Enterprise carbon credit report generation method and system, electronic equipment and storage medium
By preprocessing enterprise data and building LightGBM models for verification and comparative analysis, the problem of insufficient quality and credibility of enterprise carbon credit report data is solved, and more accurate and credible carbon credit ratings and report generation is achieved.
Patent Information
- Application Number
- CN202411636937.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-15
- Publication Date
- 2025-02-28
AI Technical Summary
When generating corporate carbon credit reports in the existing technology, the data quality is low and the accuracy is insufficient, and the credibility of carbon credit reports is insufficient, which cannot fully reflect the development of the low-carbon economy of the enterprise.
By obtaining enterprise data for pre-processing, using LightGBM algorithm to construct enterprise prediction models for data verification, comparative analysis method is used to evaluate enterprise energy efficiency levels, and weighted calculations are used to determine enterprise carbon credit ratings, and finally generate enterprise carbon credit report.
It improves data quality and accuracy, ensures the credibility of corporate carbon credit reports, can fully reflect the low-carbon development of the company, and supports corporate carbon management decisions.
Smart Images
Figure CN119539831A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of green finance technology for carbon emission reduction, and in particular to a method, system, electronic device and storage medium for generating a corporate carbon credit report. Background Art
[0002] Corporate carbon credit reports are not only an important tool for companies to manage carbon emissions and participate in carbon market transactions, but also an effective means to respond to policy requirements, enhance corporate environmental image, and obtain green financial support. With the advancement of the "dual carbon" goals and the improvement of market mechanisms, the demand for corporate carbon credit reports is expected to continue to grow.
[0003] Existing technologies often focus on a single aspect of carbon emissions and lack a comprehensive integrated solution to generate carbon credit reports. Secondly, carbon credit ratings require a large amount of carbon emission data as support. However, in existing technologies, data is collected and processed manually, which leads to low data quality and insufficient accuracy, and thus cannot fully reflect the development of the company's low-carbon economy, which is not conducive to investors' assessment and supervision of the company's carbon credit status. In addition, some companies may have problems with concealing or falsifying carbon emission data, and some assessment agencies are not open and transparent in the assessment process when conducting carbon credit ratings, resulting in insufficient credibility of corporate carbon credit reports. Summary of the invention
[0004] The purpose of the embodiments of the present invention is to provide a method, system, electronic device and storage medium for generating a corporate carbon credit report, which are used to completely or at least partially solve the problems of low data quality, insufficient accuracy and insufficient credibility of corporate carbon credit reports in the above-mentioned prior art.
[0005] In order to achieve the above object, an embodiment of the present invention provides a method for generating a corporate carbon credit report, comprising: Obtain enterprise data and pre-process the enterprise data to obtain target enterprise data, where the target enterprise data includes basic enterprise information, enterprise credit information and carbon reduction path; Use the enterprise prediction model pre-built based on the LightGBM algorithm to verify the target enterprise data to cross-verify the correctness of the target enterprise data; Comparative analysis is used to evaluate the energy efficiency level of enterprises, and weighted calculation is performed based on the energy efficiency level and revenue of the enterprises to determine the carbon credit rating of the enterprises; Provide comprehensive evaluation scores and energy efficiency ratings to companies based on their carbon credit ratings; Generate a corporate carbon credit report based on basic corporate information, corporate rating, corporate logo, corporate credit information and carbon reduction path.
[0006] Optionally, enterprise data is obtained and preprocessed to obtain target enterprise data, including: Based on the basic data of each enterprise, the total level of projects and enterprises in each industry, the industry average level, the energy efficiency and carbon emission intensity of each enterprise, and the carbon reduction path of the enterprise are obtained through data cleaning and data conversion preprocessing; among them, the data cleaning objects mainly include outliers, missing values and redundant data, and the data conversion objects mainly include energy measurement units, measurement units of energy consumption and energy carbon emission factors.
