Carbon emission reduction path generation method and device, terminal equipment and storage medium

Abstract

The embodiment of the invention provides a carbon emission reduction path generation method and device, terminal equipment and a storage medium, and relates to the technical field of computers. Obtaining region basic data of a to-be-planned region, and inputting the region basic data into a pre-trained prediction model for processing to obtain basic scene data; the basic scene data is used for representing the development trend of energy consumption and carbon emission of the to-be-planned region; determining a target carbon reduction means set according to a target carbon reduction scene input by a user, the basic scene data and a preset carbon reduction means library; the target carbon reduction means set comprises at least one carbon reduction means; and generating a carbon emission reduction path according to the target carbon reduction means set. Therefore, the planning efficiency and practicability of the carbon emission reduction path can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, in particular to a carbon emission reduction path generation method and device, a terminal equipment and a storage medium. BACKGROUND

[0002] At present, the double carbon target has become the mainstream trend of global development, and new energy technology is advancing at an unprecedented speed. The entire chain of energy from production to consumption is undergoing profound changes.

[0003] Under this background, the energy development planning and carbon emission reduction path research at the regional level are facing increasing work pressure. At present, the regional new energy and carbon emission reduction path planning involves many parameters, complex optional paths and various technical means, resulting in obvious deficiencies in planning efficiency and practicability of the carbon emission reduction path planning mode relying on expert experience or traditional systems, which is difficult to meet the growing planning demand. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a carbon emission reduction path generation method, device, terminal equipment and storage medium to improve the planning efficiency and practicability of the carbon emission reduction path.

[0005] In order to achieve the above-mentioned purpose, the technical solutions adopted by the embodiments of the present application are as follows: In a first aspect, the present application provides a carbon emission reduction path generation method, which comprises: obtaining the regional basic data of the region to be planned, inputting the regional basic data into a pre-trained prediction model for processing to obtain basic scenario data; the basic scenario data is used to represent the development trend of energy consumption and carbon emission of the region to be planned; determining a target carbon reduction means set according to the target carbon reduction scenario input by the user, the basic scenario data and a pre-set carbon reduction means library; the target carbon reduction means set includes at least one carbon reduction means; generating a carbon emission reduction path according to the target carbon reduction means set.

[0006] In an optional implementation, the method of determining a target carbon reduction means set according to the target carbon reduction scenario input by the user, the basic scenario data and a pre-set carbon reduction means library comprises: obtaining at least one carbon reduction means in response to the selection operation of the user based on the target carbon reduction scenario and the carbon reduction means library; determining a carbon reduction means set according to at least one carbon reduction means, and performing carbon reduction simulation according to the carbon reduction means set and the basic scenario data to obtain a prediction curve; the prediction curve represents the development trend of energy consumption and carbon emission of the region to be planned under the carbon reduction means; In response to a selection operation of a user based on a plurality of carbon reduction means sets, a target carbon reduction means set is obtained.

[0007] In an optional implementation, the method further includes: The region basic data of the region to be planned is obtained by a pre-trained large language model, and the region basic data is input into a pre-trained prediction model for processing to obtain basic scenario data. The target carbon reduction means set is determined according to the target carbon reduction scenario input by the user, the basic scenario data, and a preset carbon reduction means library. The target carbon reduction means set is determined by the large language model according to the target carbon reduction scenario input by the user, the basic scenario data, and the preset carbon reduction means library. The carbon reduction path is generated according to the target carbon reduction means set. The carbon reduction path is generated by the large language model according to the target carbon reduction means set.

[0008] In an optional implementation, the method further includes: The carbon reduction path is input into a pre-trained large language model, and supplementary information of the carbon reduction path is generated by the large language model; the supplementary information includes evaluation information and / or update information of the carbon reduction path.

[0009] In an optional implementation, the large language model is trained by a pre-constructed corpus, and the corpus is constructed by a carbon emission database, the prediction model, and the carbon reduction means library.

[0010] In an optional implementation, the method further includes: A carbon emission database is constructed. The prediction model and the carbon reduction means library are constructed according to the carbon emission database.

[0011] In a second aspect, the application provides a carbon reduction path generation device, which includes: An acquisition module is configured to acquire region basic data of a region to be planned, input the region basic data into a pre-trained prediction model for processing, and obtain basic scenario data; the basic scenario data is used to represent a development trend of energy consumption and carbon emission of the region to be planned. A determination module is configured to determine a target carbon reduction means set according to a target carbon reduction scenario input by a user, the basic scenario data, and a preset carbon reduction means library. The determining module is further configured to generate a carbon emission reduction path according to the target carbon emission reduction means set.

