Coal power enterprise pollution reduction and carbon reduction cooperative control effect accounting evaluation system and method

Abstract

The invention provides a coal power enterprise pollution reduction and carbon reduction cooperative control effect accounting evaluation system and method, and relates to the technical field of coal power. The method comprises the following steps: intelligently identifying coal and electricity emission data of each pollution source class with a timestamp through a trained and constructed emission AI accounting evaluation model, recommending and outputting an emission amount calculation strategy of a corresponding type, carrying out corresponding emission amount accounting based on the recommended emission amount calculation strategy, and outputting a corresponding emission amount accounting result. And the emission accounting result of each pollution source class is counted, so that the coal-electricity emission accounting amount of the enterprise can be quickly obtained. According to the invention, the monitored coal electricity emission data is marked with the timestamp based on the credibility institution, and the coal electricity emission data marked based on the timestamp is subjected to data intelligent accounting calculation, so that the data credibility can be improved, and the AI model can be utilized to carry out data classification calculation, thereby realizing intelligent accounting of emission of pollutants such as coal electricity carbon and the like. The checking efficiency is improved, the checking period is shortened, and the checking difficulty of pollution reduction and carbon reduction of coal power enterprises is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of coal power, and in particular to a system and method for accounting and evaluating the effectiveness of collaborative control of pollution reduction and carbon emission reduction in coal power enterprises. Background Art

[0002] The coal power industry has long suffered from high energy consumption and high emissions. How to achieve low-carbon transformation while taking into account the collaborative control of pollutant emission reduction and carbon emission reduction is a key challenge that urgently needs to be solved in current coal power emission accounting.

[0003] The coal power emission accounting list plays a core role in the low-carbon transformation of coal power enterprises and the collaborative control of pollution reduction and carbon emission reduction. By constructing an accurate emission list, emission data of various pollutants and greenhouse gases of coal power enterprises can be systematically collected, and the emission reduction potential of emission sources can be quantified. A precise accounting list can provide a clear technical path for the low-carbon transformation of coal power enterprises, clarify which links have the greatest emission reduction potential, and how to achieve the reduction of multiple pollutants through collaborative control.

[0005] Table 1 shows the accounting scope of various emission sources. The accounting substances for general air pollutants include sulfur dioxide (SO₂), oxides (NOₓ), carbon monoxide (CO), volatile organic compounds (VOCs), ammonia (NH₃), total suspended particulates (TSP), inhalable particulates (PM₁₀), fine particulates (PM₂.₅), black carbon (BC), and organic carbon (OC). The accounting scope of power and heat sources includes the atmospheric pollutant emissions generated by production facilities of enterprises in the industries of thermal power generation (D4411), cogeneration of heat and power (D4412), biomass power generation (D4417), and heat production and supply (D4430), as well as the emissions of CO₂ and N₂O during the fuel combustion process. The facilities include coal-fired units and related facilities for power generation in coal-fired power plants, as well as supporting facilities such as coal transportation systems, waste gas treatment facilities, and fuel storage systems. The emission substances include SO₂, NOₓ, PM₁₀, PM₂.₅, CO₂, CH₄, N₂O, etc. In addition, indirect carbon emissions from purchased electricity or heat should be included. First, the annual time range forms a complete accounting cycle, and it can be changed to daily according to data requirements.

[0006] Table 1 Accounting Scope of Various Emission Sources

[0007]

[0008] In addition, for the emission accounting method, in the traditional emission accounting method, mainly based on the differences in pollution source types and emission characteristics, the calculation methods for atmospheric pollutants and greenhouse gas emissions can be divided into the monitoring method, the material balance method, and the emission factor method. The calculation method and priority recommended by the reference guide should be considered for each source and substance, and combined with the local actual situation to determine the appropriate emission calculation method. The tentative integrated list is a daily-scale list, and currently, it is mainly determined by the following three methods:

[0009] Emission factor method: The emissions are calculated by multiplying a certain type of activity data (such as fuel consumption) by the corresponding emission factor.

[0010] Material balance method: It is applicable to occasions where the energy or material flow can be clearly tracked. By tracking the material input and output inside and outside the system, the emissions of pollutants and greenhouse gases are estimated. First, determine the material input and output (such as the input amount of coal and the exhaust gas emissions), and then calculate the emissions by calculating the material input, consumption, and waste emissions.

[0011] Online monitoring method: For large emission sources (such as power generation boilers), the emission data are directly obtained through online monitoring equipment. Install real-time monitoring equipment to ensure that the equipment can continuously measure the main pollutants and greenhouse gases in the flue gas, and regularly calibrate the monitoring equipment while reading the data to ensure the accuracy of the data.

[0012] However, in the above existing accounting calculation methods, there may be some problems with the credibility of the data during the calculation. For example, for the calculation methods of the emissions of SO 2 , NOx, TSP, and VOCs, they are usually calculated according to the automatic monitoring method or the production and pollutant discharge coefficient method, or are derived from the pollutant discharge permit implementation report; the automatic monitoring method preferably uses the automatic monitoring data that meet the specification requirements for accounting. If the equipment fails to meet the requirements, the production and pollutant discharge coefficient method is used. The production and pollutant discharge coefficient method mainly calculates the pollutant emissions through the production and pollutant discharge coefficients provided in the enterprise's pollutant discharge permit implementation report. However, this accounting calculation process lacks supervision of the data.

[0013] In addition, for the emission accounting method of coal-fired power generation emission reduction projects, the traditional emission accounting method is not intelligent enough. It still requires enterprise administrators to manually process, collect, and manually calculate a large amount of data. The administrator needs to select the corresponding emission calculation method according to the pollution source type and emission characteristics for accounting calculation. Therefore, this process is relatively long, with a long time-consuming cycle and low efficiency, and the accounting method is not intelligent enough. Summary of the Invention

[0014] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0015] On the one hand, a method for accounting and evaluating the effectiveness of coordinated pollution reduction and carbon emission reduction in coal-fired power enterprises is provided. This method is implemented by electronic equipment and includes:

[0016] S1. Real-time monitor and collect a coal-fired power emission dataset with timestamps, including at least the following data: activity level data, generation coefficient data, end-of-pipe treatment facility information, and automatic monitoring data;

[0017] S2. Classify the coal-fired power emission dataset based on the LLM large language model to obtain subsets of coal-fired power emission data for different pollution source categories;

[0018] S3. Import the subsets of coal-fired power emission data into a preset emission AI accounting and evaluation model. The emission AI accounting and evaluation model identifies the emission characteristics of the subsets of coal-fired power emission data and recommends and outputs an emission calculation strategy matching the emission characteristics;

[0019] S4. Based on the recommended emission calculation strategy, conduct corresponding emission accounting for the subsets of coal-fired power emission data and output the corresponding emission accounting results;

[0020] S5. Statistically analyze the emission accounting results for each pollution source category and generate a corresponding emission source accounting list in a preset report format.