[0007] Optionally, the enterprise prediction model built based on the LightGBM algorithm is characterized as:
[0008] In the formula, f* represents the optimal enterprise prediction model after multiple iterations of training, n represents the sample data set, and the target variable y i is the target predicted by the model, f(X i ) represents the i-th sample data set X i The predicted value of .
[0009] Optionally, the process of evaluating the energy efficiency level of an enterprise using the comparative analysis method includes: When the energy efficiency level of an enterprise is greater than the industry benchmark level, the rating is the first level; When the energy efficiency level of an enterprise is less than or equal to the industry benchmark level and greater than or equal to the baseline level, the rating is the second level; When the energy efficiency level of an enterprise is less than the benchmark level, the rating is the third level, wherein the first level is better than the second level, and the second level is better than the third level.
[0010] Optionally, the comprehensive evaluation score of the enterprise is calculated by weighting the enterprise's energy efficiency level and revenue according to the following formula: α 企业 =β 能效 +β 营收 +β 税收 +β 利润 ; In the formula, α 企业 is the comprehensive evaluation score of the enterprise, β 能效 is the energy efficiency score of the enterprise, β 营收 is the enterprise revenue level score, β 税收 is the corporate tax level score, β 利润 Score the company's profit level.
[0011] Optionally, the enterprise indicator evaluation score is calculated by weighting the enterprise's energy efficiency level and revenue according to the following formula: β x =(θ+ )*δ; In the formula, β x They represent the enterprise energy efficiency, revenue, tax, and profit indicators respectively, and δ represents β x The corresponding indicator weight, θ represents the basic score of the enterprise.
[0012] Optionally, a comprehensive evaluation score and energy efficiency rating label is provided for the enterprise based on its carbon credit rating, including: The high-carbon enterprise classification is achieved through the interval rating method, where the green logo represents the enterprise with the highest comprehensive evaluation score, the light green logo represents the enterprise with a medium comprehensive evaluation score, and the yellow logo represents the enterprise with the lowest comprehensive evaluation score.
[0013] On the other hand, the present invention also provides a system for generating a corporate carbon credit report, comprising: An acquisition unit is used to acquire enterprise data and pre-process the enterprise data to obtain target enterprise data, wherein the target enterprise data includes basic enterprise information, enterprise credit information and carbon reduction path; The verification unit is used to verify the target enterprise data using the enterprise prediction model pre-built based on the LightGBM algorithm to cross-verify the correctness of the target enterprise data; The evaluation unit is used to evaluate the energy efficiency level of enterprises by comparative analysis, and to determine the carbon credit rating of enterprises by weighted calculation based on their energy efficiency level and revenue; Identification unit, used to identify the comprehensive evaluation score and energy efficiency level of enterprises based on their carbon credit ratings; The generation unit is used to generate a corporate carbon credit report based on basic corporate information, corporate rating, corporate logo, corporate credit information and carbon reduction path.
[0014] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for generating a corporate carbon credit report when executing the program.
[0015] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for generating a corporate carbon credit report are implemented.
[0016] Through the above technical solutions, it is no longer limited to the single aspect of carbon emissions. It integrates multi-dimensional data such as basic information of enterprises, production information, business information, carbon emission data, credit information, etc., to generate carbon credit reports for enterprises in all aspects. After data collection and processing, the LightGBM mathematical algorithm model is used for comprehensive comparison and cross-validation to ensure data quality and accuracy. The enterprise data is comprehensively compared and verified with the platform data, and the public credit information platform is connected to query the administrative dishonesty records of enterprises, thereby ensuring the credibility of the enterprise carbon credit report.
[0017] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is an implementation flow chart of a method for generating a corporate carbon credit report provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of the composition of an enterprise carbon credit report provided by an embodiment of the present invention; Figure 3 The present invention provides a structural diagram of a system for generating a corporate carbon credit report. DETAILED DESCRIPTION
[0019] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.
[0020] See also Figure 1 As shown, it is an implementation flow chart of a method for generating a corporate carbon credit report provided by an embodiment of the present invention, which includes the following execution steps: Step 100: Acquire enterprise data and pre-process the enterprise data to obtain target enterprise data, wherein the target enterprise data includes basic enterprise information, enterprise credit information and carbon reduction path.