[0012] In an optional implementation, the determining module is further configured to: in response to a selection operation of a user based on the target carbon emission reduction scenario and the carbon emission reduction means library, obtain at least one carbon emission reduction means; determine a carbon emission reduction means set according to the at least one carbon emission reduction means; perform carbon emission reduction simulation according to the carbon emission reduction means set and the basic scenario data to obtain a prediction curve; the prediction curve represents a development trend of energy consumption and carbon emission of the region to be planned under the carbon emission reduction means; and in response to a selection operation of a user based on a plurality of carbon emission reduction means sets, obtain the target carbon emission reduction means set.

[0013] In a third aspect, the present application provides a terminal device, comprising a processor and a memory, the memory stores a computer program capable of being executed by the processor, and the processor can execute the computer program to implement the method of any one of the preceding embodiments.

[0014] In a fourth aspect, the present application provides a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method of any one of the preceding embodiments.

[0015] The carbon emission reduction path generation method and device, terminal device and storage medium provided by the embodiments of the present application input the region basic data of the region to be planned into a prediction model for processing to obtain basic scenario data representing the development trend of energy consumption and carbon emission of the region to be planned, which provides a benchmark basis for subsequent superposition and path optimization of carbon emission reduction means, thereby guaranteeing the practicability of the finally generated carbon emission reduction path. On this basis, a target carbon emission reduction means set containing at least one carbon emission reduction means can be determined based on the target carbon emission reduction scenario, the carbon emission reduction means library and the basic scenario data, so that the carbon emission reduction path is generated according to the target carbon emission reduction means set, and therefore the planning efficiency of the carbon emission reduction path can be further improved.

[0016] In order to make the above objectives, characteristics and advantages of the present application more apparent and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0018] Figure 1 The block schematic diagram of the terminal device provided by the embodiments of the present application is shown. Figure 2 A flowchart of a carbon emission reduction path generation method provided by an embodiment of the present application is shown; Figure 3 A platform interface diagram is shown; Figure 4 A functional module diagram of a carbon emission reduction path generation device provided by an embodiment of the present application is shown.

[0019] Icon: 100 - memory; 110 - processor; 120 - communication module; 200 - acquisition module; 210 - determination module. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0021] Therefore, the detailed description of the embodiments of the present application provided in the drawings below is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0022] It should be noted that the relational terms such as "first" and "second" and the like are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0023] Figure 1 is a block diagram of a terminal device provided by an embodiment of the present application, please see Figure 1 The terminal device includes a memory 100, a processor 110 and a communication module 120. The memory 100, the processor 110 and the communication module 120 are directly or indirectly electrically connected to each other to realize the transmission or interaction of data. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines.

[0024] The memory 100 is configured to store computer programs or data capable of being executed by the processor. The memory 100 can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0025] The processor 110 is configured to read / write the data or programs stored in the memory and execute the computer programs to implement the carbon emission reduction path generation method provided in the embodiments of the present application.

[0026] The communication module 120 is configured to establish a communication connection between the terminal device and other communication terminals through a network, and to receive and transmit data through the network.

[0027] It should be understood that, Figure 1 The structure shown is only a structural schematic diagram of the terminal device, and the terminal device can further include more or fewer components than those shown in Figure 1 or have a different configuration from Figure 1 The components shown in Figure 1 may be implemented in hardware, software, or a combination thereof.

[0028] Next, the terminal device in the above Figure 1 is taken as the execution subject, and the carbon emission reduction path generation method provided in the embodiments of the present application is exemplarily introduced in combination with the flowchart.

[0029] Specifically, Figure 2 for the carbon emission reduction path generation method provided in the embodiments of the present application, please refer to Figure 2 The method comprises the following steps. In step S20, the region basic data of the region to be planned is acquired, and the region basic data is input into a pre-trained prediction model for processing to obtain basic scene data.

[0030] The basic scene data is used to represent the development trend of energy consumption and carbon emission of the region to be planned.

[0031] Optionally, the regional basic data refers to energy consumption and carbon emission related data of the region to be planned, which is the input basic information of the prediction model.

[0032] In a possible implementation manner, the regional basic data includes, but is not limited to, regional energy consumption status data, carbon emission status data, regional basic information (such as population, industrial structure, economic development level, etc.), planning year, and other parameters related to energy consumption and carbon emission. The data can be obtained from local government statistical data, industry reports, scientific research literature, news information, and other channels.

