Method for dynamically optimizing urban carbon emission through digital twinborn model, electronic equipment and storage medium

Abstract

The invention discloses a method for dynamically optimizing urban carbon emission through a digital twinborn model, electronic equipment and a storage medium, and relates to the technical field of data analysis, and the method comprises the following steps: calculating a first emission amount, screening a first driving factor, constructing a first driving model, screening a second driving factor, and constructing a second driving model. And a comprehensive driving model is obtained, the comprehensive driving model is compensated, the current carbon dioxide emission amount is compared with the standard carbon dioxide emission amount, and a driving factor adjusting decision is made. According to the method, through a clear classification standard, the reliability of the model is improved, a basis is provided for decision-making through identification and analysis of driving factors, the adaptability and prediction capability of dynamic change of carbon emission are enhanced by integrating a multi-level driving model, an accurate emission reduction strategy is formulated, the management efficiency is improved, and sustainable development of cities is promoted. The scientificity and rationality of carbon emission management are improved, and data support and theoretical basis are provided for urban policy making.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method, electronic equipment and storage medium for dynamically optimizing urban carbon emissions through a digital twin model. Background Art

[0002] In recent years, urban carbon emission optimization technology has been developing in a diversified and systematic direction, involving multiple fields such as energy and transportation. It uses big data and artificial intelligence to analyze urban carbon emission sources, optimize resource allocation and policy formulation, and plays a key role in the ability to respond to climate change, improve environmental quality and achieve sustainable development.

[0003] At present, a Chinese invention patent with publication number CN 116205325A discloses a carbon dioxide emission accounting and optimization method for cities. The method establishes a city carbon emission factor accounting model, clarifies the main carbon emission reduction behaviors of the city, establishes a city carbon emission reduction accounting model, establishes a city carbon neutrality progress rate calculation model based on the city's carbon emissions and carbon emission reduction levels, analyzes the main influencing factors of urban carbon emissions, and constructs a city carbon emission optimization model. However, the relevant technology does not construct a comprehensive indicator model to calculate the indicators of the carbon emission footprint of enterprises, lacks the simplicity, applicability and comprehensiveness of calculation, does not divide the sources of corporate carbon footprint into levels, is not conducive to the simplicity and accuracy of indicator selection, and is not conducive to the clear formulation of optimization strategies, and has certain limitations. Summary of the invention

[0004] The technical problem solved by the present invention is that: the relevant technology does not construct a comprehensive indicator model to calculate the indicators of the carbon emission footprint of the enterprise, lacks the simplicity, applicability and comprehensiveness of the calculation, does not hierarchically divide the sources of the carbon footprint of the enterprise, is not conducive to the simplicity and accuracy of the indicator selection, and is not conducive to the clear formulation of optimization strategies, and has certain limitations.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, a method for dynamically optimizing urban carbon emissions through a digital twin model comprises the following steps:

[0006] Step S100, setting the primary standard and secondary standard for enterprise classification, performing a first classification on the enterprises in the city according to the primary standard to obtain a first sub-enterprise, assigning a first number to the first sub-enterprise, performing a second classification on the enterprises in the city according to the secondary standard to obtain a second sub-enterprise, assigning a second number to the second sub-enterprise, obtaining the carbon dioxide emissions of the enterprises after the second number, and recording it as the first emissions;

[0007] Step S200, screening a first driving factor according to the first sub-enterprise, calculating a first weight of the first driving factor, constructing a first driving model according to the first weight, screening a second driving factor according to the second sub-enterprise, calculating a second weight of the second driving factor, constructing a second driving model according to the second weight, obtaining a comprehensive driving model according to the first driving model and the second driving model, and compensating the comprehensive driving model;

[0008] Step S300, obtain the current second subsidiary, obtain the current carbon dioxide emissions of the current second subsidiary according to the compensated comprehensive driving model, obtain the standard carbon dioxide emissions of the second subsidiary, compare the current carbon dioxide emissions with the standard carbon dioxide emissions, and make a driving factor adjustment decision based on the comparison result.

[0009] As a preferred solution of the method for dynamically optimizing urban carbon emissions through a digital twin model described in the present invention, step S100 includes the following sub-steps:

[0010] Step S101, setting the primary standard and secondary standard for enterprise classification, wherein the primary standard is set according to the enterprise size, and the secondary standard is divided according to the industry to which it belongs;

[0011] The first-level standard includes large scale, medium scale and small scale. The enterprise scale is divided according to the number of employees. The first value and the second value are set as the number threshold. When the number of employees is greater than the first value, the first-level standard is set to large scale. When the number of employees is less than or equal to the first value and greater than the second value, the first-level standard is set to medium scale. When the number of employees is less than or equal to the second value, the first-level standard is set to small scale.