[0021] Optionally, S1. Real-time monitor and collect a coal-fired power emission dataset with timestamps, including:

[0022] The coal-fired power enterprise monitors and collects the coal-fired power emission dataset of the coal-fired power enterprise through the background server according to a preset sampling frequency and reports it to the government affairs server of the credibility institution;

[0023] Through the government affairs server, conduct credibility review on the coal-fired power enterprise and the reported coal-fired power emission dataset:

[0024] If the review is passed, timestamp the coal-fired power emission dataset to generate a coal-fired power emission dataset with timestamps;

[0025] If the review fails, issue corresponding review opinions to the background server of the coal-fired power enterprise.

[0026] Optionally, S2. Classify the coal-fired power emission dataset based on the LLM large language model to obtain subsets of coal-fired power emission data for different pollution source categories, including:

[0027] Construct classification keywords and classification logics for different pollution source categories;

[0028] Combine the classification keywords and the classification logics to construct large language model prompts;

[0029] Input the large language model prompt into a preset LLM large language model, and perform prompt training and learning on the LLM large language model;

[0030] Traverse and read the coal power emission dataset through the LLM large language model, and classify the coal power emission dataset based on the large language model prompt to identify subsets of coal power emission data for different pollution source classes;

[0031] Output and save the subsets of the coal power emission data for different pollution source classes.

[0032] Optionally, the method for generating the emission AI accounting and evaluation model includes:

[0033] Collect and preprocess coal power emission data for several different pollution source classes, where the coal power emission data includes historical coal power consumption data, equipment operation data, and coal quality information for the corresponding pollution sources;

[0034] Perform feature engineering on the coal power emission data to extract emission features from the coal power emission data, where the emission features include the activity level of the emission source corresponding to the pollution source in the coal power emission data within a preset time period, that is, the difference between the emission amount of the pollution source and the emission threshold within the preset time period;

[0035] Perform feature annotation on the emission features, and the annotation information includes: the pollution source attribute corresponding to the emission feature and the calculation strategy for calculating the emission amount of the pollution source corresponding to the emission feature;

[0036] Collect the annotated emission features for different pollution source classes to construct a feature set;

[0037] Divide the feature set into a training set and a validation set according to a preset ratio;

[0038] Input the training set into a preset random forest model for feature training and learning to generate the emission AI accounting and evaluation model;

[0039] Use the validation set to verify the prediction performance of the emission AI accounting and evaluation model:

[0040] If the verification is passed, deploy the emission AI accounting and evaluation model to the background server;

[0041] If the verification fails, repeat the above steps to reconstruct the emission AI accounting and evaluation model.

[0042] Optionally, in step S3, import the coal-fired power emission data subset into a preset emission AI accounting and evaluation model, and have the emission AI accounting and evaluation model identify the emission characteristics of the coal-fired power emission data subset and recommend and output an emission calculation strategy matching the emission characteristics, including:

[0043] Output the coal-fired power emission data subset of different pollution source categories to the emission AI accounting and evaluation model in sequence through the LLM large language model;

[0044] Identify the emission characteristics of the coal-fired power emission data subset through the emission AI accounting and evaluation model, and retrieve, recommend, and output the corresponding emission calculation strategy according to the emission characteristics and their annotation information;

[0045] Bind the recommended emission calculation strategy to the coal-fired power emission data subset corresponding to the emission characteristics.

[0046] Optionally, in step S4, based on the recommended emission calculation strategy, conduct corresponding emission accounting on the coal-fired power emission data subset and output the corresponding emission accounting result, including:

[0047] Analyze the emission calculation strategy to obtain the emission calculation formula therein;

[0048] Read the emission parameters in the coal-fired power emission data subset through the LLM large language model, import them into the emission calculation formula, and calculate and output the corresponding emission accounting result;

[0049] Bind the emission accounting result to the corresponding pollution source and its coal-fired power emission data subset.

[0050] On the other hand, a coal-fired power enterprise pollution reduction and carbon emission reduction collaborative control effectiveness accounting and evaluation system is provided. The coal-fired power enterprise pollution reduction and carbon emission reduction collaborative control effectiveness accounting and evaluation system is used to implement the above-mentioned coal-fired power enterprise pollution reduction and carbon emission reduction collaborative control effectiveness accounting and evaluation method. The system includes:

[0051] A coal-fired power data monitoring module, which is used to monitor and collect in real time a coal-fired power emission data set with timestamps, including at least the following data: activity level data, production coefficient data, end-of-pipe treatment facility information, or automatic monitoring data;

[0052] An LLM classification module, which is used to classify the coal-fired power emission data set based on the LLM large language model to obtain coal-fired power emission data subsets of different pollution source categories;

[0053] An accounting strategy recommendation module, configured to import the subset of coal-fired power generation emission data into a preset emission AI accounting and evaluation model, and the emission AI accounting and evaluation model identifies the emission characteristics of the subset of coal-fired power generation emission data and recommends and outputs an emission calculation strategy matching the emission characteristics;

[0054] An emission calculation module, configured to perform corresponding emission accounting on the subset of coal-fired power generation emission data based on the recommended emission calculation strategy, and output a corresponding emission accounting result;

[0055] A statistics module, configured to statistically calculate the emission accounting results of each pollution source category, and generate a corresponding emission source accounting list according to a preset report format.

[0056] On the other hand, an electronic device is provided, and the electronic device includes: a processor; a memory, and a computer-readable instruction is stored on the memory. When the computer-readable instruction is executed by the processor, any one of the methods in the above-mentioned accounting and evaluation method for the collaborative control effect of pollution reduction and carbon emission reduction of coal-fired power enterprises is implemented.

[0057] On the other hand, a computer-readable storage medium is provided, and at least one instruction is stored in the storage medium. The at least one instruction is loaded and executed by a processor to implement any one of the methods in the above-mentioned accounting and evaluation method for the collaborative control effect of pollution reduction and carbon emission reduction of coal-fired power enterprises.