[0033] In this embodiment, in order to adapt to the input requirements of the prediction model, the terminal device can perform a preprocessing operation of structuring and formatting the regional basic data, including cleaning, standardizing, normalizing, and field mapping of the original data, to ensure the consistency of the data format and the model input format.

[0034] Optionally, the prediction model can be a secondary development and construction based on an open source machine learning model, or a special model designed and trained according to actual needs.

[0035] In this embodiment, the prediction model can be used to perform operation according to the regional basic data, to predict future scenario data capable of reflecting the development trend of future energy consumption and carbon emission of the region, and then combine the historical actual scenario data with the future scenario data to obtain basic scenario data.

[0036] It can be understood that the basic scenario data includes historical scenario data and predicted future scenario data. For example, it covers the past 5-10 years to the future 5-40 years, and each year of the basic scenario data corresponds to a complete section of data, including total energy consumption, total carbon emission, and its sub-item composition (such as the contribution proportion of the fields of industry, transportation, and building).

[0037] It should be noted that the basic scenario data refers to the energy consumption and carbon emission of the region to be planned without any carbon reduction processing. The basic scenario data can be used to represent the historical trend and future trend of energy consumption and carbon emission of the region to be planned, and also provides a benchmark reference for subsequent scenario construction based on carbon reduction means.

[0038] In actual application, the basic scenario data supports manual fine-tuning by the user, so as to locally correct the model output result according to actual policy guidance, technical feasibility, or social and economic development expectation, thereby enhancing the practicality and adaptability of the planning scheme.

[0039] Step S21, determining a target carbon reduction means set according to the target carbon reduction scenario input by the user, the basic scenario data, and a preset carbon reduction means library.

[0040] The target carbon reduction means set includes at least one carbon reduction means.

[0041] Optionally, the target carbon reduction scene is related to a carbon reduction target to be achieved by the user, such as a low-carbon scene, a zero-carbon scene, and the like.

[0042] Optionally, the carbon reduction means library includes specific carbon reduction means, such as improving the energy efficiency of building equipment, limiting the production capacity of high-energy-consuming industries, implementing the elimination of backward production capacity, and the like.

[0043] It can be understood that in the embodiment, on the basis of the basic scene data, the development trend of energy consumption and carbon emissions of the to-be-planned region can be made to meet the requirements of the target carbon reduction scene by superimposing the carbon reduction means in the target carbon reduction means set.

[0044] In step S22, a carbon emission reduction path is generated according to the target carbon reduction means set.

[0045] In the embodiment, the terminal device can integrate all the carbon reduction means in the target carbon reduction means set according to a preset integration rule, and encapsulate the same to obtain the carbon emission reduction path.

[0046] In addition, the basic scene data, regional basic data, and the like can be integrated when the carbon emission reduction path is integrated.

[0047] Optionally, in one planning service project for a to-be-planned region, one basic scene can correspond to multiple target carbon reduction scenes, that is, carbon emission reduction path planning for multiple carbon reduction scenes can be simultaneously performed according to the basic situation of the to-be-planned region, so as to allow the user to make overall analysis and research. In order to ensure that different target carbon reduction scenes can coexist completely, a data isolation operation can be performed on the carbon emission reduction paths corresponding to different target carbon reduction scenes. Optionally, the carbon emission reduction path can be fed back to the user in the form of a table, a document, a report, web page content, APP feedback, mini-program feedback, and the like.

[0048] The carbon emission reduction path generation method provided in the embodiment of the application, the terminal device inputs the regional basic data of the to-be-planned region into a prediction model for processing to obtain basic scene data representing the development trend of energy consumption and carbon emissions of the to-be-planned region, which provides a benchmark basis for subsequent superposition of carbon reduction means and path optimization, thereby ensuring the practicability of the finally generated carbon emission reduction path. On this basis, the target carbon reduction means set including at least one carbon reduction means can be determined based on the target carbon reduction scene, the carbon reduction means library, and the basic scene data, and the carbon emission reduction path can be generated according to the target carbon reduction means set, so as to further improve the planning efficiency of the carbon emission reduction path.

[0049] In order to ensure the rational and effective generation of the carbon emission reduction path, a prediction model and a carbon reduction means library can be constructed in advance to build the data basis and technical support of the entire carbon emission reduction path planning method.