[0012] The secondary standards include industry, transportation and agriculture;

[0013] Step S102: Perform a first classification on the enterprises in the city according to the primary standard to obtain a first sub-enterprise, and assign a first number to the first sub-enterprise, wherein the first number is represented by X. i , where i is a natural number and i∈[1,3], the first subsidiary enterprise includes a large-scale first-level subsidiary enterprise, a medium-scale first-level subsidiary enterprise and a small-scale first-level subsidiary enterprise;

[0014] Obtain the number of employees of the enterprise and compare it with the first-level standard. When the number of employees of the enterprise is large-scale, set the first subsidiary enterprise as a large-scale first-level subsidiary enterprise; when the number of employees of the enterprise is medium-scale, set the first subsidiary enterprise as a medium-scale first-level subsidiary enterprise; when the number of employees of the enterprise is small-scale, set the first subsidiary enterprise as a small-scale first-level subsidiary enterprise;

[0015] Step S103, performing a second classification on the enterprises in the city according to the secondary standard to obtain a second sub-enterprise, and assigning a second number to the second sub-enterprise, wherein the second number corresponds to the first number, and the second number is represented by X ij , where j is a natural number and j∈[1,3], the second sub-enterprises include the second industrial sub-enterprises, the second transportation sub-enterprises and the second agricultural sub-enterprises;

[0016] Step S104, obtain the carbon dioxide emissions of the second-numbered enterprises, calculate the average of the carbon dioxide emissions of the second-numbered enterprises, record it as the first average, calculate the second emissions based on the carbon dioxide emissions of the second-numbered enterprises, the second emissions represent the total carbon dioxide emissions of the city, and are obtained by weighted calculation of the carbon dioxide emissions of the second-numbered enterprises.

[0017] As a preferred solution of the method for dynamically optimizing urban carbon emissions through a digital twin model described in the present invention, step S200 includes the following sub-steps:

[0018] Step S201, screening a first driving factor according to the first subsidiary, wherein the first driving factor includes equipment efficiency, management efficiency, production scale and supply chain turnover times;

[0019] Step S202, calculating a first weight of a first driving factor, and constructing a first driving model according to the first weight. The calculation logic of the first weight includes:

[0020] Obtain the carbon dioxide emissions of the first subsidiary, perform weighted calculation on the carbon dioxide emissions of the first subsidiary to obtain the total emissions of the first subsidiary category, calculate the average of the total emissions of the first subsidiary category, record it as the first average, take the carbon dioxide emissions of the first subsidiary as the dependent variable, take equipment efficiency, management efficiency, production scale and supply chain turnover times as independent variables, calculate the weights corresponding to equipment efficiency, management efficiency, production scale and supply chain turnover times respectively through multiple regression analysis, record it as the first weight;

[0021] Step S203, screening the second driving factor according to the second sub-enterprise, the second driving factor corresponding to the industrial second sub-enterprise includes energy efficiency, manufacturing process duration and waste recycling efficiency, the second driving factor corresponding to the transportation second sub-enterprise includes fuel combustion efficiency and the number of vehicles, the second driving factor corresponding to the agricultural second sub-enterprise includes pesticide dosage and vegetation coverage, calculating the second weight of the second driving factor, constructing the second driving model according to the second weight, the calculation logic of the second weight includes:

[0022] Obtain the first emission of the second subsidiary, take the first emission of the second subsidiary as the dependent variable, take the second driving factor corresponding to the second subsidiary as the independent variable, and calculate the weights corresponding to the second driving factor corresponding to the second subsidiary through multiple regression analysis, which are recorded as second weights;

[0023] Step S204: obtaining a comprehensive driving model according to the first driving model and the second driving model.

[0024] As a preferred solution of the method for dynamically optimizing urban carbon emissions through a digital twin model described in the present invention, the calculation logic of the first average value includes:

[0025] Get the first number as X i The carbon dioxide emissions corresponding to the first subsidiary of i The carbon dioxide emissions corresponding to the first sub-enterprises of the i-th category are weighted to obtain the total emissions of the first sub-enterprises, and the average of the total emissions of the first sub-enterprises is calculated, which is recorded as the first average. The first average is represented by the average of the carbon dioxide emissions of the first sub-enterprises of the i-th category;

[0026] The calculation logic of the first emission amount includes:

[0027] Get the second number as X ij The carbon dioxide emissions corresponding to the second subsidiary of ij The carbon dioxide emissions corresponding to the second subsidiaries are weightedly calculated to obtain the total emissions of the second sub-enterprises, and the average value of the total emissions of the second sub-enterprises is calculated and recorded as the first emissions. The first emissions represent the average value of the carbon dioxide emissions of the first subsidiaries of the i-th category and the second subsidiaries of the j-th category.

[0028] As a preferred solution of the method for dynamically optimizing urban carbon emissions through a digital twin model described in the present invention, the calculation expression of the first driving model is:

[0029]

[0030] Among them, P i is the first average value of the first subsidiary of the first category i, k t is the tth first driving factor, C t is the coefficient corresponding to the tth first driving factor, that is, the first weight, and m is the number of first driving factors;

[0031] The calculation expression of the second driving model is:

[0032]

[0033] Among them, Q ij The second number is x ij The first emission corresponding to the second subsidiary, G n is the nth second driving factor, l n is the coefficient corresponding to the nth second driving factor, that is, the second weight, and n is the number of second driving factors.

