Multi-dimensional carbon management performance visual evaluation system and method

Abstract

The invention relates to the technical field of energy management, and discloses a multi-dimensional carbon management performance visual evaluation system and method.The system comprises a data acquisition and integration module, a performance calculation and analysis module and a visual rendering and output module, and the system and the method are used for evaluating the performance of carbon emission by acquiring carbon emission data, management performance index data and environmental influence factor data. Generating a standardized carbon management data set based on data preprocessing, performing multi-dimensional performance index calculation processing according to the data set to generate carbon management performance evaluation index data, and performing iterative optimization on performance short board data by applying an artificial intelligence optimization algorithm to generate optimized carbon management performance data; the method comprises the following steps: constructing a dynamic visual evaluation model, calling the model to perform visual rendering to generate an interactive carbon management performance visual report, and finally outputting optimization suggestion data according to the report; according to the method, the distortion risk of a carbon management decision is reduced, the scientificity and objectivity of performance scoring are improved, and the accuracy and timeliness of carbon management strategy optimization are improved.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and specifically to a multi-dimensional carbon management performance visualization evaluation system and method. Background Art

[0002] Energy management is a general term for the scientific planning, organization, inspection, control and supervision of the entire process of energy production, distribution, conversion and consumption. It includes: formulating correct energy development policies and energy-saving policies, continuously improving energy planning, energy regulations, and energy control systems, arranging the production and operation of industrial energy and domestic energy, strengthening energy equipment management, timely carrying out technical transformation and updating of boilers, industrial kilns, and various electrical appliances, improving energy utilization rate, implementing energy quota management, calculating indicators of effective energy consumption and process loss, approving various energy consumption quotas at all levels, and implementing energy consumption quotas to workshops, work teams and individuals through economic responsibility systems and reward and punishment systems, urging enterprises to reach advanced energy consumption levels, regularly inspecting key enterprises, key projects and key equipment with high energy consumption, continuously conducting technical analysis of the degree of effective energy utilization, establishing and improving energy management systems, forming an energy management network that combines professional management with mass management, educating employees to establish energy-saving awareness, and continuously strengthening measurement supervision, standard supervision and statistical supervision of energy consumption.

[0003] Energy consumption is one of the main sources of carbon emissions. Currently, because the carbon management process involves the interaction of multi-source heterogeneous data, the basic carbon emission data collection method relied upon when conducting comprehensive carbon performance evaluation has limitations, and it is impossible to verify in real time whether the measurement accuracy of the monitoring equipment is offset. If there is a systematic deviation in the data collected by the equipment, it may lead to distortion of the carbon accounting results and the reliability of the benchmark data cannot be guaranteed.

[0004] Therefore, a multi-dimensional carbon management performance visualization evaluation system and method are proposed to solve the above problems. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a multi-dimensional carbon management performance visualization evaluation system and method, which solves the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: a multi-dimensional carbon management performance visualization evaluation system and method, the method comprising the following steps: S1. Collect multi-dimensional carbon management data, including carbon emissions data, management performance indicator data, and environmental impact factor data; S2. Performing data preprocessing based on the carbon emission data, the management performance indicator data, and the environmental impact factor data to generate a standardized carbon management data set; S3. Calculate and process multi-dimensional performance indicators based on the standardized carbon management data set to generate carbon management performance evaluation indicator data; S4. Performing performance optimization analysis and processing based on the carbon management performance evaluation indicator data to generate optimized carbon management performance data; S5. Constructing a visualization model based on the optimized carbon management performance data to generate a dynamic visualization evaluation model; S6. Calling the dynamic visualization evaluation model to perform carbon management performance visualization rendering processing to generate a carbon management performance visualization report; S7. Output and process evaluation results based on the carbon management performance visualization report to generate carbon management performance optimization recommendation data; Preferably, said S1 comprises the following steps: S11. Collect real-time carbon emission data of enterprises and regions through the IoT sensor network, including carbon dioxide emissions, methane emissions, and nitrous oxide emissions, and generate a carbon emission dataset; S12. Collect management performance indicator data through the management information system, including energy efficiency data, resource recycling rate data, and low-carbon technology application rate data, and generate a management performance indicator data set; S13. Collect data on environmental impact factors through the environmental monitoring platform, including climate condition data, geographical location data, and socioeconomic data, and generate an environmental impact factor dataset.