[0050] Specifically, a carbon emission database can be constructed first, and then a prediction model and a carbon reduction means library can be constructed based on the carbon emission database.

[0051] In actual application, the process of constructing the carbon emission database includes obtaining structured or unstructured data related to carbon emissions from multiple sources and standardizing the data to ensure consistency and availability. These data sources include but are not limited to: existing regional energy development planning documents, professional terms and their explanations, national and local relevant standards and laws and regulations, the latest carbon reduction measures and policy documents, the current energy consumption and carbon emission data of the target region, its natural and geographical conditions, economic development level, energy structure, historical carbon emission change trend, relevant news materials and academic research results, etc. After extraction, cleaning, classification and structuring, the above data is uniformly stored in the carbon emission database as basic data support for subsequent model construction and means design.

[0052] In one possible implementation, based on the current energy consumption and carbon emission data of the region in the carbon emission database, the basic information of the region, the planning year and other related parameters, a prediction model that can predict the medium and long-term energy consumption and carbon emission development trend of the region can be constructed by using mathematical modeling or machine learning methods.

[0053] In this embodiment, the output result of the prediction model can be future scenario data. In addition, in order to facilitate visual analysis, the prediction model can also output the change curve corresponding to the basic scenario data, as well as the sub-item composition data classified by industry or use. It can be understood that the change curve can reflect the energy consumption and carbon emission development trend from the past to the future.

[0054] Optionally, the prediction model can be developed based on existing open source models, or it can be developed independently according to actual needs.

[0055] Optionally, the process of constructing the carbon reduction means library is based on the carbon reduction measures, projects, policies, etc. in the carbon emission database, which are abstracted into operable "means" according to certain classification rules, and the corresponding mathematical expressions are established to quantify their impact on the development trend of energy consumption and carbon emissions.

[0056] In this embodiment, the carbon reduction means can be classified according to application fields, such as primary classifications of building, transportation, industry, agriculture, carbon absorption, energy, waste, etc., and each classification contains several specific carbon reduction means, such as prolonging the service life of buildings, promoting near-zero carbon energy consumption buildings, and improving the energy efficiency of building equipment in the field of building; optimizing the energy consumption structure of the industry, limiting high energy consumption capacity, implementing the elimination of backward production capacity, and promoting the replacement of electric energy in the field of industry. Each means has an independent influence function, and there is also an interaction relationship between different means, which can also be modeled by a mathematical model.

[0057] In addition, some means can support users to change their effects by adjusting the parameters in the function, thereby enhancing the flexibility and applicability of the system, for example, adjusting the size of photovoltaics to adapt to the actual photovoltaic conditions of the specific area to be planned.

[0058] Optionally, in order to ensure the effectiveness of the carbon reduction means library and prevent the carbon reduction means therein from being outdated, the terminal device can also update the carbon reduction means in the carbon reduction means library in real time according to news, academic research, and other information to ensure the integration of the latest technical means.

[0059] It can be understood that constructing the carbon emission database and the prediction model and the carbon reduction means library based on the database are indispensable basic links in the entire carbon emission reduction path generation method. The carbon emission database provides raw data support for the prediction model and the carbon reduction means library, and the prediction model and the carbon reduction means library respectively undertake the functions of trend simulation and means evaluation. In actual application, this three-layer structure system of data-model-means ensures that the system has sufficient data basis, scientific calculation logic, and rich means selection when generating the carbon emission reduction path, thereby realizing efficient and accurate planning of regional energy development and carbon emission reduction path.

[0060] For example, when the system constructs the carbon emission reduction path of a certain business district in a city, it first calls the basic data of the region, such as historical energy consumption data, carbon emission data, economic structure information, etc., to construct the carbon emission database; then trains or selects a prediction model based on the database to simulate the basic energy consumption and carbon emission trend of the region without intervention; and finally, combined with the mathematical expressions of various means in the carbon reduction means library, the carbon reduction effect under different means combinations is simulated to generate a carbon emission reduction path scheme for users to evaluate and select.

[0061] Next, a possible implementation way of how to determine the target carbon reduction means set according to the target carbon reduction scene input by the user, the basic scene data, and the preset carbon reduction means library is provided. In one possible implementation way, a carbon emission reduction path generation platform or application program can be provided on the terminal device, and the user can realize human-computer interaction with the terminal device based on the platform or application program.