[0058] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0059] The present invention provides an accounting and evaluation method for the collaborative control effect of pollution reduction and carbon emission reduction of coal-fired power enterprises, aiming to use big data technology to intelligently identify the coal-fired power generation emission data of each pollution source category with time stamps through a trained and constructed emission AI accounting and evaluation model, and recommend and output a corresponding type of emission calculation strategy, and perform corresponding emission accounting based on the recommended emission calculation strategy, and output a corresponding emission accounting result. Finally, the emission accounting results of each pollution source category are statistically calculated to quickly obtain the coal-fired power generation emission accounting amount of the enterprise. The present invention can mark time stamps for the monitored coal-fired power generation emission data by a public trust institution, and perform intelligent data accounting calculations based on the time-stamped coal-fired power generation emission data, which can not only improve the data credibility, but also perform data classification calculations using an AI model, so as to realize the intelligent accounting of coal-fired power carbon and other pollutant emissions, greatly improve the accounting efficiency, shorten the accounting cycle, and reduce the verification difficulty of pollution reduction and carbon emission reduction of coal-fired power enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0061] Figure 1 is the flowchart of the method for calculating and evaluating the co - control effectiveness of pollution reduction and carbon emission reduction in coal - fired power enterprises provided by the embodiments of the present invention;

[0062] Figure 2 is the interactive schematic diagram of the data processing system for public credibility supervision provided by the embodiments of the present invention;

[0063] Figure 3 is the training flowchart of the emission AI calculation and evaluation model provided by the embodiments of the present invention;

[0064] Figure 4 is the block diagram of the system for calculating and evaluating the co - control effectiveness of pollution reduction and carbon emission reduction in coal - fired power enterprises provided by the embodiments of the present invention;

[0065] Figure 5 is the structural schematic diagram of the electronic device provided by the embodiments of the present invention. Specific Embodiments

[0066] The following will describe the technical solutions in the present invention with reference to the accompanying drawings.

[0067] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as an "example" in the present invention should not be interpreted as being more preferred or having more advantages than other embodiments or design solutions. Exactly, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either one of the two.

[0068] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when not emphasizing the difference, their intended meanings are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when not emphasizing the difference, their intended meanings are the same.

[0069] In the embodiments of the present invention, sometimes subscripts such as W 1 may be written in a non - subscript form such as W1. When not emphasizing the difference, their intended meanings are the same.

[0070] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0071] An embodiment of the present invention provides a method for accounting and evaluating the effectiveness of coordinated control of pollution reduction and carbon emission reduction in coal-fired power enterprises. This method can be implemented by an electronic device, which can be a terminal or a server. As Figure 1 shown in the flowchart of the method for accounting and evaluating the effectiveness of coordinated control of pollution reduction and carbon emission reduction in coal-fired power enterprises, the processing flow of this method can include the following steps:

[0072] S1. Real-time monitor and collect a coal-fired power emission dataset with timestamps, including at least the following data: activity level data, generation coefficient data, end-of-pipe treatment facility information, and automatic monitoring data;

[0073] S2. Classify the coal-fired power emission dataset based on the LLM large language model to obtain subsets of coal-fired power emission data for different pollution source categories;

[0074] S3. Import the subsets of coal-fired power emission data into a preset emission AI accounting and evaluation model. The emission AI accounting and evaluation model identifies the emission characteristics of the subsets of coal-fired power emission data and recommends and outputs an emission calculation strategy that matches the emission characteristics;

[0075] S4. Based on the recommended emission calculation strategy, conduct corresponding emission accounting for the subsets of coal-fired power emission data and output the corresponding emission accounting results;

[0076] S5. Statistically analyze the emission accounting results for each pollution source category and generate a corresponding emission source accounting list in a preset report format.

[0077] In the present invention, for the accounting scope of coal-fired power emissions for different pollution source categories, it can be the accounting scope table shown in Table 1. Sampling accounting can be specifically carried out according to accounting requirements. For the first-level emission sources, for example, by collecting statistical yearbooks, pollutant discharge permit and its implementation report data information, and environmental statistical data, etc., the first-level emission sources in the local power industry can be identified, and the types of air pollutants and greenhouse gases to be accounted for can be determined based on the first-level emission sources.

[0078] For the accounting strategies of coal-fired power emissions for different pollution source categories, the present invention combines AI algorithms and the LLM large language model for joint calculation and processing, thereby replacing manual work to complete the corresponding accounting, and thus realizing the intelligent accounting process of the effectiveness of coordinated control of pollution reduction and carbon emission reduction in coal-fired power enterprises and improving the accounting efficiency.

[0079] The following will describe steps S1 - S5 in detail.

[0080] Optionally, S1 monitors and collects a timestamped coal-fired power emission dataset in real time, including:

[0081] The coal-fired power enterprise monitors and collects the coal-fired power emission dataset of the coal-fired power enterprise through the background server according to a preset sampling frequency and reports it to the government affairs server of the credibility institution;

[0082] Through the government affairs server, conduct credibility review on the coal-fired power enterprise and the reported coal-fired power emission dataset:

[0083] If the review is passed, timestamp the coal-fired power emission dataset to generate a timestamped coal-fired power emission dataset;

[0084] If the review fails, send the corresponding review opinion to the background server of the coal-fired power enterprise.

[0085] As Figure 2 shown, the present invention is to solve the accuracy and effectiveness of the accounting data of coal-fired power enterprises. By enabling data communication between coal-fired power enterprises and the third-party government credibility institution, according to a preset sampling frequency, the background server can monitor and collect the corresponding coal-fired power emission dataset for each accounting and report it to the government affairs server. The government affairs server conducts credibility review on the coal-fired power emission data to be accounted for each time, thereby giving credibility and certification to the emission data to be accounted for by coal-fired power enterprises. During specific operations, on the government affairs server, the coal-fired power emission dataset can be reviewed according to corresponding review conditions and a timestamp can be marked on the dataset, so that each monitored and collected coal-fired power emission data has a corresponding credibility certification mark. Subsequently, during accounting, these certified coal-fired power emission datasets need to be used for the next accounting certification, thereby avoiding false reporting of enterprise emission data and improving its credibility and accuracy. It is sufficient to complete the timestamp marking on the government affairs server. The steps and certification functions for marking the timestamp after data review can be referred to as follows:

[0086] 1. Timestamp application and verification operation steps

[0087] Log in to the timestamp management system:

[0088] First, it is necessary to log in to the official website of the timestamp service provider (such as the official website of Mesign: www.mesign.com).