[0021] Specifically, based on the basic data of each enterprise, the total level of projects and enterprises in each industry, the industry average level, the energy efficiency and carbon emission intensity of each enterprise, and the carbon reduction path of the enterprise are obtained through data cleaning and data conversion pre-processing; among which, the data cleaning objects mainly include outliers, missing values and redundant data, and the data conversion objects mainly include energy measurement units, measurement units of energy consumption and energy carbon emission factors.
[0022] Preferably, the core data of enterprises in the "two high" industries are collected by information technology, including enterprise name, unified social credit code, legal person, contact number, enterprise nature, business status, above-scale type, number of employees, enterprise address, business scope, enterprise production data, carbon emission data, equipment level, and operating data. The above data are processed and used to calculate the carbon emission intensity and energy efficiency level of the enterprise.
[0023] Exemplary data cleaning methods: For outliers, simple statistical analysis, 3σ principle and other methods are used to identify and process them; for missing values, interpolation method is selected to fill them; and for redundant data, they are mainly removed through data deletion and data merging.
[0024] It should be noted that the 3σ principle, also known as the Laida criterion, is a method of processing data in statistics, especially suitable for sample data with normal or approximately normal distribution. This principle is derived based on the central limit theorem. It assumes that a set of test data contains only random errors. By calculating and processing these data, the standard deviation (σ) is obtained, and then an interval is determined. It is believed that errors beyond this interval are not random errors but gross errors, and data containing such errors should be eliminated. The two high-energy industries referred to in this article mainly include the "six high-energy-consuming industries" specified in the statistical communique, including petroleum, coal and other fuel processing industries, chemical raw materials and chemical products manufacturing industries, non-metallic mineral products industries, ferrous metal smelting and rolling processing industries, non-ferrous metal smelting and rolling processing industries, and electricity, heat production and supply industries.
[0025] Data conversion: Converting data into a unified format is a key step in energy statistics and carbon emissions calculation. This requires converting the measurement units of different energy sources into standard coal units for unified comparison and calculation. In addition, the measurement units of different energy consumption are converted into tons of standard coal. At the same time, in order to calculate carbon emissions, it is also necessary to refer to the carbon emission factors of different energy sources with standard coal, that is, to determine the carbon dioxide emissions generated by each energy source per unit of energy. The above conversion method enables comprehensive comparison between different energy sources and accurate calculation of carbon emissions.
[0026] Among them, the enterprise energy efficiency and enterprise carbon emission intensity are obtained through preprocessing, and the calculation formula is as follows: Energy efficiency = comprehensive energy consumption of the enterprise / product output; Enterprise carbon emission intensity = enterprise monthly carbon emissions (tons) / enterprise monthly income (10,000 yuan).
[0027] Step 101: Use the enterprise prediction model pre-built based on the LightGBM algorithm to verify the target enterprise data to cross-validate the correctness of the target enterprise data.
[0028] In a specific implementation, after data preprocessing, a mathematical analysis model is established to conduct a comprehensive comparison and cross-validation of production data, energy data such as electricity, water, coal, and gas, statistical data, tax data, and credit data. The analysis process of the mathematical analysis model is as follows: from the dimensions of energy input and energy output, industry indicator sets are established to form an industry indicator library to precipitate industry production characteristics. The LightGBM algorithm is used to build an enterprise prediction model, which mines the correlation between energy consumption, carbon emissions, electricity consumption, etc., and uses the model for comprehensive comparison to cross-validate the correctness of enterprise data.