[0034] As a preferred solution of the method for dynamically optimizing urban carbon emissions through a digital twin model described in the present invention, the calculation logic of the comprehensive driving model includes:

[0035] Obtain the first weight of the first driving model and the second weight of the second driving model, and according to the coefficient rule of multiple regression analysis, obtain that the sum of the first weight is 1 and the sum of the second weight is 1, use the independent variable of the first driving model and the independent variable of the second driving model as new independent variables of the comprehensive driving model, use half of the first weight of the first driving model and half of the second weight of the second driving model as new weights of the comprehensive driving model, construct the comprehensive driving model, and set the correction value to compensate for the error of the comprehensive driving model;

[0036] The setting logic of the correction value includes:

[0037] Obtain any first emission amount and a corresponding first average value, calculate the difference between the first emission amount and the corresponding first average value, record it as a first difference, traverse the first difference values, calculate the average value of the first difference values, take half of the average value of the first difference values, set half of the average value of the first difference values ​​as a correction value, perform weighted calculation on the correction value and the comprehensive driving model, and the correction value is a positive value, a negative value or zero;

[0038] The calculation expression of the compensated comprehensive driving model is:

[0039]

[0040] Among them, ε is the correction value.

[0041] As a preferred solution of the method for dynamically optimizing urban carbon emissions through a digital twin model described in the present invention, the acquisition logic of the first driving factor and the second driving factor includes:

[0042] Retrieve a survey database, input the source of carbon dioxide into the survey database, match survey data related to the source of carbon dioxide, automatically segment the text to obtain words through a word segmentation model, count the frequency of each word in the survey data through an unsupervised network learning model, set a word frequency threshold, traverse the word frequency, compare the word frequency with the word frequency threshold, when the word frequency is greater than the word frequency threshold, retain the word corresponding to the word frequency, otherwise, delete the word corresponding to the word frequency, extract semantic features of the retained words, the semantic features include scale features and industry features, set the retained words related to the scale features as the first driving factor, and set the words related to the industry features as the second driving factor.

[0043] As a preferred solution of the method for dynamically optimizing urban carbon emissions through a digital twin model described in the present invention, step S300 includes the following sub-steps:

[0044] Step S301, obtaining the second number of the current second subsidiary enterprise;

[0045] Step S302, obtaining the current first average value of the current second subsidiary according to the compensated comprehensive driving model, obtaining the standard carbon dioxide emissions of the second subsidiary, and comparing the current first average value with the standard carbon dioxide emissions to obtain a comparison result, wherein the comparison result includes that the current first average value is greater than the standard carbon dioxide emissions, and the current first average value is less than or equal to the standard carbon dioxide emissions;

[0046] Step S303: formulating a driving factor adjustment decision according to the comparison result. The logic for formulating the driving factor adjustment decision includes:

[0047] Obtain a comparison result. When the comparison result is that the current first average value is less than or equal to the standard carbon dioxide emissions, set the driving factor adjustment decision to maintain the status quo. When the comparison result is that the current first average value is greater than the standard carbon dioxide emissions, calculate the difference between the current first average value and the standard carbon dioxide emissions, record it as the second difference, obtain a new weight of the comprehensive driving model, calculate the product of the new weight and the second difference, record it as the first product, set the first product as the change amount, and set the driving factor adjustment decision to reduce or increase the corresponding first driving factor and the corresponding second driving factor according to the first product.

[0048] In a second aspect, the present invention provides an electronic device comprising a memory, a processor and storage in the memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in any one of the methods described above are executed.

[0049] In a third aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in any one of the methods described above are executed.

[0050] The beneficial effects of the present invention are as follows: through clear classification standards, it is easy to identify and compare the emissions of different enterprises, formulate targeted measures, provide accurate emission data for subsequent calculations and optimization, and improve the reliability of the model. By identifying and analyzing driving factors, a more comprehensive understanding of the causes of emissions can be achieved to provide a basis for decision-making. The integrated multi-level driving model enhances the adaptability and prediction capabilities to the dynamic changes in carbon emissions, dynamically obtains current emission data, ensures timely grasp of the carbon emissions of enterprises, formulates accurate emission reduction strategies based on real-time data and model predictions, improves management efficiency, and realizes dynamic optimization of carbon emissions of urban enterprises, thereby effectively controlling and reducing carbon dioxide emissions and promoting the sustainable development of cities. It not only improves the scientificity and rationality of carbon emission management, but also provides data support and theoretical basis for urban policy making. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A basic flow chart of a method for dynamically optimizing urban carbon emissions through a digital twin model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0053] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a method for dynamically optimizing urban carbon emissions through a digital twin model, comprising the following steps:

[0054] Step S100, setting the primary standard and secondary standard for enterprise classification, performing a first classification on the enterprises in the city according to the primary standard to obtain a first sub-enterprise, assigning a first number to the first sub-enterprise, performing a second classification on the enterprises in the city according to the secondary standard to obtain a second sub-enterprise, assigning a second number to the second sub-enterprise, obtaining the carbon dioxide emissions of the enterprises after the second number, and recording it as the first emissions;

[0055] Step S200, screening a first driving factor according to the first sub-enterprise, calculating a first weight of the first driving factor, constructing a first driving model according to the first weight, screening a second driving factor according to the second sub-enterprise, calculating a second weight of the second driving factor, constructing a second driving model according to the second weight, obtaining a comprehensive driving model according to the first driving model and the second driving model, and compensating the comprehensive driving model;

[0056] Step S300, obtain the current second subsidiary, obtain the current carbon dioxide emissions of the current second subsidiary according to the compensated comprehensive driving model, obtain the standard carbon dioxide emissions of the second subsidiary, compare the current carbon dioxide emissions with the standard carbon dioxide emissions, and make a driving factor adjustment decision based on the comparison result.