[0089] Select timestamp certification:

[0090] In the logged-in management interface, find the option related to timestamp certification and click to enter.

[0091] Upload the file and apply for a timestamp:

[0092] Select the file for which you need to apply for a timestamp (usually a data file that has been reviewed), and then click the button to apply for a timestamp.

[0093] Download the timestamp authentication compressed package:

[0094] After the application is successful, download the timestamp authentication compressed package according to the system instructions. This compressed package usually contains the original file, the timestamp.tsa file, and the timestamp authentication certificate.

[0095] Save and backup

[0096] Properly save the original file, the timestamp.tsa file, and the timestamp authentication certificate to ensure the integrity and traceability of the data.

[0097] 2. Authentication function of timestamp

[0098] Evidence preservation:

[0099] Timestamp authentication is a means of evidence preservation, which can provide reliable time proof, content authenticity, and integrity proof for electronic files. Through the timestamp, the generation time of the electronic file can be determined and its tampering can be prevented.

[0100] Legal effect:

[0101] Legally, the electronically stored information authenticated by a timestamp has probative force. This means that, when needed, this electronically stored information can be used as legal evidence.

[0102] Reduce the cost of presenting evidence:

[0103] As a means of fixing electronic data, the timestamp technology is recognized in judicial practice. The timestamp authentication certificate issued by an authoritative and trustworthy third-party electronic certification service agency can be recognized without notarization and judicial expertise, thus greatly reducing the cost of presenting evidence and improving the efficiency of presenting evidence.

[0104] Ensure data integrity:

[0105] The application of the timestamp can ensure the integrity of the data from generation to storage and transmission. Any tampering with the data will result in the failure of timestamp verification, thus ensuring the authenticity and credibility of the data.

[0106] Precautions

[0107] Before applying for a timestamp, it is necessary to ensure that the uploaded file has been reviewed and meets the relevant requirements.

[0108] When saving and backing up the timestamp authentication files, appropriate measures need to be taken to ensure the security and integrity of the files.

[0109] When using timestamps as legal evidence, relevant legal procedures and regulations need to be followed.

[0110] From the above steps and function introduction, it can be seen that the application of timestamps after data review is of great significance. It can not only ensure the authenticity and integrity of data but also provide effective legal evidence support.

[0111] Optionally, in S2, classify the coal-fired power generation emission dataset based on the large language model (LLM) to obtain subsets of coal-fired power generation emission data for different pollution source categories, including:

[0112] Construct classification keywords and classification logics for different pollution source categories;

[0113] Combine the classification keywords and the classification logics to construct LLM prompts;

[0114] Input the LLM prompts into a preset LLM to perform prompt training and learning on the LLM;

[0115] Traverse and read the coal-fired power generation emission dataset through the LLM, and classify the coal-fired power generation emission dataset based on the LLM prompts to identify subsets of coal-fired power generation emission data for different pollution source categories;

[0116] Output and save the subsets of coal-fired power generation emission data for different pollution source categories.

[0117] When classifying the coal-fired power generation emission data for different pollution source categories in the present invention, the LLM deployed on the background automatically performs corresponding classification operations (custom training or requesting to call the LLM through the LLM API interface from a third party). The specific operations can refer to the following steps:

[0118] 1. Construct LLM prompts:

[0119] Clarify the task objective: First, it is necessary to clarify that the task objective is to classify the coal-fired power generation emission dataset and identify subsets of coal-fired power generation emission data for different pollution source categories.

[0120] Design the prompt structure: According to the task objective, design the structure of the prompts, including an instruction part and an input data part. The instruction part should clearly describe the classification task and requirements, and the input data part provides relevant information about the coal-fired power generation emission dataset.

[0121] Write specific prompts: For example, the following prompts can be written: "Please classify the following coal-fired power generation emission dataset according to pollution source categories and identify subsets of coal-fired power generation emission data for different pollution source categories. The dataset contains [specific data description], and please classify it according to [specific classification criteria]."

[0122] 2. Input the prompt for training and learning:

[0123] Select the large language model (LLM): According to the task requirements and model performance, select a suitable LLM, such as the GPT series, PaLM, etc.

[0124] Input the prompt: Input the constructed prompt into the selected LLM.

[0125] Conduct training and learning: Let the model conduct training and learning based on the prompt so that it can understand the task requirements and learn to classify the coal-fired power generation emission dataset.

[0126] 3. Traverse and read the coal-fired power generation emission dataset:

[0127] Load the dataset: Load the coal-fired power generation emission dataset into the LLM.

[0128] Traverse the data: Use the model to traverse and read each piece of data in the dataset.

[0129] Classify based on the prompt:

[0130] Apply the prompt: During the process of traversing the data, continuously apply the constructed prompt to guide the model to classify each piece of data.

[0131] Identify the pollution source class: According to the classification criteria in the prompt, the model should be able to identify the pollution source class to which each piece of data belongs.

[0132] Generate data subsets: Classify the coal-fired power generation emission data of different pollution source classes identified into the corresponding data subsets.

[0133] Through the above steps, the coal-fired power generation emission dataset can be classified using the LLM prompt, and the coal-fired power generation emission data subsets of different pollution source classes can be identified. During this process, the generalization ability, few-shot learning ability, and in-context learning ability of the LLM will be fully utilized, thereby achieving accurate classification and identification of the coal-fired power generation emission data.

[0134] On the background, the coal-fired power generation emission data subsets of each pollution source class can be classified and saved.

[0135] The coal-fired power generation emission dataset can include:

[0136] Fuel consumption data: The usage amount of coal, combustion efficiency, etc.;

[0137] Equipment operation data: The working load and usage time of the generator set;

[0138] Coal quality information: Index data such as carbon content, ash content, volatile matter, etc.

[0139] The collected indicators can be set according to requirements.

[0140] The following is the training process of the AI algorithm model of the present invention, which can be understood in combination with the model structure and its training application principle of, for example, the random forest algorithm.

