, obtaining parameter category information corresponding to the list parameter set; When the category complexity corresponding to the parameter category information is greater than the complexity threshold, category identification is performed on the parameters of each list total in the list type parameter set to obtain the input category of the parameters of each list total.

3. The method according to claim 2, characterized in that The control planning simulation tool calls an application programming interface (API) and uses a low-carbon energy system planning simulation algorithm to perform planning and simulation processing on the input parameters and the parameter set to obtain planning simulation results, including: Controlling the planning simulation tool to initialize the parameter set using the input parameters, and obtaining the parameter set and converting it into JSON format information; The planning simulation tool is controlled to call an application programming interface (API), and a low-carbon energy system planning simulation algorithm is used to perform planning processing and simulation processing on the JSON format information to obtain a planning simulation result.

4. The method according to claim 1, wherein The obtaining of a parameter set corresponding to the low-carbon energy system of wind, solar, hydrogen and storage includes: Determine the input structure corresponding to the planning simulation demand information of the low-carbon energy system of wind, solar, hydrogen and storage; Determining, according to the input structure, parameter names corresponding to the wind, solar, hydrogen and storage low-carbon energy system; According to the parameter name, obtain a parameter set corresponding to the wind, solar, hydrogen and storage low-carbon energy system.

5. The method according to claim 1, characterized in that The returning the planning simulation result to the large model includes: According to the planning simulation requirement information of the wind, solar, hydrogen and storage low-carbon energy system, obtaining display format information corresponding to the planning simulation result; The display format information and the planning simulation result are returned to the large model, wherein the display format information is used to instruct the large model to use the display format information to display the planning simulation result.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining a modified planning simulation result according to a modification instruction for the planning simulation result; The modified planning simulation result is used to fine-tune the large model to obtain an adjusted large model.

7. A large-scale model planning simulation intelligent agent implementation device based on wind, solar, and hydrogen storage, characterized in that: include: A set acquisition unit is used to acquire a parameter set corresponding to the low-carbon energy system of wind, solar, hydrogen and storage according to the planning simulation demand information; A set conversion unit, configured to perform language conversion processing on the parameter set using the LangChain programming framework, and use the converted natural language description information as a prompt word; A parameter generating unit, configured to input the prompt word prompt into the large model to generate input parameters; A result returning unit is used to control the planning simulation tool to call the application programming interface API, use the low-carbon energy system planning simulation algorithm to perform planning processing and simulation processing on the input parameters and the parameter set, and return the planning simulation results to the large model; The result returning unit is further used to display the planning simulation result through the large model.

8. A server, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images