[0007] Preferably, said S2 comprises the following steps: S21. Import the generated carbon emission dataset, the management performance indicator dataset, and the environmental impact factor dataset into the carbon management cloud platform, use a data cleaning algorithm to remove outliers and missing values, and generate a preliminary integrated dataset; S22. Perform data normalization based on the preliminary integrated data set, apply a minimum-maximum scaling algorithm to convert data of different dimensions into a unified dimension, and generate a standardized carbon management data set, wherein the normalization range is 0 to 1.

[0008] Preferably, said S3 comprises the following steps: S31. Acquire the standardized carbon management dataset; S32. Input the standardized carbon management data set into a multi-dimensional performance evaluation model, calculate environmental dimension performance indicators, economic dimension performance indicators, and social dimension performance indicators, and generate carbon management performance evaluation indicator data; Environmental performance indicators include the normalized carbon intensity index, which is calculated as follows: ; ; in, is the normalized environmental performance score, dimensionless, with a value range of [0,1], a threshold greater than 0.8 for excellent, 0.6-0.8 for good, and less than 0.6 for poor. is the original carbon intensity index, with the unit of kg / 10,000 yuan, is the total carbon dioxide emissions in tons, is the gross domestic product, in ten thousand yuan. is the preset maximum carbon intensity threshold, with the unit of kg / 10,000 yuan and a typical value of 1000. It is the preset minimum carbon intensity threshold, with the unit of kg / 10,000 yuan and a typical value of 200. The economic dimension performance indicators include the normalized carbon cost-benefit ratio, and the social dimension performance indicators include the community participation index, all of which are converted to the [0,1] interval using the same normalization logic.

[0009] Preferably, said S4 comprises the following steps: S41. Performing performance deviation analysis based on the carbon management performance evaluation indicator data to identify performance shortcoming data; S42. Applying an artificial intelligence optimization algorithm to iteratively optimize the performance shortcoming data to generate optimized carbon management performance data; The artificial intelligence optimization algorithm uses a genetic algorithm, and the fitness function is: ; Constraints: ; in, is the normalized fitness value, dimensionless, range [0,1], optimization target threshold , is the normalized environmental performance score, is the normalized economic performance score, is the normalized social performance score, , , is the dynamic weight coefficient, dimensionless, with an initial value of 0.4 / 0.3 / 0.3, which is adaptively adjusted during iteration, and the optimization goal is to maximize Value, when Output optimized carbon management performance data in real time.

[0010] Preferably, the S5 comprises the following steps: S51. Performing visualization parameter mapping processing based on the optimized carbon management performance data, mapping performance indicators into visualization elements, including color coding, chart types, and dynamic interactive controls; S52. Construct a dynamic visualization evaluation model based on the mapped visualization elements, wherein the model includes a three-dimensional heat map, a time series line graph, and a geographic space distribution map, and generate a model configuration file.

[0011] Preferably, the S6 comprises the following steps: S61, calling the dynamic visual evaluation model and the model configuration file to initialize the data rendering engine; S62. Rendering the optimized carbon management performance data into an interactive visualization interface in real time based on a rendering engine to generate a carbon management performance visualization report, wherein the report supports multi-dimensional data drilling and dynamic parameter adjustment.

[0012] Preferably, the S7 comprises the following steps: S71. Perform performance score generation processing based on the carbon management performance visualization report and output carbon management performance score data; S72. Perform optimization suggestion reasoning processing based on the performance score data, and apply a rule engine to generate carbon management performance optimization suggestion data, including technology upgrade suggestions, management strategy adjustment suggestions, and policy compliance suggestions.

[0013] Preferably, the method further comprises the following steps: S8. Perform predictive analysis based on the carbon management performance optimization suggestion data to generate a carbon management performance forecast report; Wherein, S8 includes the following steps: S81. Obtain the carbon management performance optimization suggestion data and extract key performance parameters, including environmental dimension optimization parameters, economic dimension optimization parameters, and social dimension optimization parameters; S82. Apply a time series prediction model to simulate future trends of the key performance parameters to generate a predicted performance data set, wherein the time series prediction model includes an ARIMA model and an LSTM neural network, and the prediction period is 1-5 years; S83. Perform risk assessment based on the predicted performance data set to identify potential performance risk data, including technical implementation risk, policy compliance risk, and market volatility risk; S84. Integrate the predicted performance data set and the potential performance risk data to generate a carbon management performance forecast report, wherein the report includes a visual forecast chart and risk warning prompts.