[0141] Optionally, the method for generating the emission AI accounting and evaluation model includes:

[0142] Collect coal-fired power generation emission data of several different pollution source categories and preprocess it. Among them, the coal-fired power generation emission data includes historical coal-fired power consumption data, equipment operation data, and coal quality information of the corresponding pollution sources;

[0143] Perform feature engineering on the coal-fired power generation emission data to extract emission features in the coal-fired power generation emission data. Among them, the emission features include the emission source activity level of the corresponding pollution source in the coal-fired power generation emission data within a preset time period, that is: the difference between the emission amount of the pollution source and the emission threshold within the preset time period;

[0144] Perform feature annotation on the emission features, and the annotation information includes: the pollution source attribute corresponding to the emission feature and the calculation strategy for calculating the emission amount of the pollution source corresponding to the emission feature;

[0145] Collect the emission features corresponding to different pollution source categories after annotation, and construct a feature set;

[0146] Divide the feature set into a training set and a validation set according to a preset ratio;

[0147] Input the training set into a preset random forest model, perform feature training and learning, and generate the emission AI accounting and evaluation model;

[0148] Use the validation set to verify the prediction performance of the emission AI accounting and evaluation model:

[0149] If the verification is passed, deploy the emission AI accounting and evaluation model to the background server;

[0150] If the verification fails, repeat the above steps to reconstruct the emission AI accounting and evaluation model.

[0151] As Figure 3 shown, coal-fired power generation emission data of different pollution source categories can be extracted from the enterprise background log library and preprocessed. Referring to the above-mentioned LLM-based prompt method, the LLM can be used to collect coal-fired power generation emission data of several different pollution source categories from the log library based on the data collection prompt. The preprocessing can be steps such as cleaning.

[0152] Next, the random forest algorithm will be used to train the emission AI accounting evaluation model. Random forest is an ensemble learning algorithm that improves prediction accuracy and stability by constructing multiple decision trees and combining their results. In practical applications, the parameters and structure of the random forest model can be flexibly adjusted according to the requirements of specific problems and data characteristics.

[0153] The steps to build a model using the random forest algorithm usually include the following main links:

[0154] ‌Data preprocessing‌:

[0155] Clean the original dataset and handle missing values, outliers, etc.

[0156] Standardize or normalize the data to ensure that the numerical ranges of different features are on the same scale and avoid some features having too much influence on the model.

[0157] Divide the dataset into a training set and a test set (or a training set, a validation set, and a test set) for model training and evaluation.

[0158] ‌Parameter setting‌:

[0159] Determine the number of decision trees (n_estimators) in the random forest. Usually, more trees can improve the stability and accuracy of the model, but it will also increase the computational cost.

[0160] Set the maximum depth (max_depth) of each tree to help prevent overfitting.

[0161] Determine the maximum number of features (max_features) to consider when splitting each node, which can increase the diversity between trees.

[0162] Set other relevant parameters, such as the minimum number of samples to split a node (min_samples_split), the minimum number of samples in a leaf node (min_samples_leaf), etc.

[0163] ‌Model training‌:

[0164] Use the training set (divide the feature set according to 8:2) to train the random forest model. During the training process, each tree is independently trained on its corresponding bootstrap sample (sampling with replacement), and a random subset of features is considered when splitting each node.

[0165] ‌Model evaluation‌:

[0166] Use the test set (or validation set) to evaluate the trained model and calculate performance metrics such as the accuracy, recall rate, and F1 score of the model.

[0167] The out-of-bag (OOB) error can be used to evaluate the generalization ability of the model, which is an evaluation method that does not require additional reserved test samples.

[0168] Feature importance evaluation:

[0169] After training is completed, the feature importance output by the model can be used to evaluate the contribution degree of each feature to the model prediction result.

[0170] Model tuning:

[0171] According to the evaluation results and feature importance evaluation, the model parameters are tuned to improve the performance of the model.

[0172] Model application:

[0173] Apply the trained model to new data for tasks such as prediction or classification.

[0174] When performing feature engineering to extract emission features from the coal-fired power generation emission data, supervised learning algorithms can be used to extract the corresponding emission features:

[0175] The coal-fired power generation emission data includes information such as the concentration, emission amount, and timestamp of various emissions.

[0176] Label the data, that is, classify the data into different categories or labels according to emission features (such as the type of emissions, concentration range, etc.).

[0177] Divide the dataset into a training set, a validation set, and a test set for model training and evaluation.

[0178] Data preprocessing:

[0179] Clean the data and handle missing values, outliers, etc.

[0180] Normalize or standardize the data to ensure that the numerical ranges of different features are on the same order of magnitude.

[0181] Feature engineering may be required, such as feature extraction (such as mapping the original data to a low-dimensional space through mathematical transformation) and feature selection (such as selecting the most useful feature subset for the prediction task).

[0182] Model selection and construction:

[0183] Select appropriate supervised learning algorithms, such as logistic regression, support vector machines, decision trees, random forests, neural networks, etc.

[0184] Build a prediction model according to the selected algorithm and set corresponding hyperparameters (such as learning rate, number of iterations, regularization strength, etc.).

[0185] Model training:

[0186] Use the training set data to train the model, and continuously adjust the model parameters through optimization methods (such as gradient descent method) to minimize the loss function (such as cross-entropy, mean squared error, etc.), so as to improve the prediction ability of the model.

[0187] Model validation and tuning:

[0188] Use the validation set data to validate the model and evaluate the performance of the model (such as accuracy, recall rate, F1 score, etc.).

[0189] Tune the model according to the validation results, such as adjusting hyperparameters, changing algorithms, etc., to improve the generalization ability of the model.

[0190] Feature extraction:

[0191] During the model training process, the supervised learning algorithm will automatically learn and extract the most useful features for the prediction task from the original data (such as the types of emissions, concentration ranges, etc.).

[0192] These features can be used to explain the prediction results of the model and help understand the internal laws of coal-fired power generation emission data.

[0193] Model testing and application:

[0194] Use the test set data to conduct a final test on the model to evaluate the performance of the model in actual applications.

[0195] If the model performs well, it can be deployed to actual applications for real-time monitoring and prediction of coal-fired power generation emission data.

[0196] The performance of the supervised learning algorithm depends to a large extent on the quality and quantity of the training data. The administrator needs to do a good job in preprocessing during the preprocessing stage, and can combine the LLM to supervise the data quality and quantity. Specifically, it is judged and completed by the administrator.