[0062] In this embodiment, the terminal device can respond to the user's selection operation based on the target carbon reduction scenario and the carbon reduction means library, obtain at least one carbon reduction means, determine a carbon reduction means set based on the at least one carbon reduction means, perform carbon reduction simulation based on the carbon reduction means set and basic scenario data, obtain a prediction curve, and then respond to the user's selection operation based on multiple carbon reduction means sets to obtain the target carbon reduction means set.

[0063] Among them, the prediction curve represents the development trend of energy consumption and carbon emissions in the planned area under carbon reduction measures.

[0064] Specifically, in actual application, the terminal device first uses the generated basic scenario data, that is, the energy consumption and carbon emission development trends in the region without additional intervention, as the starting point for constructing the target carbon reduction scenario.

[0065] The terminal device can display the various carbon reduction measures in the carbon reduction measures library and the basic scenario curve composed of basic scenario data through the platform interface, so that the user can select the carbon reduction measures based on the interface. At this time, the terminal device can perform carbon reduction simulation on the basic scenario based on the carbon reduction measures selected by the user, thereby generating a prediction curve.

[0066] In one example, Figure 3 This is a schematic diagram of the platform interface, please see Figure 3 The corresponding means library can be displayed on this interface. The carbon reduction means library contains multiple means classified by application fields, such as construction, transportation, industry, etc. Each means has a mathematical expression that affects the regional energy consumption and carbon emission curve, and supports users to adjust parameters to optimize the simulation effect.

[0067] Users can add the required means to the current scenario by dragging, clicking buttons, or selecting through pop-up windows. For example, by dragging the corresponding means to the planning measures, the platform can combine the selected means into a carbon reduction means set after receiving the user's selection operation. The platform then calls the prediction model and performs simulation calculations based on the carbon reduction means set and basic scenario data to generate a prediction curve reflecting the changing trend of regional energy consumption and carbon emissions under the combination of means. This prediction curve not only contains overall trend data, but can also be subdivided into sub-curves for various industries or uses, such as Figure 3 The emission reductions in the building sector, carbon reductions in the industrial sector, etc. are included for users to conduct multi-dimensional assessments.

[0068] Further, the user can also create multiple different carbon reduction means sets in the platform and perform simulation calculations respectively to obtain multiple corresponding prediction curves. These prediction curves represent the carbon reduction effects under different means combinations, and the user can compare and analyze multiple simulation results based on factors such as planning goals, policy orientation, and economic feasibility, and finally select an optimal carbon reduction means set as a target carbon reduction means set. The target carbon reduction means set will be the core input for generating a carbon emission reduction path in the subsequent process, and will be used to generate the final planning scheme required by the user.

[0069] It should be noted that the "responding to the selection operation of the user based on multiple carbon reduction means sets" in the above process does not only refer to the simple selection of multiple means by the user, but also refers to the comprehensive evaluation of the simulation results of different means combinations by the user with the support of the system, and the selection of the combination that best meets the planning goals of the user. This interactive selection mechanism improves the flexibility and practicality of the system, enabling the user to more intuitively and efficiently participate in the construction process of the carbon emission reduction path.

[0070] It can be understood that through the above-mentioned manner, the target carbon reduction means set finally generated can not only meet the specific planning needs of the user, but also have scientificity and executability.

[0071] In another possible implementation manner, the user can also input the data standards corresponding to the target carbon reduction scenario, and the terminal device can filter out the prediction curves that meet the corresponding data standards based on the prediction curves corresponding to multiple different carbon reduction means sets, and take the carbon reduction means set corresponding to the prediction curves as the target carbon reduction means set.

[0072] Considering that the above-mentioned operations not only have certain requirements for the professional knowledge reserves of the user, but also involve a large amount of complex data processing, model calling and parameter configuration operations, making it difficult for non-professionals to efficiently participate in the planning work, in order to reduce the operation threshold of the user, a pre-trained large language model can also be introduced to reduce the interaction complexity between the user and the system. Specifically, the terminal device can obtain the regional basic data of the region to be planned through the pre-trained large language model, input the regional basic data into the pre-trained prediction model for processing to obtain basic scenario data; determine the target carbon reduction means set according to the target carbon reduction scenario input by the user, the basic scenario data and the preset carbon reduction means library through the large language model; and generate a carbon emission reduction path according to the target carbon reduction means set through the large language model.

[0073] Specifically, in actual application, the large language model can be embedded in the platform, and can be used to assist the user in generating basic scenario data.