[0014] Preferably, the system includes a data collection and integration module, a performance calculation and analysis module, and a visualization rendering and output module; The data collection and integration module includes a carbon emission data collection unit, a management performance data collection unit, and an environmental factor collection unit; the carbon emission data collection unit collects carbon emission data in real time through Internet of Things devices; the management performance data collection unit collects management performance indicator data through the enterprise resource planning system; and the environmental factor collection unit collects environmental impact factor data through a satellite remote sensing system. The performance calculation and analysis module includes a data preprocessing unit, a multi-dimensional indicator calculation unit, and a performance optimization unit; the data preprocessing unit performs cleaning and normalization based on the collected data; the multi-dimensional indicator calculation unit calculates environmental, economic, and social performance indicators based on standardized data; and the performance optimization unit applies AI algorithms to optimize performance data. The visualization rendering and output module includes a model construction unit, a rendering engine unit and a report generation unit; the model construction unit constructs a dynamic visualization model based on the optimization data; the rendering engine unit calls the model to perform real-time data rendering; and the report generation unit outputs an interactive visualization report and optimization suggestions.

[0015] Compared with the existing technology, the present invention provides a multi-dimensional carbon management performance visualization evaluation system and method, which has the following beneficial effects: 1. In this invention, by formulating carbon emission measurement accuracy verification rules and setting differentiated measurement standards for different industries, the accuracy of multi-source data collection is guaranteed. At the same time, the measurement deviation degree of the monitoring equipment is verified in real time, which can dynamically identify whether there is a systematic deviation in the data collected by the equipment, ensure the reliability of carbon accounting benchmark data, and reduce the risk of distortion in carbon management decisions. 2. In the present invention, by calculating the weight balance value of indicators in the environmental, economic, and social dimensions, it is possible to determine in real time whether the performance score deviates from the actual management level, so that the system can automatically correct the imbalance problem of the model framework. In addition, when the weight distribution is abnormal, the dimension parameter weights can be adjusted in real time according to the preset optimization goals, ensuring that the evaluation model dynamically adapts to complex management scenarios and improving the scientificity and objectivity of the performance score.