[0057] The present invention uses clear classification standards to facilitate the identification and comparison of emissions from different enterprises, formulate targeted measures, provide accurate emission data for subsequent calculations and optimization, and improve the reliability of the model. By identifying and analyzing driving factors, we can more comprehensively understand the causes of emissions and provide a basis for decision-making. The integrated multi-level driving model enhances the adaptability and prediction capabilities to dynamic changes in carbon emissions, dynamically obtains current emission data, ensures timely grasp of the carbon emissions of enterprises, formulates accurate emission reduction strategies based on real-time data and model predictions, improves management efficiency, and realizes dynamic optimization of carbon emissions of urban enterprises, thereby effectively controlling and reducing carbon dioxide emissions and promoting the sustainable development of cities. It not only improves the scientificity and rationality of carbon emission management, but also provides data support and theoretical basis for urban policy making.

[0058] In specific implementation, the driver adjustment decisions for the first driver include implementing regular preventive maintenance plans, introducing new technologies and automated equipment, selecting energy-saving equipment, regularly training operators, using process automation software, introducing an enterprise resource planning (ERP) system, dynamically adjusting production scale according to changes in market demand, implementing inventory management strategies such as first-in, first-out (FIFO) or last-in, first-out (LIFO), and adopting a JIT (just-in-time) model;

[0059] Driver adjustment decisions for the second driver of the industrial second subsidiary include investing in energy-saving equipment and technology, using renewable energy, reducing equipment idling time, regularly training employees on energy conservation, developing standard operating procedures (SOPs), recycling materials, and developing new materials and processes;

[0060] Driver adjustment decisions for the second driver of the second subsidiary of the transportation industry include adopting high-efficiency engines (such as turbocharging and direct injection technology), regularly cleaning fuel injectors, air filters and exhaust systems, using cleaner alternative fuels (such as biodiesel, natural gas or electric drive), training drivers to adopt fuel-efficient driving behaviors (such as gentle acceleration, deceleration and maintaining a steady speed) and choosing the optimal route;

[0061] The driver adjustment decisions for the second driver of the second agricultural subsidiary include using precision fertilization and pesticide application agricultural technologies (such as drones, GPS and sensors), implementing variable application (such as adjusting the amount of pesticides applied according to the occurrence of pests and diseases in different areas), selecting high-efficiency and low-toxic pesticide varieties, ensuring that the dosage and frequency of use are in line with the optimal time, regularly training farmers and agricultural practitioners on the safe use of pesticides and environmental protection, adopting crop rotation and intercropping methods, maintaining vegetation and residues on the soil surface, setting up shelterbelts, grass belts or terraces on slopes or areas prone to erosion, and recycling rainwater.

[0062] The step S100 includes the following sub-steps:

[0063] Step S101, setting the primary standard and secondary standard for enterprise classification, wherein the primary standard is set according to the enterprise size, and the secondary standard is divided according to the industry to which it belongs;

[0064] The first-level standard includes large scale, medium scale and small scale. The enterprise scale is divided according to the number of employees. The first value and the second value are set as the number threshold. When the number of employees is greater than the first value, the first-level standard is set to large scale. When the number of employees is less than or equal to the first value and greater than the second value, the first-level standard is set to medium scale. When the number of employees is less than or equal to the second value, the first-level standard is set to small scale.

[0065] The secondary standards include industry, transportation and agriculture;

[0066] Step S102: Perform a first classification on the enterprises in the city according to the primary standard to obtain a first sub-enterprise, and assign a first number to the first sub-enterprise, wherein the first number is represented by X. i , where i is a natural number and i∈[1,3], the first subsidiary enterprise includes a large-scale first-level subsidiary enterprise, a medium-scale first-level subsidiary enterprise and a small-scale first-level subsidiary enterprise;

[0067] Obtain the number of employees of the enterprise and compare it with the first-level standard. When the number of employees of the enterprise is large-scale, set the first subsidiary enterprise as a large-scale first-level subsidiary enterprise; when the number of employees of the enterprise is medium-scale, set the first subsidiary enterprise as a medium-scale first-level subsidiary enterprise; when the number of employees of the enterprise is small-scale, set the first subsidiary enterprise as a small-scale first-level subsidiary enterprise;

[0068] Step S103, performing a second classification on the enterprises in the city according to the secondary standard to obtain a second sub-enterprise, and assigning a second number to the second sub-enterprise, wherein the second number corresponds to the first number, and the second number is represented by X ij , where j is a natural number and j∈[1,3], the second sub-enterprises include the second industrial sub-enterprises, the second transportation sub-enterprises and the second agricultural sub-enterprises;

[0069] Step S104, obtain the carbon dioxide emissions of the second-numbered enterprises, calculate the average of the carbon dioxide emissions of the second-numbered enterprises, record it as the first average, calculate the second emissions based on the carbon dioxide emissions of the second-numbered enterprises, the second emissions represent the total carbon dioxide emissions of the city, and are obtained by weighted calculation of the carbon dioxide emissions of the second-numbered enterprises.

[0070] In the specific implementation, by setting primary and secondary standards, enterprises are systematically classified according to their scale and industry, which helps to accurately analyze the characteristics and needs of different types of enterprises. The scale is divided by the number of employees (large, medium and small), making the classification more objective and easy to implement. A unique number (such as Xii and Xij) is assigned to each subsidiary, effectively managing and tracking the data of enterprises of different categories, facilitating subsequent data analysis and decision support, and calculating the average carbon dioxide emissions (first average) and the city's overall emissions (second emissions), which helps to understand the overall emission trends and support the formulation of environmental protection policies. Through classification and emission calculations, the government and relevant departments can formulate more scientific and reasonable environmental protection policies and industrial development plans.