[0074] At this stage, the user can describe the relevant information of the target region in natural language form, such as the name of the region, the scale of the building, the current status of energy use, the level of carbon emissions, the planning year, etc.

[0075] During the execution of the above steps, the large language model is limited to the professional field of energy planning through a preset context guidance mechanism (such as the fixed prompt "Please act as an expert in regional energy development and carbon reduction path planning. Please extract key parameters from my conversation content and generate basic scene data below"), so that it can accurately identify the key information in the user input and automatically extract the input parameters required for generating the basic scene.

[0076] For parameters not explicitly provided by the user, the large language model can also intelligently complete or fine-tune based on existing data, ensuring that the prediction model has complete input conditions. Subsequently, the system inputs the extracted and completed regional basic data into the pre-trained prediction model, and after calculation, outputs the basic scene data reflecting the development trend of energy consumption and carbon emissions in the region without intervention, including annual data and itemized constituent data.

[0077] In addition, after the user proposes the target carbon reduction scenario demand, the terminal device will combine the pre-obtained basic scene data, the user's input carbon reduction target and related constraint conditions, and the preset carbon reduction means library, and use the large language model to recommend and build means combinations.

[0078] In this process, the terminal device can input the basic scene data as context information into the large language model, and guide the user to input their carbon reduction target, policy orientation, resource constraints, or industry characteristics, etc. through natural language input. Based on the user input content, the large language model intelligently analyzes and recommends the most suitable means combination from the carbon reduction means library, forming one or more candidate carbon reduction means combinations. These candidate combinations are then input into the prediction model for simulation calculation, generating corresponding prediction curves for further selection and optimization by the user, or automatically selected by the large language model to provide the best carbon reduction means combination to the user.

[0079] When the user confirms the target carbon reduction means combination, the terminal device can also call the large language model again to generate the final carbon reduction path based on the means combination. In this step, the large language model not only undertakes the functions of organizing and presenting path data, but also automatically generates natural language form output content such as path explanation, technical suggestion, policy matching, implementation points, etc. based on the simulation results of the means combination, to assist the user in understanding the planning results.

[0080] The carbon emission reduction path generation method provided in the embodiments of the present application effectively reduces the dependence of users on professional modeling knowledge by introducing a large language model, improves the ease of use and adaptability of the system, so that non-professional users can also efficiently complete the whole process operation from data input to path output, and at the same time, the interactive experience of the user can be improved.

[0081] In addition, after the terminal device completes the construction of the basic scene and the multiple target carbon reduction scenes, the carbon emission reduction path data that has been determined can be input into the large language model, and supplementary information of the carbon emission reduction path can be generated by the large language model. The supplementary information can include evaluation information and / or update information of the carbon emission reduction path.

[0082] Specifically, after receiving the carbon emission reduction path data, the large language model can perform semantic understanding and comprehensive evaluation on the input path based on professional knowledge in the field of energy development planning, policies and regulations, standards and specifications, and typical cases, evaluate the scientificity, rationality, operability and economy of the carbon emission reduction path from multiple dimensions, and generate corresponding evaluation information.

[0083] In a possible implementation manner, the evaluation information includes but is not limited to whether the path meets the time node requirement of the national or local carbon peak and carbon neutralization target, whether there is a technical implementation difficulty, whether there is economic feasibility, whether there is policy support condition, and the like.

[0084] In the embodiment, the update information refers to the modification suggestion or adjustment suggestion given by the large language model. Based on the latest policy dynamics, technical progress or academic research results, the large language model can generate update information for the carbon emission reduction path, for example, recommend to add or optimize certain emission reduction means, adjust the implementation order or parameter configuration of the means, so as to improve the timeliness and advancement of the overall planning scheme.

[0085] It can be understood that whether the evaluation information or the update information is generated by the large language model can be determined according to the interactive content of the user.

[0086] In the embodiment, the large language model can be trained by a pre-constructed corpus, and the corpus is constructed by a carbon emission database, a prediction model and a carbon reduction means library.

[0087] Optionally, the large language model is not a general-purpose large language model, but a model that has been specialized trained for the field of regional energy development and carbon reduction path planning, thereby having the ability to understand, reason, generate and optimize carbon reduction paths in this vertical field. Specifically, the training process of the large language model includes key steps such as corpus construction, model training, packaging and calling, and the core training resources it relies on include carbon emission database, prediction model and carbon reduction means library. These data and models provide the large language model with a foundation of domain knowledge and support for reasoning capabilities.