[0016] 3. In this invention, by analyzing the correlation between multi-dimensional performance indicators in a hierarchical manner, the performance shortcomings of management entities at different levels are located in real time. The optimization strategy library is automatically matched according to the characteristics of the shortcomings to generate decision-making suggestions. This enables the system to achieve cross-level and cross-dimensional penetrating analysis, avoids the problem of delayed strategy formulation caused by static reports, and improves the accuracy and timeliness of carbon management strategy optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the architecture of the multi-dimensional carbon management performance visualization evaluation system of the present invention; Figure 2This is a flowchart of the steps of the multi-dimensional carbon management performance visual evaluation method of the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] See also Figure 1-Figure 2 The specific implementation of the multi-dimensional carbon management performance visualization evaluation system and method is as follows: The method comprises the following steps: S1. Collect multi-dimensional carbon management data, including carbon emissions data, management performance indicator data, and environmental impact factor data; S2. Preprocess the data based on carbon emission data, management performance indicator data, and environmental impact factor data to generate a standardized carbon management data set; Preprocessing includes unified conversion of carbon emission equivalents and dimensional normalization, specifically: Carbon emission equivalent conversion formula: ; Dimensional normalization formula: ; Constraints: ; in, is the total carbon emission equivalent, in tons of CO2 equivalent, is the global warming potential of the ith greenhouse gas, dimensionless, typical values: CO2=1, CH4=28, N2O=265, is the emission of greenhouse gas type i, in tons, is the normalized carbon emission equivalent, dimensionless, range [0,1], The preset industry minimum threshold is in tons of CO2 equivalent, with a typical value of 500. The preset industry maximum threshold is expressed in tons of CO2 equivalent, with a typical value of 50,000. S3. Calculate and process multi-dimensional performance indicators based on the standardized carbon management data set to generate carbon management performance evaluation indicator data; S4. Perform performance optimization analysis and processing based on carbon management performance evaluation indicator data to generate optimized carbon management performance data; S5. Build and process a visualization model based on the optimized carbon management performance data to generate a dynamic visualization evaluation model; S6. Calling the dynamic visualization evaluation model to perform carbon management performance visualization rendering processing and generate a carbon management performance visualization report; S7. Output and process evaluation results based on the carbon management performance visualization report to generate carbon management performance optimization recommendation data; S11. Collect real-time carbon emission data of enterprises and regions through the IoT sensor network, including carbon dioxide emissions, methane emissions, and nitrous oxide emissions, and generate a carbon emission dataset; S12. Collect management performance indicator data through the management information system, including energy efficiency data, resource recycling rate data, and low-carbon technology application rate data, and generate a management performance indicator data set; S13. Collect environmental impact factor data through the environmental monitoring platform, including climate condition data, geographical location data, and socioeconomic data, and generate an environmental impact factor data set; S21. Import the generated carbon emission dataset, management performance indicator dataset, and environmental impact factor dataset into the carbon management cloud platform, use a data cleaning algorithm to remove outliers and missing values, and generate a preliminary integrated dataset; S22. Perform data normalization based on the preliminary integrated data set, apply the minimum-maximum scaling algorithm to convert data of different dimensions into a unified dimension, and generate a standardized carbon management data set; Missing value filling and normalization processing include: Missing value weighted filling formula: ; Weight: ; Dimensional normalization formula: ; Range ; in, Fill the missing values ​​with the result, dimensionless, is the value of the adjacent k-th data point, The data point spacing < <...< , threshold =5, is an exponential decay weight, and the constraint > >...> , is the normalized value, the range is [0,1], the threshold is greater than 0.8, it is good, and less than 0.4 is bad. is the minimum value of the data feature, is the maximum value of the data feature; S31. Obtain standardized carbon management data sets; S32. Input the standardized carbon management data set into the multi-dimensional performance evaluation model, calculate the environmental dimension performance indicators, economic dimension performance indicators, and social dimension performance indicators, and generate carbon management performance evaluation indicator data; Environmental performance indicators include the normalized carbon intensity index, which is calculated as follows: ; ; in, is the normalized environmental performance score, dimensionless, with a value range of [0,1], a threshold greater than 0.8 for excellent, 0.6-0.8 for good, and less than 0.6 for poor. is the original carbon intensity index, with the unit of kg / 10,000 yuan, is the total carbon dioxide emissions in tons, is the gross domestic product, in ten thousand yuan. is the preset maximum carbon intensity threshold, with the unit of kg / 10,000 yuan and a typical value of 1000. is the preset minimum carbon intensity threshold, with the unit of kg / 10,000 yuan and a typical value of 200. The economic dimension performance indicators include the normalized carbon cost-benefit ratio, and the social dimension performance indicators include the community participation index. Both are converted to the [0,1] interval using the same normalization logic; S41. Conduct performance deviation analysis based on carbon management performance evaluation indicator data to identify performance shortcomings; S42. Apply artificial intelligence optimization algorithms to iteratively optimize performance shortcoming data to generate optimized carbon management performance data; The artificial intelligence optimization algorithm uses a genetic algorithm, and the fitness function is: ; Constraints: ; in, is the normalized fitness value, dimensionless, range [0,1], optimization target threshold , is the normalized environmental performance score, is the normalized economic performance score, is the normalized social performance score, , , is the dynamic weight coefficient, dimensionless, with an initial value of 0.4 / 0.3 / 0.3, which is adaptively adjusted during iteration, and the optimization goal is to maximize Value, when Output optimized carbon management performance data in real time; S51. Perform visualization parameter mapping processing based on the optimized carbon management performance data, and map the performance indicators into visualization elements; The color coding conversion uses a double threshold normalization mechanism: ; in, The red, green and blue color values ​​are 0-255, is the environmental performance score, dimensionless [0,1], is the warning threshold, with a typical value of 0.4. <0.4 when mandatory =255, red alert, is an excellent threshold, with a typical value of 0.8. >0.8 when mandatory =255, green excellent; when ∈[0.4,0.8]: Gradually from 255 to 0, From 0 to 255, when <0.4: pure red, =255, =0, when >0.8: pure green, =0, =255; S52. Construct a dynamic visualization evaluation model based on the mapped visualization elements, the model including a three-dimensional heat map, a time series line graph, and a geographic space distribution map, and generate a model configuration file; S61, calling the dynamic visualization evaluation model and model configuration file to initialize the data rendering engine; S62. Based on the rendering engine, the optimized carbon management performance data is rendered in real time into an interactive visualization interface to generate a carbon management performance visualization report, wherein the report supports multi-dimensional data drilling and dynamic parameter adjustment; S71. Generate and process performance scores based on the carbon management performance visualization report, and output carbon management performance score data; S72. Perform optimization suggestion reasoning based on performance score data and apply a rule engine to generate carbon management performance optimization suggestion data; It is recommended to use the normalized weight formula for priority calculation: ; ; ; constraint: ; in, is the normalized priority score, with a value range of [0,1], is the normalized impact factor, with a value range of [0,1], To normalize the feasibility of implementation, the value range is [0,1], is the dynamic weight coefficient, , initial value =0.7, =0.3; when It is implemented urgently, marked in red. When the plan is implemented, it is marked in yellow. When the implementation is suspended, it is marked in gray; S8. Perform predictive analysis and processing based on the carbon management performance optimization recommendation data to generate a carbon management performance forecast report; Wherein, S8 includes the following steps: S81. Obtain carbon management performance optimization recommendation data and extract key performance parameters, including environmental dimension optimization parameters, economic dimension optimization parameters, and social dimension optimization parameters; S82. Apply the time series forecasting model to simulate the future trends of key performance parameters and generate a forecast performance data set; The prediction confidence is calculated using the normalized formula: ; ; constraint: ; in, is the normalized confidence, with a value range of [0,1], is the actual value of period t, in tons of CO2 equivalent, is the forecast value for period t, in tons of CO2 equivalent, is the data fluctuation range, is the normalization coefficient, fixed value 2, is the number of verification periods, the threshold =12 months; when When the confidence level is high, the decision is reliable. When is medium confidence, reference decision, when When the confidence level is low, it needs to be reviewed; S83. Conduct risk assessment based on the predicted performance data set to identify potential performance risk data, including technical implementation risk, policy compliance risk, and market volatility risk; S84. Integrate the predicted performance data set and potential performance risk data to generate a carbon management performance forecast report, which includes visual forecast charts and risk warning prompts.