[0029] The LightGBM model training process is as follows: (1) Feature variable definition: Assume that there are n sample data sets, and the features of each sample include: energy consumption data (such as power consumption X i,1 , water consumption X i,2 、Coal consumption X i,3 、Gas consumption X i,4 Statistics (such as production, working hours, etc., with X i,5 ,X i,6 ,......,X i,k ), tax data (such as tax expenditure X i,k+1 ), credit data (credit rating X i,k+2 ). (2) Model construction: Let the target variable y i For the target predicted by the model (such as enterprise risk level, energy consumption trend or production efficiency, etc.), the model that needs to be fitted is: =f(X i ); where f is the prediction function constructed by the LightGBM model. (3) Loss function: If the mean square error (MSE) is used as the loss function, the loss function is defined as: ,(4) Model training and cross-validation: Iteratively update the gradient boosting tree of LightGBM to gradually minimize the loss function, and perform cross-validation (such as K-fold cross-validation) on the training set to ensure the generalization ability of the model.
[0030] Specifically, the enterprise prediction model built based on the LightGBM algorithm is characterized as follows:
[0031] In the formula, f* represents the optimal enterprise prediction model after multiple iterations of training, n represents the sample data set, and the target variable y i is the target predicted by the model, f(X i ) represents the i-th sample data set X i The predicted value of .
[0032] Step 102: Use comparative analysis to evaluate the energy efficiency level of the enterprise, and perform weighted calculation based on the energy efficiency level and revenue of the enterprise to determine the carbon credit rating of the enterprise.
[0033] Specifically, the process of evaluating the energy efficiency level of an enterprise using the comparative analysis method includes: when the energy efficiency level of an enterprise is greater than the energy efficiency of the industry benchmark level, it is rated as the first level; when the energy efficiency level of an enterprise is less than or equal to the energy efficiency of the industry benchmark level and greater than or equal to the energy efficiency of the benchmark level, it is rated as the second level; when the energy efficiency level of an enterprise is less than the energy efficiency of the benchmark level, it is rated as the third level, wherein the first level is better than the second level, and the second level is better than the third level.
[0034] For example, the evaluation of the energy efficiency level of an enterprise: First, define the following variables. E: the energy efficiency level of the enterprise, S: the energy efficiency of the industry benchmark level, B: the energy efficiency of the baseline level. Then, the rating is performed according to the following rating conditions. When E>S, the rating is A. When S≥E≥B, the rating is B. When E <b 时，评级为c。用数学表达式，可表示为：rating="A，IFE">S; Rating=B, IF S≥E≥B; Rating=C, IF E <B。
[0035] More specifically, the comprehensive evaluation score of an enterprise is calculated by weighting its energy efficiency level and revenue according to the following formula: α 企业 =β 能效 +β 营收 +β 税收 +β 利润 ; In the formula, α 企业 is the comprehensive evaluation score of the enterprise, β 能效 is the energy efficiency score of the enterprise, β 营收 is the enterprise revenue level score, β 税收 is the corporate tax level score, β 利润 Score the company's profit level.
[0036] It should be noted that the maximum comprehensive evaluation score of an enterprise shall not exceed 100 points, the maximum energy efficiency score of an enterprise shall not exceed 70 points, the maximum revenue score of an enterprise shall not exceed 10 points, the maximum tax score of an enterprise shall not exceed 10 points, and the maximum profit score of an enterprise shall not exceed 10 points.
[0037] More specifically, the enterprise index evaluation score is calculated by weighting the enterprise's energy efficiency level and revenue according to the following formula: β x =(θ+ )*δ; In the formula, β x They represent the enterprise energy efficiency, revenue, tax, and profit indicators respectively, and δ represents β x The corresponding indicator weight, θ represents the basic score of the enterprise.
[0038] Exemplarily, the enterprise indicator evaluation score calculation method is as follows: β x =(60+ )*δ; β x They represent the energy efficiency, revenue, tax and profit of enterprises respectively, and δ represents the corresponding β x The indicator weights include 70% for energy efficiency, 10% for revenue, 10% for tax and 10% for profit. When the actual value of an enterprise is the same as the industry average, the α enterprise is 60 points; when the actual value of an enterprise is the same as the industry optimal value, the α enterprise is 100 points.
[0039] Step 103: Based on the corporate carbon credit rating, the enterprise is given a comprehensive evaluation score and an energy efficiency rating.