[0088] In this embodiment, first, the corpus can be extracted and organized based on the carbon emission database, prediction model related parameters and carbon reduction means library. These data can include structured historical planning cases, professional terms, policies and regulations, carbon reduction measures, and historical and predicted data of regional energy consumption and carbon emissions, etc. After screening, classification and formatting, they can be organized into question and answer pairs or dialogue samples suitable for large language model training. For example, simulate the interactive process between the user and the system, and convert the input of the regional energy status into guided dialogue records generated by the basic scene data. In actual operation, reference can be made to the construction method of public data sets, such as the multi-turn dialogue data set provided by Belle Group, to ensure the diversity and practicality of the corpus.

[0089] After obtaining the structured corpus, secondary training can be performed based on open source large language model framework, such as DeepSeek series model. This process involves adjusting and optimizing the parameters of the original large language model to enable it to accurately understand and respond to professional problems and instructions related to regional energy development and carbon reduction path planning.

[0090] In addition to the corpus, during the training process, the energy consumption and carbon emission trend data output by the prediction model, the mathematical expressions of each means in the carbon reduction means library and their combined influence relationship, etc. can also be used as supplementary input for model training to enhance the model's prediction ability and logical reasoning ability in specific tasks. Finally, the trained model is packaged as a dedicated vertical field large language model and knowledge base, which can support user and system interaction in multiple use stages.

[0091] To perform the corresponding steps in the above embodiments and various possible manners, an implementation of a carbon reduction path generation device is given below, which can optionally use the device structure of the terminal equipment shown in the above Figure 1 . Further, please refer to Figure 4 , Figure 4A functional module diagram of a carbon emission reduction path generation apparatus provided by an embodiment of the present application. It should be noted that the carbon emission reduction path generation apparatus provided by the present embodiment has the same basic principles and technical effects as the above-described embodiments. For brevity, the present embodiment is not described in some parts, and the corresponding content of the above-described embodiments can be referred to. The carbon emission reduction path generation apparatus comprises an acquisition module 200 and a determination module 210.

[0092] The acquisition module 200 is configured to acquire regional basic data of a region to be planned, input the regional basic data into a pre-trained prediction model for processing, and obtain basic scenario data. The basic scenario data is used to represent the development trend of energy consumption and carbon emission of the region to be planned.

[0093] It can be understood that the acquisition module 200 can also be used to perform the above step S20.

[0094] The determination module 210 is configured to determine a target carbon reduction means set according to a target carbon reduction scenario input by a user, basic scenario data, and a pre-set carbon reduction means library.

[0095] The determination module is further configured to generate a carbon emission reduction path according to the target carbon reduction means set.

[0096] It can be understood that the determination module 210 can also be used to perform the above steps S21-S22.

[0097] Optionally, the determination module 210 is further configured to acquire at least one carbon reduction means in response to a selection operation of the user based on the target carbon reduction scenario and the carbon reduction means library, determine a carbon reduction means set according to the at least one carbon reduction means, perform carbon reduction simulation according to the carbon reduction means set and the basic scenario data to obtain a prediction curve, wherein the prediction curve represents the development trend of energy consumption and carbon emission of the region to be planned under the carbon reduction means, and obtain a target carbon reduction means set in response to a selection operation of the user based on a plurality of carbon reduction means sets.

[0098] Optionally, the acquisition module 200 is further configured to acquire regional basic data of a region to be planned by using a pre-trained large language model, input the regional basic data into a pre-trained prediction model for processing, and obtain basic scenario data.

[0099] Optionally, the determination module 210 is further configured to determine a target carbon reduction means set according to a target carbon reduction scenario input by a user, basic scenario data, and a pre-set carbon reduction means library by using a large language model, and generate a carbon emission reduction path according to the target carbon reduction means set by using the large language model.

[0100] Optionally, the determining module 210 is further configured to input the carbon emission reduction path into a pre-trained large language model, and generate supplementary information of the carbon emission reduction path by the large language model; the supplementary information comprises evaluation information and / or update information of the carbon emission reduction path.

[0101] Optionally, the carbon emission reduction path generation apparatus further comprises a constructing module configured to construct a carbon emission database, and construct a prediction model and a carbon emission reduction means library according to the carbon emission database.

[0102] Optionally, the above modules can be stored in the memory shown in the form of software or firmware (Firmware) or solidified in the operating system (Operating System, OS) of the terminal device, and can be executed by the processor in the terminal device. Figure 1 The data, program code and the like required for executing the above modules can be stored in the memory. Figure 1

[0103] The application also provides a storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the carbon emission reduction path generation method provided by the application.