[0197] And the described emission characteristics herein include the emission source activity level of the corresponding pollution source in the coal-fired power generation emission data within a preset time period, that is: the difference between the emission amount of the pollution source and the emission threshold within the preset time period. The emission characteristics can be the emission concentration, emission amount (taking the maximum value) or time stamp of the corresponding pollutant, etc. Herein, it is preferred that the difference between the emission amount of the pollution source and the emission threshold within the current time period (such as the maximum emission value of sulfur dioxide stipulated in this quarter) is used as the emission characteristic, and it is used as the emission characteristic for feature recognition and matching strategy.

[0198] For the pollution source attributes marked for emission characteristics and the calculation strategy for the emissions of the pollution sources corresponding to the emission characteristics, the corresponding configuration can be made with reference to the following strategy conditions, which facilitates subsequent models to perform strategy matching based on the identified emission characteristics:

[0199] The calculation strategy for the emissions marked for the emission characteristics of different pollution source categories can be marked and associated with the corresponding calculation strategy for emissions by the administrator according to the pollution source type and its emission characteristics. The calculation formula for the emissions of the corresponding pollution source is included in the calculation strategy for emissions, and the administrator can specifically configure the strategy according to accounting standards such as industry / country, etc. For example, the following accounting strategies for different pollution sources:

[0200] 1. SO 2 , NOx, TSP and VOCs emission calculation methods

[0201] SO 2 , NOx, TSP and VOCs emissions are calculated by the automatic monitoring method or the production and pollution discharge coefficient method, or are sourced from the pollution discharge permit implementation report.

[0202] For the automatic detection method, automatically monitored data that meets the specification requirements should be preferentially used for accounting. The automatically monitored equipment should comply with the relevant laws and regulations on installation, commissioning, acceptance, and operation and maintenance to ensure that the quarterly effective capture rate is not less than 75%. There should be no record of false monitoring data within three years. If the equipment fails to meet the requirements, the production and pollution discharge coefficient method shall be used. The production and pollution discharge coefficient method mainly calculates the pollutant emissions through the production and pollution discharge coefficients provided in the pollution discharge permit implementation report of the enterprise.

[0203] 2. PM10, PM2.5, BC and OC emission calculation methods

[0204] The emissions of PM10 and PM2.5 can be calculated based on the emissions of TSP and the proportion (E PM ) of particulate matter in a certain particle size range (such as PM2.5 and PM10) to the total particulate matter, and the formula is as (4-1); the emissions of BC and OC can be calculated respectively based on the emissions of PM2.5 and the proportions of BC and OC in PM2.5: (E BC and E OC ), and the formulas are as (4-2) and (4-3):

[0205] E PM =E TSP x f PM (4-1),

[0206] E BC =E PM2.5 x f BC (4-2),

[0207] E OC = E PM2.5 x f OC (4 - 3),

[0208] In the formula, E TSP is the TSP emission, fpm is the proportion of particulate matter in a certain particle size range (such as PM5 and PMio) in the emitted TSP, and f BC and f OC are the proportions of BC and OC in PM2.5 respectively.

[0209] 3. Calculation method of CO emissions

[0210] The CO emissions during the combustion process of power and heat sources can be calculated according to the production and pollution discharge coefficient method. The calculation formula of the production and pollution discharge coefficient method is as follows:

[0211] E = A × EF (4 - 4)

[0212] In the formula, A is the activity level of the emission source; EF is the generation coefficient of the pollutant (which can be obtained by referring to the corresponding coefficient table).

[0213] 4. CO 2 emission calculation method

[0214] The CO emissions generated by the combustion of fossil fuels in power and heat sources 2 and the indirect CO emissions due to the purchase of external power and heat 2 shall be calculated with reference to the "Enterprise Greenhouse Gas Emission Accounting and Reporting Guidelines for Power Generation Facilities". When calculating indirect emissions, it is recommended to use the national grid emission factor newly released by the Ministry of Ecology and Environment.

[0215] For key enterprises that have been included in the scope of greenhouse gas emission reporting and verification work, the CO2 emissions can be directly adopted from the verification data.

[0216] 5. N 2 O emission calculation method

[0217] The N 2 O emissions generated by fuel combustion shall be calculated according to the method in the "Provincial Greenhouse Gas Emission Inventory Compilation Guidelines (Trial)".

[0218] Through the above training, an emission AI accounting and evaluation model is obtained, which can be deployed to the background server for subsequent policy recommendation.

[0219] Optionally, step S3: Import the coal - power emission data subset into a preset emission AI accounting and evaluation model. The emission AI accounting and evaluation model identifies the emission characteristics of the coal - power emission data subset and recommends and outputs an emission calculation strategy matching the emission characteristics, including:

[0220] Output the subsets of the coal - power emission data for different pollution - source categories to the emission AI accounting and evaluation model in sequence through the large - language model (LLM).

[0221] Identify the emission characteristics of the subsets of the coal - power emission data through the emission AI accounting and evaluation model, and retrieve and recommend the corresponding emission - quantity calculation strategies according to the emission characteristics and their annotation information.

[0222] Bind the recommended emission - quantity calculation strategies to the subsets of the coal - power emission data corresponding to the emission characteristics.

[0223] After classification by the large - language model, the large - language model can directly communicate with the emission AI accounting and evaluation model for data. Input the subsets of the coal - power emission data for each type of pollution source into the emission AI accounting and evaluation model in sequence. After the model identifies and recommends the emission - quantity calculation strategy for the current type of pollution source, it then makes recommendations for the corresponding type of pollution source. The data communication between the large - language model and the AI model can be carried out according to the corresponding transmission ports for model deployment.

[0224] After classification by the large - language model, it can directly input into the AI model for strategy recommendation, and bind the recommended strategies for the corresponding pollution sources to the corresponding subsets on the background server, and then conduct emission - quantity accounting calculations.

[0225] Optionally, in step S4, based on the recommended emission - quantity calculation strategies, conduct corresponding emission - quantity accounting for the subsets of the coal - power emission data, and output the corresponding emission - quantity accounting results, including:

[0226] Analyze the emission - quantity calculation strategy to obtain the emission - quantity calculation formula therein.

[0227] Read the emission parameters in the subsets of the coal - power emission data through the large - language model (LLM), import them into the emission - quantity calculation formula, and calculate and output the corresponding emission - quantity accounting results.

[0228] Bind the emission - quantity accounting results to the corresponding pollution sources and their subsets of the coal - power emission data.

[0229] In step S5, count the emission - quantity accounting results for each pollution - source category and generate a corresponding emission - source accounting list in a preset report format.