[0071] The step S200 includes the following sub-steps:

[0072] Step S201, screening a first driving factor according to the first subsidiary, wherein the first driving factor includes equipment efficiency, management efficiency, production scale and supply chain turnover times;

[0073] Step S202, calculating a first weight of a first driving factor, and constructing a first driving model according to the first weight. The calculation logic of the first weight includes:

[0074] Obtain the carbon dioxide emissions of the first subsidiary, perform weighted calculation on the carbon dioxide emissions of the first subsidiary to obtain the total emissions of the first subsidiary category, calculate the average of the total emissions of the first subsidiary category, record it as the first average, take the carbon dioxide emissions of the first subsidiary as the dependent variable, take equipment efficiency, management efficiency, production scale and supply chain turnover times as independent variables, calculate the weights corresponding to equipment efficiency, management efficiency, production scale and supply chain turnover times respectively through multiple regression analysis, record it as the first weight;

[0075] Step S203, screening the second driving factor according to the second sub-enterprise, the second driving factor corresponding to the industrial second sub-enterprise includes energy efficiency, manufacturing process duration and waste recycling efficiency, the second driving factor corresponding to the transportation second sub-enterprise includes fuel combustion efficiency and the number of vehicles, the second driving factor corresponding to the agricultural second sub-enterprise includes pesticide dosage and vegetation coverage, calculating the second weight of the second driving factor, constructing the second driving model according to the second weight, the calculation logic of the second weight includes:

[0076] Obtain the first emission of the second subsidiary, take the first emission of the second subsidiary as the dependent variable, take the second driving factor corresponding to the second subsidiary as the independent variable, and calculate the weights corresponding to the second driving factor corresponding to the second subsidiary through multiple regression analysis, which are recorded as second weights;

[0077] Step S204: obtaining a comprehensive driving model according to the first driving model and the second driving model.

[0078] In the specific implementation, through the analysis of the first subsidiary and the second subsidiary, the key driving factors affecting carbon dioxide emissions (such as equipment efficiency, management efficiency, etc.) are scientifically identified, which provides a basis for subsequent optimization. The multivariate regression analysis method is used to calculate the weight of each driving factor and quantify its impact on carbon dioxide emissions. Data support is provided to help enterprises formulate targeted emission reduction strategies, build the first driving model and the second driving model, form an operational management tool, and help enterprises systematically evaluate and improve their own emission status. By integrating the first driving model and the second driving model, a comprehensive driving model is formed, which helps to comprehensively consider the impact of various factors and improve the comprehensiveness and scientificity of decision-making. By focusing on the key factors affecting emissions, environmental protection measures can be implemented more effectively, helping to achieve low-carbon goals and promote sustainable development. The establishment of a comprehensive driving model supports enterprises to establish a dynamic monitoring mechanism, timely understand emission changes, and make corresponding adjustments.

[0079] The calculation logic of the first average value includes:

[0080] Get the first number as X i The carbon dioxide emissions corresponding to the first subsidiary of i The carbon dioxide emissions corresponding to the first sub-enterprises of the i-th category are weighted to obtain the total emissions of the first sub-enterprises, and the average of the total emissions of the first sub-enterprises is calculated, which is recorded as the first average. The first average is represented by the average of the carbon dioxide emissions of the first sub-enterprises of the i-th category;

[0081] The calculation expression of the first driving model is:

[0082]

[0083] Among them, P i is the first average value of the first subsidiary of the first category i, k t is the tth first driving factor, C t is the coefficient corresponding to the tth first driving factor, that is, the first weight, and m is the number of first driving factors;

[0084] The calculation expression of the second driving model is:

[0085]

[0086] Among them, Q ij The second number is x ij The first emission corresponding to the second subsidiary, G n is the nth second driving factor, l n is the coefficient corresponding to the nth second driving factor, that is, the second weight, and n is the number of second driving factors.

[0087] In specific implementation, the definition of the first average value and the first emission amount ensures an in-depth analysis of the emissions of specific categories of enterprises, provides reliable data for subsequent decision-making, and through scientific calculation and analysis, encourages enterprises to switch to more environmentally friendly production methods, achieve low-carbon economic transformation, and support the realization of sustainable development goals.

[0088] The calculation logic of the comprehensive driving model includes:

[0089] Obtain the first weight of the first driving model and the second weight of the second driving model, and according to the coefficient rule of multiple regression analysis, obtain that the sum of the first weight is 1 and the sum of the second weight is 1, use the independent variable of the first driving model and the independent variable of the second driving model as new independent variables of the comprehensive driving model, use half of the first weight of the first driving model and half of the second weight of the second driving model as new weights of the comprehensive driving model, construct the comprehensive driving model, and set the correction value to compensate for the error of the comprehensive driving model;

[0090] The setting logic of the correction value includes:

[0091] Obtain any first emission amount and a corresponding first average value, calculate the difference between the first emission amount and the corresponding first average value, record it as a first difference, traverse the first difference values, calculate the average value of the first difference values, take half of the average value of the first difference values, set half of the average value of the first difference values ​​as a correction value, perform weighted calculation on the correction value and the comprehensive driving model, and the correction value is a positive value, a negative value or zero;

[0092] The calculation expression of the compensated comprehensive driving model is:

[0093]

[0094] Among them, ε is the correction value.