[0040] Exemplarily, the high-carbon enterprise classification is achieved through an interval rating method, in which a green logo is used to represent an enterprise with the highest comprehensive evaluation score, a light green logo represents an enterprise with a medium comprehensive evaluation score, and a yellow logo represents an enterprise with the lowest comprehensive evaluation score.
[0041] In a specific implementation, the high-carbon enterprise classification is achieved through the interval rating method. The green mark indicates that the enterprise has the highest comprehensive evaluation score, followed by the light green mark, and finally the yellow mark. The specific rules are as follows: Enterprise level 1: When the enterprise's comprehensive evaluation score is in the interval [B, ꝏ), the enterprise is marked with green; Enterprise level 2: When the enterprise's comprehensive evaluation score is in the interval [A, B), the enterprise is marked with light green; Enterprise level 3: When the enterprise's comprehensive evaluation score is in the interval [0, A), the enterprise is marked with yellow. Among them, A and B represent the boundary values of the enterprise score interval determination.
[0042] For example, at the first level of enterprise: when the enterprise comprehensive evaluation score is in the interval [75, ꝏ), the enterprise is marked with green; at the second level of enterprise: when the enterprise comprehensive evaluation score is in the interval [55, 75), the enterprise is marked with light green; at the third level of enterprise: when the enterprise comprehensive evaluation score is in the interval [0, 55), the enterprise is marked with yellow. First, define the following parts: define variable S as the comprehensive evaluation score of the enterprise. Define three intervals, corresponding to three enterprise carbon credit levels. Convert the rules into the following mathematical expressions: If S ∈[75,ꝏ), then carbon credit rating = green label (enterprise level); If S ∈[55,75), then carbon credit rating = light green mark (enterprise level 2); If S ∈[0,55), then carbon credit rating = yellow mark (enterprise level 3).
[0043] Here S is the comprehensive evaluation score of the enterprise. The enterprise's carbon credit rating and corresponding logo are determined according to the range to which the value of S belongs.
[0044] In the present invention, the comparative analysis and weighted calculation methods are used to evaluate the energy efficiency level of enterprises and rate their carbon credit. In the carbon credit evaluation process, not only the energy efficiency of the enterprise's carbon emissions is considered, but also the enterprise's revenue, tax, profit and other factors are combined to more comprehensively reflect the carbon credit of the enterprise through multi-dimensional data analysis.
[0045] Step 104: Generate a corporate carbon credit report based on the corporate basic information, corporate rating, corporate logo, corporate credit information and carbon reduction path.
[0046] Among them, corporate credit information is connected to the public credit information platform to conduct a comprehensive evaluation query of corporate public credit, query whether the reporting subject has a record of dishonest behavior in administrative fields such as market supervision, environmental protection, industry and commerce, and taxation, and display the corporate credit rating and dishonest behavior record in the credit report. Carbon reduction path (measures taken by enterprises to achieve carbon reduction targets) obtains information on corporate technological transformation projects through processed data, including project name, implementation time, industry, technical route, expected results, and funding source.
[0047] For example, see Figure 2 As shown in the figure, the carbon credit report includes five modules: basic information of the enterprise, enterprise rating, enterprise logo, public credit information, and carbon reduction path. Each module contains the following content. Basic information: enterprise name, unified social credit code, legal person, contact number, enterprise nature, business status, above-scale type, number of employees, environmental performance rating, safety production standardization classification, annual R&D investment, enterprise information, enterprise detailed address, and enterprise business scope. Enterprise rating: industry, energy efficiency level, enterprise carbon emission intensity. Enterprise logo: industry, color logo, logo interpretation. Public credit information: public credit rating, public credit interpretation. Carbon reduction path: project name, implementation time, industry, technical route, expected effect, and source of funds. The relevant logic code written in Python language is used to realize the generation of an automated carbon credit report. The report covers five core modules: basic information of the enterprise, enterprise rating, enterprise logo, public credit information, and carbon reduction path. Specifically, the report will show in detail the basic information such as enterprise name, unified social credit code, legal representative, contact number, enterprise nature, business status, and number of employees. In the enterprise rating module, the focus is on assessing the energy efficiency level and carbon emission intensity of the enterprise. The enterprise identification module displays the industry affiliation, color identification and its interpretation. The public credit information module will reveal the public credit rating of the enterprise and its specific meaning. Finally, the carbon reduction path module will display the name of the enterprise's carbon reduction project, implementation time, technical route, expected effect and funding source in detail, providing strong support for enterprises to formulate scientific carbon reduction strategies.