[0020] The system includes data collection and integration module, performance calculation and analysis module, and visualization rendering and output module; The data collection and integration module includes a carbon emission data collection unit, a management performance data collection unit, and an environmental factor collection unit. The carbon emission data collection unit collects carbon emission data in real time through IoT devices. The management performance data collection unit collects management performance indicator data through the enterprise resource planning system. The environmental factor collection unit collects environmental impact factor data through a satellite remote sensing system. The performance calculation and analysis module includes a data preprocessing unit, a multi-dimensional indicator calculation unit, and a performance optimization unit. The data preprocessing unit performs cleaning and normalization based on the collected data. The multi-dimensional indicator calculation unit calculates environmental, economic, and social performance indicators based on standardized data. The performance optimization unit applies AI algorithms to optimize performance data. The visualization rendering and output module includes a model building unit, a rendering engine unit and a report generation unit; the model building unit builds a dynamic visualization model based on the optimization data; the rendering engine unit calls the model for real-time data rendering; and the report generation unit outputs interactive visualization reports and optimization suggestions.

[0021] The operating steps of the multi-dimensional carbon management performance visualization evaluation system and method are as follows: Intelligent collection of multi-source data: Dynamic capture of carbon emissions data: Deploy IoT sensors to monitor direct emission sources in real time and connect to energy management systems to collect indirect emissions data, covering all types of greenhouse gases; Integration of management performance indicators: extracting energy efficiency parameters from the enterprise resource planning system, integrating resource recycling rate indicators from the supply chain management platform, and obtaining third-party certified carbon footprint report data; Synchronization of environmental influencing factors: Linking the meteorological database to capture climate parameters such as temperature and humidity, parsing the location characteristic data in the geographic information system, and integrating the industrial distribution information of the socio-economic database.

[0022] Dynamic preprocessing and normalization; Data cleaning and repair: Automatically identify outliers and use weighted filling of adjacent data to repair missing data caused by equipment failure based on spatial correlation; Multi-dimensional dimensional unification: Convert different gas emissions into standard carbon dioxide equivalents, set benchmark values ​​according to industry characteristics to achieve cross-scale data comparability, and compress all indicators to the range of zero to one to eliminate dimensional differences.

[0023] Intelligent Performance Modeling: Construction of a three-dimensional evaluation system: environmental dimension: quantifying carbon emission intensity per unit of economic output; economic dimension: calculating the ratio of emission reduction costs to economic benefits; social dimension: assessing community participation and public satisfaction; Adaptive weighting mechanism: Initially set the weight distribution dominated by the environmental dimension, and dynamically adjust the influence ratio of each dimension based on real-time feedback.