[0230] When conducting emission - quantity accounting, since corresponding strategy calculations are performed on the subset data of different pollution sources, the strategies can be analyzed to obtain the emission - quantity calculation formulas therein. For specific references, see the formula descriptions for each type above.

[0231] Moreover, the subset data also contains the emission parameters of the corresponding pollutants. Therefore, it is necessary to extract them and import them into the formula for calculation. Here, a large language model is used to read the emission parameters in the coal-fired power generation emission data subset and import the corresponding emission parameters into the corresponding calculation factors in the corresponding emission calculation formula for automated accounting calculation.

[0232] The step of using the LLM large language model to read the corresponding emission parameters and import them into the corresponding calculation factors in the formula can refer to the process of the above large language model performing automated operations based on prompts. The administrator can define in advance the keywords of the corresponding calculation factors and the calculation logic, etc., so that the large language model can extract the corresponding emission parameters based on the above logic and keywords and import the parameters into the corresponding calculation factors, thereby calculating the corresponding emissions according to the corresponding execution logic.

[0233] The step of using the LLM large language model to read the corresponding emission parameters in the dataset and import them into the corresponding calculation factors in the preset formula can be carried out according to the following process:

[0234] 1. Data preparation:

[0235] Ensure that the coal-fired power generation emission dataset has been organized into a format that the LLM large language model can understand, such as CSV, JSON, etc.

[0236] The dataset should contain the required emission parameters, such as the types, concentrations, emissions, etc. of the pollutants.

[0237] Model selection and configuration:

[0238] Select a suitable LLM large language model, such as the GPT series, BERT, etc.

[0239] Configure the model to ensure that it can process and understand text data.

[0240] Writing instructions and scripts:

[0241] Write detailed instructions to tell the LLM large language model which emission parameters need to be read from the dataset.

[0242] Write a script or program to interface the output of the LLM large language model with the preset formula.

[0243] 2. Reading data:

[0244] Read the emission parameters in the dataset through the LLM large language model. This may require inputting the dataset as text to the model and instructing the model to extract specific information.

[0245] The model may return a text containing the required parameters or a structured data format (such as JSON).

[0246] ‌Data parsing and mapping‌:

[0247] Parse the output of the LLM large language model to extract specific emission parameter values.

[0248] Map these parameter values to the corresponding calculation factors in the preset formula.

[0249] ‌Formula calculation‌:

[0250] Execute the preset formula for calculation based on the mapped parameter values.

[0251] The formula can be a simple mathematical operation or a more complex model or algorithm.

[0252] 3.‌Result output and application‌:

[0253] Output the calculation result, which can be a specific value, a set of values, or a certain form of report, depending on the strategy.

[0254] Therefore, a large language model is used here to automatically execute the corresponding calculation process, so as to realize the automated emission accounting calculation process and improve the accounting efficiency.

[0255] In order to statistically evaluate the results of this emission accounting, the emission accounting results of each pollution source can be orderly input into a preset report form, and a corresponding emission source accounting list for this time can be generated according to the report form format. The background server synchronously uploads the generated accounting list for this time to the government affairs server for the government affairs department to review, etc.

[0256] Figure 4 It is a block diagram of a system for accounting and evaluating the effectiveness of coordinated pollution reduction and carbon emission reduction in coal-fired power enterprises shown according to an exemplary embodiment. This system is used for the method of accounting and evaluating the effectiveness of coordinated pollution reduction and carbon emission reduction in coal-fired power enterprises. Refer to Figure 4 , this system includes a coal-fired power data monitoring module 510, an LLM classification module 520, an accounting strategy recommendation module 530, an emission calculation module 540, and a statistics module 550. Among them:

[0257] The coal-fired power data monitoring module 510 is used to monitor and collect in real time a coal-fired power emission data set with timestamps, including at least the following data: activity level data, production coefficient data, end-of-pipe treatment facility information, or automatic monitoring data;

[0258] The LLM classification module 520 is used to classify the coal-fired power emission data set based on the LLM large language model to obtain subsets of coal-fired power emission data for different pollution source classes;

[0259] The accounting strategy recommendation module 530 is configured to import the subset of coal-fired power generation emission data into a preset emission AI accounting and evaluation model, and the emission AI accounting and evaluation model identifies the emission characteristics of the subset of coal-fired power generation emission data and recommends and outputs an emission calculation strategy that matches the emission characteristics.

[0260] The emission calculation module 540 is configured to perform corresponding emission accounting on the subset of coal-fired power generation emission data based on the recommended emission calculation strategy and output a corresponding emission accounting result.

[0261] The statistics module 550 is configured to statistically calculate the emission accounting results of each pollution source category and generate a corresponding emission source accounting list in a preset report format.

[0262] For the functions and interactions of the above-mentioned modules, please refer to the corresponding procedures and content in the above method steps for understanding, and will not be elaborated here.

[0263] Figure 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As Figure 5 shown, the electronic device may include the above-mentioned Figure 4 coal-fired power generation enterprise pollution reduction and carbon emission reduction collaborative control effectiveness accounting and evaluation system shown. Optionally, the electronic device 410 may include a first processor 2001.

[0264] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003.

[0265] Among them, the first processor 2001 is connected to the memory 2002 and the transceiver 2003, such as through a communication bus.

[0266] Next, Figure 5 a specific introduction to each component of the electronic device 410 will be given:

[0267] Among them, the first processor 2001 is the control center of the electronic device 410, which may be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be a specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as: one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs).

[0268] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0269] In a specific implementation, as an example, the first processor 2001 may include one or more CPUs, such as Figure 5 the CPU0 and CPU1 shown in

[0270] In a specific implementation, as an example, the electronic device 410 may also include multiple processors, such as Figure 5 the first processor 2001 and the second processor 2004 shown in

[0271] Among them, the memory 2002 is used to store software programs for implementing the solution of the present invention and is controlled by the first processor 2001 for execution. The specific implementation manner can refer to the above method embodiments and will not be elaborated here.

[0272] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic storage medium such as a disk storage medium, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001 or exist independently and be coupled to the first processor 2001 through an interface circuit ( Figure 5 not shown in

[0273] The transceiver 2003 is used to communicate with a network device or with a terminal device.