[0048] The technical effects achieved by this application are as follows: it is no longer limited to the single aspect of carbon emissions, but integrates multi-dimensional data such as basic enterprise information, production information, business information, carbon emission data, and credit information to generate a comprehensive carbon credit report for the enterprise. After data collection and processing, the LightGBM mathematical algorithm model is used for comprehensive comparison and cross-validation to ensure data quality and accuracy. The enterprise data is comprehensively compared and verified with the platform data, and the public credit information platform is connected to query the administrative dishonesty record of the enterprise, thereby ensuring the credibility of the enterprise carbon credit report.
[0049] See also Figure 3 FIG. 1 is a schematic diagram of a structure of a system for generating a corporate carbon credit report provided by an embodiment of the present invention, including: The acquisition unit 30 is used to acquire enterprise data and pre-process the enterprise data to obtain target enterprise data, wherein the target enterprise data includes basic enterprise information, enterprise credit information and carbon reduction path; A verification unit 31 is used to verify the target enterprise data by using the enterprise prediction model pre-built based on the LightGBM algorithm to cross-verify the correctness of the target enterprise data; An evaluation unit 32 is used to evaluate the energy efficiency level of the enterprise by using a comparative analysis method, and to perform a weighted calculation based on the energy efficiency level and revenue of the enterprise to determine the carbon credit rating of the enterprise; An identification unit 33 is used to identify the comprehensive evaluation score and energy efficiency level of the enterprise based on the enterprise carbon credit rating; The generating unit 34 is used to generate a corporate carbon credit report based on the basic information of the enterprise, the corporate rating, the corporate identification, the corporate credit information and the carbon reduction path.
[0050] To sum up, the carbon credit report generation system proposed in this application integrates multi-dimensional data sources, including basic information of enterprises, enterprise ratings, enterprise logos, public credit information, and carbon reduction paths, reflecting the low-carbon development of enterprises in many aspects and providing reference value for investors, financial institutions and other stakeholders.
[0051] The enterprise carbon credit report generation system includes a processor and a memory. The acquisition unit, verification unit, evaluation unit, identification unit and generation unit are all stored in the memory as program units. The processor executes the program units stored in the memory to realize corresponding functions.
[0052] The processor contains a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problems of single data dimension, insufficient report accuracy, and insufficient credibility in the current corporate carbon credit report generation process. By utilizing multi-source data, this method can improve the comprehensiveness and accuracy of data, and at the same time combine efficient data processing and analysis technology to generate more comprehensive, accurate, and reliable corporate carbon credit reports to support the company's low-carbon economic development and carbon management decisions.
[0053] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0054] An embodiment of the present invention provides an electronic device, the device including a processor, a memory, and a program stored in the memory and executable on the processor. The device in this article may be a server, a PC, a PAD, a mobile phone, etc.
[0055] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0056] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0057] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0059] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0060] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0061] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0062] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the existence of other identical elements in the process, method, commodity or device including the element.
[0063] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.
Claims
1. A method for generating a corporate carbon credit report, characterized in that: include: Obtain enterprise data and pre-process the enterprise data to obtain target enterprise data, where the target enterprise data includes basic enterprise information, enterprise credit information and carbon reduction path; Use the enterprise prediction model pre-built based on the LightGBM algorithm to verify the target enterprise data to cross-verify the correctness of the target enterprise data; Comparative analysis is used to evaluate the energy efficiency level of enterprises, and weighted calculation is performed based on the energy efficiency level and revenue of the enterprises to determine the carbon credit rating of the enterprises; Provide comprehensive evaluation scores and energy efficiency ratings to companies based on their carbon credit ratings; Generate a corporate carbon credit report based on basic corporate information, corporate rating, corporate logo, corporate credit information and carbon reduction path.