[0095] In specific implementation, by integrating the independent variables of the first driving model and the second driving model into new independent variables of the comprehensive driving model, it is possible to more comprehensively consider multiple factors affecting emissions, improve the explanatory power and accuracy of the model, and use half of the first weight and the second weight as the new weight to ensure that the impact of factors from different sources on the model is balanced, thereby improving the reliability of the model. By setting correction values, dynamic adjustments can be made to the differences between model predictions and actual emissions, thereby improving the adaptability and accuracy of the model.

[0096] The acquisition logic of the first driving factor and the second driving factor includes:

[0097] Retrieve a survey database, input the source of carbon dioxide into the survey database, match survey data related to the source of carbon dioxide, automatically segment the text to obtain words through a word segmentation model, count the frequency of each word in the survey data through an unsupervised network learning model, set a word frequency threshold, traverse the word frequency, compare the word frequency with the word frequency threshold, when the word frequency is greater than the word frequency threshold, retain the word corresponding to the word frequency, otherwise, delete the word corresponding to the word frequency, extract semantic features of the retained words, the semantic features include scale features and industry features, set the retained words related to the scale features as the first driving factor, and set the words related to the industry features as the second driving factor.

[0098] In the specific implementation, information related to the source of carbon dioxide is input into the survey database to ensure that the extracted data is highly relevant, thereby improving the accuracy of the analysis results. The word segmentation model and unsupervised learning model are used to make the information extraction process efficient and automated, reducing the need for manual intervention. By counting the frequency of each word and comparing it with the threshold, it is ensured that the data finally retained are keywords that have a practical contribution to the analysis and reduce noise data. The word frequency threshold can be adjusted according to specific analysis needs to adapt to different research environments and ensure the flexibility and adaptability of the extracted information. The retained words extract scale characteristics and industry characteristics, providing a multi-dimensional perspective for subsequent analysis and making the model more explanatory. The words related to scale characteristics are set as the first driving factor, and the words related to industry characteristics are set as the second driving factor, making the classification of factors clearer and facilitating subsequent analysis and application. Combining the characteristics of two different dimensions, scale and industry, can comprehensively and in-depth analyze the driving factors of carbon dioxide emissions and promote the depth and breadth of research.

[0099] The step S300 includes the following sub-steps:

[0100] Step S301, obtaining the second number of the current second subsidiary enterprise;

[0101] Step S302, obtaining the current first average value of the current second subsidiary according to the compensated comprehensive driving model, obtaining the standard carbon dioxide emissions of the second subsidiary, and comparing the current first average value with the standard carbon dioxide emissions to obtain a comparison result, wherein the comparison result includes that the current first average value is greater than the standard carbon dioxide emissions, and the current first average value is less than or equal to the standard carbon dioxide emissions;

[0102] Step S303: formulating a driving factor adjustment decision according to the comparison result. The logic for formulating the driving factor adjustment decision includes:

[0103] Obtain a comparison result. When the comparison result is that the current first average value is less than or equal to the standard carbon dioxide emissions, set the driving factor adjustment decision to maintain the status quo. When the comparison result is that the current first average value is greater than the standard carbon dioxide emissions, calculate the difference between the current first average value and the standard carbon dioxide emissions, record it as the second difference, obtain a new weight of the comprehensive driving model, calculate the product of the new weight and the second difference, record it as the first product, set the first product as the change amount, and set the driving factor adjustment decision to reduce or increase the corresponding first driving factor and the corresponding second driving factor according to the first product.

[0104] In specific implementation, by obtaining the first average value of the current second subsidiary and comparing it with the standard carbon dioxide emissions, the company can monitor its own emissions in real time, help the company understand whether the current emission level meets environmental protection standards or exceeds the standard, and make timely adjustments. Based on the comparison results, dynamic driver adjustment decisions are made to ensure that the company's emission level can be continuously optimized. For subsidiaries that meet the standards, choose to maintain the status quo to avoid unnecessary waste of resources. For situations that exceed the standard, emissions are controlled and reduced by adjusting the driving factors. The "change amount" is set by multiplying the "new weight" and the "second difference", ensuring that the emission adjustment decision can accurately control the emission level and avoid large fluctuations, helping the company to operate stably. The entire adjustment process is based on automated models and algorithms, which reduces manual intervention and judgment bias, improves decision-making efficiency and accuracy, and manages carbon dioxide emissions more efficiently through this intelligent decision support tool.

[0105] The present invention uses clear classification standards to facilitate the identification and comparison of emissions from different enterprises, formulate targeted measures, provide accurate emission data for subsequent calculations and optimization, and improve the reliability of the model. By identifying and analyzing driving factors, we can more comprehensively understand the causes of emissions and provide a basis for decision-making. The integrated multi-level driving model enhances the adaptability and prediction capabilities to dynamic changes in carbon emissions, dynamically obtains current emission data, ensures timely grasp of the carbon emissions of enterprises, formulates accurate emission reduction strategies based on real-time data and model predictions, improves management efficiency, and realizes dynamic optimization of carbon emissions of urban enterprises, thereby effectively controlling and reducing carbon dioxide emissions and promoting the sustainable development of cities. It not only improves the scientificity and rationality of carbon emission management, but also provides data support and theoretical basis for urban policy making.