[0024] Artificial Intelligence Optimization Engine: Performance shortcoming diagnosis: Identify key dimension indicators that are below industry benchmarks and locate high-carbon emission processes or management loopholes; Dynamic optimization decision-making: Genetic algorithms are used to generate multi-objective optimization solutions and output recommendations for technology upgrades and management strategy adjustments.

[0025] Visual interactive decision making: Dynamic model construction: Mapping performance data into a red-green gradient warning color spectrum, generating a three-dimensional heat map to present spatial distribution characteristics; Interactive report output: supports drilling down to analyze performance details of any dimension and automatically marks high-priority implementation recommendations.

[0026] Predictive trend simulation: Long-term trend prediction: training a time series forecasting model based on historical data to simulate the carbon management performance trajectory over the next three to five years; Risk warning mechanism: Quantify the confidence level of prediction results and output them in a graded manner, triggering a manual review process for low-confidence predictions.

[0027] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0028] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A multi-dimensional carbon management performance visualization evaluation method, characterized by: The method comprises the following steps: S1. Collect multi-dimensional carbon management data, including carbon emissions data, management performance indicator data, and environmental impact factor data; S2. Performing data preprocessing based on the carbon emission data, the management performance indicator data, and the environmental impact factor data to generate a standardized carbon management data set; S3. Calculate and process multi-dimensional performance indicators based on the standardized carbon management data set to generate carbon management performance evaluation indicator data; S4. Performing performance optimization analysis and processing based on the carbon management performance evaluation indicator data to generate optimized carbon management performance data; S5. Constructing a visualization model based on the optimized carbon management performance data to generate a dynamic visualization evaluation model; S6. Calling the dynamic visualization evaluation model to perform carbon management performance visualization rendering processing to generate a carbon management performance visualization report; S7. Output and process the evaluation results based on the carbon management performance visualization report to generate carbon management performance optimization recommendation data.

2. The multi-dimensional carbon management performance visual evaluation method according to claim 1 is characterized by: Said S1 comprises the following steps: S11. Collect real-time carbon emission data of enterprises and regions through the IoT sensor network, including carbon dioxide emissions, methane emissions, and nitrous oxide emissions, and generate a carbon emission dataset; S12. Collect management performance indicator data through the management information system, including energy efficiency data, resource recycling rate data, and low-carbon technology application rate data, and generate a management performance indicator data set; S13. Collect data on environmental impact factors through the environmental monitoring platform, including climate condition data, geographical location data, and socioeconomic data, and generate an environmental impact factor dataset.

3. The multi-dimensional carbon management performance visual evaluation method according to claim 2, characterized in that: The S2 comprises the following steps: S21. Import the generated carbon emission dataset, the management performance indicator dataset, and the environmental impact factor dataset into the carbon management cloud platform, use a data cleaning algorithm to remove outliers and missing values, and generate a preliminary integrated dataset; S22. Perform data normalization based on the preliminary integrated data set, apply a minimum-maximum scaling algorithm to convert data of different dimensions into a unified dimension, and generate a standardized carbon management data set, wherein the normalization range is 0 to 1.

4. The multi-dimensional carbon management performance visual evaluation method according to claim 1, characterized in that: The S3 includes the following steps: S31. Acquire the standardized carbon management dataset; S32. Input the standardized carbon management data set into a multi-dimensional performance evaluation model, calculate environmental dimension performance indicators, economic dimension performance indicators, and social dimension performance indicators, and generate carbon management performance evaluation indicator data; Environmental performance indicators include the normalized carbon intensity index, which is calculated as follows: ； ； in, is the normalized environmental performance score, dimensionless, with a value range of [0,1], a threshold greater than 0.8 for excellent, 0.6-0.8 for good, and less than 0.6 for poor. is the original carbon intensity index, with the unit of kg / 10,000 yuan, is the total carbon dioxide emissions in tons, is the gross domestic product, in ten thousand yuan. is the preset maximum carbon intensity threshold, with the unit of kg / 10,000 yuan and a typical value of 1000. It is the preset minimum carbon intensity threshold, with the unit of kg / 10,000 yuan and a typical value of 200. The economic dimension performance indicators include the normalized carbon cost-benefit ratio, and the social dimension performance indicators include the community participation index, all of which are converted to the [0,1] interval using the same normalization logic.