[0104] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can also be implemented by other manners. The apparatus embodiments described above are only schematic, for example, the flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the apparatus, method and computer program product according to the embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logic function. It should also be noted that, in some alternative implementations, the functions noted in the blocks can occur in different orders from those noted in the drawings. For example, two consecutive blocks can actually be executed in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system for implementing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0105] In addition, each functional module in the embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0106] ​If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts of the prior art that make contributions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0107] The above is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for generating a carbon emission reduction path, characterized in that: The method comprises: Obtaining regional basic data for the area to be planned, inputting the regional basic data into a pre-trained prediction model for processing to obtain basic scenario data; the basic scenario data is used to characterize the development trend of energy consumption and carbon emissions in the area to be planned; Determining a target carbon reduction means set based on the target carbon reduction scenario input by the user, the basic scenario data, and a preset carbon reduction means library; the target carbon reduction means set includes at least one carbon reduction means; A carbon reduction path is generated based on the target carbon reduction means set.

2. The method according to claim 1, characterized in that The step of determining a target carbon reduction means set based on the target carbon reduction scenario input by the user, the basic scenario data, and a preset carbon reduction means library includes: In response to a user's selection operation based on the target carbon reduction scenario and the carbon reduction means library, obtaining at least one carbon reduction means; Determining a carbon reduction means set based on at least one of the carbon reduction means, performing a carbon reduction simulation based on the carbon reduction means set and the basic scenario data to obtain a prediction curve; the prediction curve represents the development trend of energy consumption and carbon emissions in the planned area under the carbon reduction means; In response to a user's selection operation based on a plurality of carbon reduction means sets, the target carbon reduction means set is obtained.

3. The method according to claim 1, characterized in that The step of obtaining basic regional data of the area to be planned and inputting the basic regional data into a pre-trained prediction model for processing to obtain basic scenario data includes: Obtaining regional basic data of the area to be planned through a pre-trained large language model, inputting the regional basic data into a pre-trained prediction model for processing to obtain basic scenario data; The step of determining a target carbon reduction means set based on the target carbon reduction scenario input by the user, the basic scenario data, and a preset carbon reduction means library includes: Determining a target carbon reduction means set by the large language model based on the target carbon reduction scenario input by the user, the basic scenario data, and a preset carbon reduction means library; Generating a carbon emission reduction path according to the target carbon reduction means set includes: A carbon emission reduction path is generated according to the target carbon reduction means set through the large language model.

4. The method according to claim 1, wherein The method further comprises: The carbon emission reduction path is input into a pre-trained large language model, and supplementary information of the carbon emission reduction path is generated by the large language model; the supplementary information includes evaluation information and / or update information of the carbon emission reduction path.

5. The method according to any one of claims 3 to 4, characterized in that: The large language model is obtained by training a pre-constructed corpus, and the corpus is constructed by using a pre-constructed carbon emission database, the prediction model and the carbon reduction means library.

6. The method according to claim 1, characterized in that The method further comprises: Build a carbon emission database; The prediction model and the carbon reduction means library are constructed based on the carbon emission database.

7. A carbon emission reduction path generation device, characterized in that: The device comprises: An acquisition module is used to obtain regional basic data of the area to be planned, input the regional basic data into a pre-trained prediction model for processing, and obtain basic scenario data; the basic scenario data is used to characterize the development trend of energy consumption and carbon emissions in the area to be planned; A determination module, configured to determine a target carbon reduction means set based on a target carbon reduction scenario input by a user, the basic scenario data, and a preset carbon reduction means library; The determination module is further configured to generate a carbon emission reduction path according to the target carbon reduction means set.

8. The device according to claim 7, characterized in that The determination module is also used to respond to the user's selection operation based on the target carbon reduction scenario and the carbon reduction means library to obtain at least one carbon reduction means; determine a carbon reduction means set based on at least one of the carbon reduction means, perform carbon reduction simulation based on the carbon reduction means set and the basic scenario data, and obtain a prediction curve; the prediction curve represents the development trend of energy consumption and carbon emissions in the area to be planned under the carbon reduction means; and respond to the user's selection operation based on multiple carbon reduction means sets to obtain the target carbon reduction means set.

9. A terminal device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the method according to any one of claims 1 to 6.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images