[0106] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. 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.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for dynamically optimizing urban carbon emissions through a digital twin model, characterized in that: The following steps are involved: Step S100, setting the primary standard and secondary standard for enterprise classification, performing a first classification on the enterprises in the city according to the primary standard to obtain a first sub-enterprise, assigning a first number to the first sub-enterprise, performing a second classification on the enterprises in the city according to the secondary standard to obtain a second sub-enterprise, assigning a second number to the second sub-enterprise, and obtaining the carbon dioxide emissions of the enterprises after the second number, which are recorded as the first emissions; Step S200, screening a first driving factor according to the first sub-enterprise, calculating a first weight of the first driving factor, constructing a first driving model according to the first weight, screening a second driving factor according to the second sub-enterprise, calculating a second weight of the second driving factor, constructing a second driving model according to the second weight, obtaining a comprehensive driving model according to the first driving model and the second driving model, and compensating the comprehensive driving model; Step S300, obtain the current second subsidiary, obtain the current carbon dioxide emissions of the current second subsidiary according to the compensated comprehensive driving model, obtain the standard carbon dioxide emissions of the second subsidiary, compare the current carbon dioxide emissions with the standard carbon dioxide emissions, and make a driving factor adjustment decision based on the comparison result.

2. A method for dynamically optimizing urban carbon emissions through a digital twin model as claimed in claim 1, characterized in that: The step S100 includes the following sub-steps: Step S101, setting the primary standard and secondary standard for enterprise classification, wherein the primary standard is set according to the enterprise size, and the secondary standard is divided according to the industry to which it belongs; The first-level standard includes large scale, medium scale and small scale. The enterprise scale is divided according to the number of employees. The first value and the second value are set as the number threshold. When the number of employees is greater than the first value, the first-level standard is set to large scale. When the number of employees is less than or equal to the first value and greater than the second value, the first-level standard is set to medium scale. When the number of employees is less than or equal to the second value, the first-level standard is set to small scale. The secondary standards include industry, transportation and agriculture; Step S102: Perform a first classification on the enterprises in the city according to the primary standard to obtain a first sub-enterprise, and assign a first number to the first sub-enterprise, wherein the first number is represented by X. i , where i is a natural number and i∈[1,3], the first subsidiary enterprise includes a large-scale first-level subsidiary enterprise, a medium-scale first-level subsidiary enterprise and a small-scale first-level subsidiary enterprise; Obtain the number of employees of the enterprise and compare it with the first-level standard. When the number of employees of the enterprise is large-scale, set the first subsidiary enterprise as a large-scale first-level subsidiary enterprise; when the number of employees of the enterprise is medium-scale, set the first subsidiary enterprise as a medium-scale first-level subsidiary enterprise; when the number of employees of the enterprise is small-scale, set the first subsidiary enterprise as a small-scale first-level subsidiary enterprise; Step S103, performing a second classification on the enterprises in the city according to the secondary standard to obtain a second sub-enterprise, and assigning a second number to the second sub-enterprise, wherein the second number corresponds to the first number, and the second number is represented by X ij , where j is a natural number and j∈[1,3], the second sub-enterprises include the second industrial sub-enterprises, the second transportation sub-enterprises and the second agricultural sub-enterprises; Step S104, obtain the carbon dioxide emissions of the second-numbered enterprises, calculate the average of the carbon dioxide emissions of the second-numbered enterprises, record it as the first average, calculate the second emissions based on the carbon dioxide emissions of the second-numbered enterprises, the second emissions represent the total carbon dioxide emissions of the city, and are obtained by weighted calculation of the carbon dioxide emissions of the second-numbered enterprises.

3. The method for dynamically optimizing urban carbon emissions through a digital twin model as claimed in claim 1, characterized in that: The step S200 includes the following sub-steps: Step S201, screening a first driving factor according to the first subsidiary, wherein the first driving factor includes equipment efficiency, management efficiency, production scale and supply chain turnover times; Step S202, calculating a first weight of a first driving factor, and constructing a first driving model according to the first weight. The calculation logic of the first weight includes: Obtain the carbon dioxide emissions of the first subsidiary, perform weighted calculation on the carbon dioxide emissions of the first subsidiary to obtain the total emissions of the first subsidiary category, calculate the average of the total emissions of the first subsidiary category, record it as the first average, take the carbon dioxide emissions of the first subsidiary as the dependent variable, take equipment efficiency, management efficiency, production scale and supply chain turnover times as independent variables, calculate the weights corresponding to equipment efficiency, management efficiency, production scale and supply chain turnover times respectively through multiple regression analysis, record it as the first weight; Step S203, screening the second driving factors according to the second sub-enterprise, the second driving factors corresponding to the second industrial sub-enterprise include energy efficiency, manufacturing process duration and waste recycling efficiency, the second driving factors corresponding to the second transportation sub-enterprise include fuel combustion efficiency and the number of vehicles, and the second driving factors corresponding to the second agricultural sub-enterprise include pesticide dosage and vegetation coverage, calculating the second weight of the second driving factor, constructing the second driving model according to the second weight, and the calculation logic of the second weight includes: Obtain the first emission of the second subsidiary, take the first emission of the second subsidiary as the dependent variable, take the second driving factor corresponding to the second subsidiary as the independent variable, and calculate the weights corresponding to the second driving factor corresponding to the second subsidiary through multiple regression analysis, which are recorded as second weights; Step S204: obtaining a comprehensive driving model according to the first driving model and the second driving model.