2. The method for generating a corporate carbon credit report according to claim 1, characterized in that: Acquire enterprise data and pre-process the enterprise data to obtain target enterprise data, including: Based on the basic data of each enterprise, the total level of projects and enterprises in each industry, the industry average level, the energy efficiency and carbon emission intensity of each enterprise, and the carbon reduction path of the enterprise are obtained through data cleaning and data conversion preprocessing; among them, the data cleaning objects mainly include outliers, missing values and redundant data, and the data conversion objects mainly include energy measurement units, measurement units of energy consumption and energy carbon emission factors.
3. The method for generating a corporate carbon credit report according to claim 1, characterized in that: The enterprise prediction model built based on the LightGBM algorithm is characterized as follows: In the formula, f* represents the optimal enterprise prediction model after multiple iterations of training, n represents the sample data set, and the target variable y i is the target predicted by the model, f(X i ) represents the i-th sample data set X i The predicted value of .
4. The method for generating a corporate carbon credit report according to claim 1, characterized in that: The process of evaluating the energy efficiency level of an enterprise using the comparative analysis method includes: When the energy efficiency level of an enterprise is greater than the industry benchmark level, the rating is the first level; When the energy efficiency level of an enterprise is less than or equal to the industry benchmark level and greater than or equal to the baseline level, the rating is the second level; When the energy efficiency level of an enterprise is less than the benchmark level, the rating is the third level, wherein the first level is better than the second level, and the second level is better than the third level.
5. The method for generating a corporate carbon credit report according to claim 1, characterized in that: The comprehensive evaluation score of an enterprise is calculated by weighting its energy efficiency level and revenue according to the following formula: α 企业 =β 能效 +β 营收 +β 税收 +β 利润 ； In the formula, α 企业 is the comprehensive evaluation score of the enterprise, β 能效 is the energy efficiency score of the enterprise, β 营收 is the enterprise revenue level score, β 税收 is the corporate tax level score, β 利润 Score the company's profit level.
6. The method for generating a corporate carbon credit report according to claim 5, characterized in that: The enterprise index evaluation score is calculated by weighting the enterprise's energy efficiency level and revenue according to the following formula: b x =(θ+ )*d; In the formula, β x They represent the enterprise energy efficiency, revenue, tax, and profit indicators respectively, and δ represents β x The corresponding indicator weight, θ represents the basic score of the enterprise.
7. The method for generating a corporate carbon credit report according to claim 1, characterized in that: Based on the corporate carbon credit rating, the company is given a comprehensive evaluation score and energy efficiency rating, including: The high-carbon enterprise classification is achieved through the interval rating method, where the green logo represents the enterprise with the highest comprehensive evaluation score, the light green logo represents the enterprise with a medium comprehensive evaluation score, and the yellow logo represents the enterprise with the lowest comprehensive evaluation score.
8. A system for generating corporate carbon credit reports, characterized in that: include: An acquisition unit is used to acquire enterprise data and pre-process the enterprise data to obtain target enterprise data, wherein the target enterprise data includes basic enterprise information, enterprise credit information and carbon reduction path; The verification unit is used to verify the target enterprise data using the enterprise prediction model pre-built based on the LightGBM algorithm to cross-verify the correctness of the target enterprise data; The evaluation unit is used to evaluate the energy efficiency level of enterprises by comparative analysis, and to determine the carbon credit rating of enterprises by weighted calculation based on their energy efficiency level and revenue; Identification unit, used to identify the comprehensive evaluation score and energy efficiency level of enterprises based on their carbon credit ratings; The generation unit is used to generate a corporate carbon credit report based on basic corporate information, corporate rating, corporate logo, corporate credit information and carbon reduction path.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for generating a corporate carbon credit report according to any one of claims 1 to 7 are implemented.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for generating a corporate carbon credit report according to any one of claims 1 to 7 are implemented.