5. The multi-dimensional carbon management performance visual evaluation method according to claim 1 is characterized by: The S4 comprises the following steps: S41. Performing performance deviation analysis based on the carbon management performance evaluation indicator data to identify performance shortcoming data; S42. Applying an artificial intelligence optimization algorithm to iteratively optimize the performance shortcoming data to generate optimized carbon management performance data; The artificial intelligence optimization algorithm uses a genetic algorithm, and the fitness function is: ； Constraints: ； in, is the normalized fitness value, dimensionless, range [0,1], optimization target threshold , is the normalized environmental performance score, is the normalized economic performance score, is the normalized social performance score, , , is the dynamic weight coefficient, dimensionless, with an initial value of 0.4 / 0.3 / 0.3, which is adaptively adjusted during iteration, and the optimization goal is to maximize Value, when Output optimized carbon management performance data in real time.

6. The multi-dimensional carbon management performance visual evaluation method according to claim 1, characterized in that: The S5 comprises the following steps: S51. Performing visualization parameter mapping processing based on the optimized carbon management performance data, mapping performance indicators into visualization elements, including color coding, chart types, and dynamic interactive controls; S52. Construct a dynamic visualization evaluation model based on the mapped visualization elements, wherein the model includes a three-dimensional heat map, a time series line graph, and a geographic space distribution map, and generate a model configuration file.

7. The multi-dimensional carbon management performance visual evaluation method according to claim 6, characterized in that: The S6 comprises the following steps: S61, calling the dynamic visual evaluation model and the model configuration file to initialize the data rendering engine; S62. Rendering the optimized carbon management performance data into an interactive visualization interface in real time based on a rendering engine to generate a carbon management performance visualization report, wherein the report supports multi-dimensional data drilling and dynamic parameter adjustment.

8. The multi-dimensional carbon management performance visual evaluation method according to claim 1, characterized in that: The S7 comprises the following steps: S71. Perform performance score generation processing based on the carbon management performance visualization report and output carbon management performance score data; S72. Perform optimization suggestion reasoning processing based on the performance score data, and apply a rule engine to generate carbon management performance optimization suggestion data, including technology upgrade suggestions, management strategy adjustment suggestions, and policy compliance suggestions.

9. The multi-dimensional carbon management performance visual evaluation method according to claim 1, characterized in that: The method further comprises the steps of: S8. Perform predictive analysis based on the carbon management performance optimization suggestion data to generate a carbon management performance forecast report; Wherein, S8 includes the following steps: S81. Obtain the carbon management performance optimization suggestion data and extract key performance parameters, including environmental dimension optimization parameters, economic dimension optimization parameters, and social dimension optimization parameters; S82. Apply a time series prediction model to simulate future trends of the key performance parameters to generate a predicted performance data set, wherein the time series prediction model includes an ARIMA model and an LSTM neural network, and the prediction period is 1-5 years; S83. Perform risk assessment based on the predicted performance data set to identify potential performance risk data, including technical implementation risk, policy compliance risk, and market volatility risk; S84. Integrate the predicted performance data set and the potential performance risk data to generate a carbon management performance forecast report, wherein the report includes a visual forecast chart and risk warning prompts.

10. A multi-dimensional carbon management performance visualization evaluation system, for implementing the multi-dimensional carbon management performance visualization evaluation method according to any one of claims 1 to 9, characterized in that: The system includes a data collection and integration module, a performance calculation and analysis module, and a visualization rendering and output module; The data collection and integration module includes a carbon emission data collection unit, a management performance data collection unit and an environmental factor collection unit; The carbon emission data collection unit collects carbon emission data in real time through the Internet of Things device; the management performance data collection unit collects management performance indicator data through the enterprise resource planning system; the environmental factor collection unit collects environmental impact factor data through the satellite remote sensing system; The performance calculation and analysis module includes a data preprocessing unit, a multi-dimensional indicator calculation unit, and a performance optimization unit; the data preprocessing unit performs cleaning and normalization based on the collected data; the multi-dimensional indicator calculation unit calculates environmental, economic, and social performance indicators based on standardized data; and the performance optimization unit applies AI algorithms to optimize performance data. The visualization rendering and output module includes a model construction unit, a rendering engine unit and a report generation unit; the model construction unit constructs a dynamic visualization model based on the optimization data; the rendering engine unit calls the model to perform real-time data rendering; and the report generation unit outputs an interactive visualization report and optimization suggestions.

Images