4. A method for dynamically optimizing urban carbon emissions through a digital twin model as claimed in claim 3, characterized in that: The calculation logic of the first average value includes: Get the first number as X i The carbon dioxide emissions corresponding to the first subsidiary of i The carbon dioxide emissions corresponding to the first sub-enterprises of the i-th category are weighted to obtain the total emissions of the first sub-enterprises, and the average of the total emissions of the first sub-enterprises is calculated, which is recorded as the first average. The first average is represented by the average of the carbon dioxide emissions of the first sub-enterprises of the i-th category; The calculation logic of the first emission amount includes: Get the second number as X ij The carbon dioxide emissions corresponding to the second subsidiary of ij The carbon dioxide emissions corresponding to the second subsidiaries are weightedly calculated to obtain the total emissions of the second sub-enterprises, and the average value of the total emissions of the second sub-enterprises is calculated and recorded as the first emissions. The first emissions represent the average value of the carbon dioxide emissions of the first subsidiaries of the i-th category and the second subsidiaries of the j-th category.

5. The method for dynamically optimizing urban carbon emissions through a digital twin model as claimed in claim 1, characterized in that: The calculation expression of the first driving model is: Among them, P i is the first average value of the first subsidiary of the first category i, k t is the tth first driving factor, C t is the coefficient corresponding to the tth first driving factor, that is, the first weight, and m is the number of first driving factors; The calculation expression of the second driving model is: Among them, Qij is the first emission corresponding to the second subsidiary with the second number xij, Gn is the nth second driving factor, ln is the nth n The coefficient corresponding to the second driving factor is the second weight, n is the number of the second driving factors.

6. A method for dynamically optimizing urban carbon emissions through a digital twin model as claimed in claim 3, characterized in that: The calculation logic of the comprehensive driving model includes: Obtain the first weight of the first driving model and the second weight of the second driving model, and according to the coefficient rule of multiple regression analysis, obtain that the sum of the first weight is 1 and the sum of the second weight is 1, use the independent variable of the first driving model and the independent variable of the second driving model as new independent variables of the comprehensive driving model, use half of the first weight of the first driving model and half of the second weight of the second driving model as new weights of the comprehensive driving model, construct the comprehensive driving model, and set the correction value to compensate for the error of the comprehensive driving model; The setting logic of the correction value includes: Obtain any first emission amount and a corresponding first average value, calculate the difference between the first emission amount and the corresponding first average value, record it as a first difference, traverse the first difference values, calculate the average value of the first difference values, take half of the average value of the first difference values, set half of the average value of the first difference values ​​as a correction value, perform weighted calculation on the correction value and the comprehensive driving model, and the correction value is a positive value, a negative value or zero; The calculation expression of the compensated comprehensive driving model is: Among them, ε is the correction value.

7. A method for dynamically optimizing urban carbon emissions through a digital twin model as claimed in claim 6, characterized in that: The acquisition logic of the first driving factor and the second driving factor includes: Retrieve a survey database, input the source of carbon dioxide into the survey database, match survey data related to the source of carbon dioxide, automatically segment the text to obtain words through a word segmentation model, count the frequency of each word in the survey data through an unsupervised network learning model, set a word frequency threshold, traverse the word frequency, compare the word frequency with the word frequency threshold, when the word frequency is greater than the word frequency threshold, retain the word corresponding to the word frequency, otherwise, delete the word corresponding to the word frequency, extract semantic features of the retained words, the semantic features include scale features and industry features, set the retained words related to the scale features as the first driving factor, and set the words related to the industry features as the second driving factor.

8. The method for dynamically optimizing urban carbon emissions through a digital twin model according to claim 1, characterized in that: The step S300 includes the following sub-steps: Step S301, obtaining the second number of the current second subsidiary enterprise; Step S302, obtaining the current first average value of the current second subsidiary according to the compensated comprehensive driving model, obtaining the standard carbon dioxide emissions of the second subsidiary, and comparing the current first average value with the standard carbon dioxide emissions to obtain a comparison result, wherein the comparison result includes that the current first average value is greater than the standard carbon dioxide emissions, and the current first average value is less than or equal to the standard carbon dioxide emissions; Step S303: formulating a driving factor adjustment decision according to the comparison result. The logic for formulating the driving factor adjustment decision includes: Obtain a comparison result. When the comparison result is that the current first average value is less than or equal to the standard carbon dioxide emissions, set the driving factor adjustment decision to maintain the status quo. When the comparison result is that the current first average value is greater than the standard carbon dioxide emissions, calculate the difference between the current first average value and the standard carbon dioxide emissions, record it as the second difference, obtain a new weight of the comprehensive driving model, calculate the product of the new weight and the second difference, record it as the first product, set the first product as the change amount, and set the driving factor adjustment decision to reduce or increase the corresponding first driving factor and the corresponding second driving factor according to the first product.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the method for dynamically optimizing urban carbon emissions through a digital twin model as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements the method of dynamically optimizing urban carbon emissions through a digital twin model as described in any one of claims 1 to 8.

Images