[0274] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 not shown separately). Among them, the receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0275] Optionally, the transceiver 2003 may be integrated with the first processor 2001 or exist independently, and is coupled to the first processor 2001 through the interface circuit ( Figure 5 not shown) of the electronic device 410. The embodiments of the present invention do not make specific limitations on this.

[0276] It should be noted that Figure 5 the structure of the electronic device 410 shown in

[0277] does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0278] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0279] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0280] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be solid-state drives.

[0281] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship. The specific meaning can be understood by referring to the context.

[0282] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0283] It should be understood that in various embodiments of the present invention, the order of the numbers of the above processes does not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0284] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0285] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the devices, systems, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0286] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of systems or units can be electrical, mechanical, or other forms.

[0287] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0288] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0289] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0290] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies, characterized in that: The method comprises: S1. Real-time monitoring and collection of coal-fired power emission data sets with time stamps, including at least the following data: activity level data, generation coefficient data, end-of-pipe treatment facility information, and automatic monitoring data; S2. Classifying the coal-fired power generation emission data set based on the LLM large language model to obtain coal-fired power generation emission data subsets of different pollution source types; S3. Importing the coal-fired power generation emission data subset into a preset emission AI accounting and evaluation model, and having the emission AI accounting and evaluation model identify the emission characteristics of the coal-fired power generation emission data subset and recommend and output an emission calculation strategy that matches the emission characteristics; S4. Based on the recommended emission calculation strategy, perform corresponding emission calculation on the coal-fired power emission data subset, and output the corresponding emission calculation result; S5. Count the emission accounting results of each pollution source category, and generate a corresponding emission source accounting list according to a preset report format.

2. The method for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies according to claim 1 is characterized in that: S1, real-time monitoring and collection of coal-fired power emission data sets with time stamps, including: Coal-fired power companies use backend servers to monitor and collect coal-fired power emission data sets at preset sampling frequencies and report them to the government server of the credibility agency; Through the government affairs server, the credibility of coal-fired power enterprises and the coal-fired power emission data sets they reported are reviewed: If the review is passed, the coal-fired power generation emission data set is timestamped to generate a coal-fired power generation emission data set with a timestamp; If the review fails, the corresponding review opinion will be sent to the backend server of the coal-fired power company.

3. The method for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies according to claim 1 is characterized in that: S2: classifying the coal-fired power generation emission data set based on the LLM large language model to obtain coal-fired power generation emission data subsets of different pollution source types, including: Construct classification keywords and classification logic for different pollution source types; Combining the classification keywords and the classification logic, constructing a large language model prompt word; Inputting the large language model prompt words into a preset LLM large language model, and performing prompt word training and learning on the LLM large language model; The coal-fired power generation emission data set is traversed and read through the LLM large language model, and the coal-fired power generation emission data set is classified based on the large language model prompt words to identify coal-fired power generation emission data subsets of different pollution source types; Output and save the coal-fired power emission data subsets of the different pollution source categories.

4. The method for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies according to claim 1 is characterized in that: The method for generating the emission AI accounting and evaluation model includes: Collect and pre-process coal-fired power emission data of several different pollution source types, wherein the coal-fired power emission data includes historical coal-fired power consumption data, equipment operation data and coal-fired power coal quality information of the corresponding pollution source; Performing feature engineering on the coal-fired power emission data to extract emission features from the coal-fired power emission data, wherein the emission features include the emission source activity level of the corresponding pollution source in the coal-fired power emission data within a preset time period, that is, the difference between the emission amount of the pollution source and the emission threshold within the preset time period; The emission characteristics are marked, and the marking information includes: the pollution source attributes corresponding to the emission characteristics and the emission calculation strategy for calculating the pollution source corresponding to the emission characteristics; Collect the labeled emission characteristics corresponding to different pollution source types to construct a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into a preset random forest model to perform feature training and learning to generate the emission AI accounting and evaluation model; The prediction performance of the emission AI accounting assessment model is verified using the validation set: If the verification is passed, the emission AI accounting and evaluation model is deployed to the backend server; If the verification fails, repeat the above steps to rebuild the emission AI accounting and evaluation model.

5. The method for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies according to claim 4 is characterized in that: S3, importing the coal-fired power emission data subset into a preset emission AI accounting and evaluation model, wherein the emission AI accounting and evaluation model identifies the emission characteristics of the coal-fired power emission data subset and recommends and outputs an emission calculation strategy that matches the emission characteristics, including: Output the coal-fired power emission data subsets of different pollution source categories to the emission AI accounting and evaluation model in sequence through the LLM large language model; Identify the emission characteristics of the coal-fired power emission data subset through the emission AI accounting and evaluation model, and retrieve and recommend the corresponding emission calculation strategy based on the emission characteristics and their annotation information; The recommended emission calculation strategy is bound to the coal-fired power emission data subset corresponding to the emission characteristics.

6. The method for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies according to claim 5 is characterized in that: S4, based on the recommended emission calculation strategy, performing corresponding emission calculation on the coal-fired power emission data subset, and outputting corresponding emission calculation results, including: Analyze the emission calculation strategy to obtain the emission calculation formula; The emission parameters in the coal-fired power emission data subset are read through the LLM large language model, and the emission calculation formula is imported to calculate and output the corresponding emission accounting result; The emission accounting results are bound to the corresponding pollution sources and their coal-fired power emission data subsets.

7. A system for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies, the system for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies is used to implement the method for calculating and evaluating the effectiveness of coordinated control of pollution reduction and carbon reduction in coal-fired power companies as described in any one of claims 1 to 6, characterized in that: The system comprises: The coal power data monitoring module is used to monitor and collect coal power emission data sets with time stamps in real time, including at least the following data: activity level data, generation coefficient data, end-of-pipe treatment facility information, and automatic monitoring data; An LLM classification module is used to classify the coal-fired power generation emission data set based on the LLM large language model to obtain coal-fired power generation emission data subsets of different pollution source types; An accounting strategy recommendation module, used to import the coal-fired power emission data subset into a preset emission AI accounting evaluation model, and the emission AI accounting evaluation model identifies the emission characteristics of the coal-fired power emission data subset and recommends and outputs an emission calculation strategy that matches the emission characteristics; An emission calculation module, used to perform corresponding emission calculation on the coal-fired power emission data subset based on the recommended emission calculation strategy, and output corresponding emission calculation results; The statistical module is used to count the emission accounting results of each pollution source category and generate a corresponding emission source accounting list according to a preset report format.

8. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 6.

Images