Index identification method, device and system for enterprise low-carbon evaluation and medium

Abstract

The invention relates to the technical field of enterprise low-carbon evaluation, and provides an index identification method, device and system for enterprise low-carbon evaluation and a medium. According to the implementation scheme, low-carbon scores of all enterprises are calculated according to index values and index weights of all evaluation indexes; performing sensitivity analysis on each evaluation index by taking each enterprise low-carbon score and each index value as input variables to obtain a first-order sensitivity index and a second-order sensitivity index of each evaluation index; performing sensitivity estimation on each evaluation index through a Monte Carlo method to obtain a first-order sensitivity estimation value of each evaluation index; determining a first-order sensitivity comprehensive index of each evaluation index based on the first-order sensitivity index and the first-order sensitivity estimated value of each evaluation index; and determining a target evaluation index based on the first-order sensitivity comprehensive index and the second-order sensitivity index of each evaluation index. According to the embodiment of the invention, the recognition accuracy of key influence indexes in enterprise low-carbon evaluation can be improved.

Description

Technical Field

[0001] This invention relates to the field of enterprise low-carbon assessment technology, and in particular to a method, apparatus, system and medium for identifying indicators in enterprise low-carbon assessment. Background Technology

[0002] As the goals of carbon peaking and carbon neutrality are advanced, the quantitative assessment of enterprises' low-carbon levels is gradually becoming an important basis for energy management, policy making, and industry regulation. Existing enterprise low-carbon evaluation methods are usually based on a pre-set evaluation index system, and a comprehensive score is obtained by weighting and summing various indicators.

[0003] However, in practical applications, the impact of each indicator on the enterprise's low-carbon level varies significantly, and some indicators even have interactive effects, making it difficult for traditional methods based on fixed weights or single-factor analysis to accurately identify the key indicators that truly affect the evaluation results.

[0004] Therefore, how to accurately identify key influencing indicators in enterprise low-carbon assessment is an urgent problem to be solved in this field. Summary of the Invention

[0005] This invention provides a method, apparatus, system, and medium for identifying indicators in enterprise low-carbon assessment, which can solve at least one of the above-mentioned technical problems.

[0006] In a first aspect, embodiments of the present invention provide a method for identifying indicators for enterprise low-carbon assessment, including: Calculate the weight of each evaluation indicator based on the values ​​of each indicator in the enterprise low-carbon evaluation index table. Based on the values ​​and weights of each of the evaluation indicators, calculate the enterprise's low-carbon score corresponding to each of the evaluation indicators. Using the low-carbon scores of each enterprise and the values ​​of each indicator as input variables, sensitivity analysis is performed on each evaluation indicator to obtain the first-order sensitivity index and the second-order sensitivity index of each evaluation indicator. The Monte Carlo method is used to perform sensitivity estimation on each of the evaluation indicators to obtain the first-order sensitivity estimate of each of the evaluation indicators. Based on the first-order sensitivity index and first-order sensitivity estimate of each of the evaluation indicators, the comprehensive first-order sensitivity index of each of the evaluation indicators is determined. The target evaluation index is determined based on the first-order sensitivity composite index and the second-order sensitivity index of each of the evaluation indicators.

[0007] Secondly, embodiments of the present invention provide an indicator identification device for enterprise low-carbon assessment, comprising: The indicator weight calculation module is used to calculate the indicator weight of each evaluation indicator based on the indicator values ​​of each evaluation indicator in the enterprise low-carbon evaluation indicator table. The enterprise low-carbon score calculation module is used to calculate the enterprise low-carbon score corresponding to each of the evaluation indicators based on the value and weight of each indicator. The sensitivity analysis module is used to take the low-carbon scores of each enterprise and the values ​​of each indicator as input variables, perform sensitivity analysis on each evaluation indicator, and obtain the first-order sensitivity index and the second-order sensitivity index of each evaluation indicator. The sensitivity estimation module is used to perform sensitivity estimation on each of the evaluation indicators using the Monte Carlo method, and obtain the first-order sensitivity estimate value of each of the evaluation indicators. The first-order sensitivity comprehensive index determination module is used to determine the first-order sensitivity comprehensive index of each evaluation index based on the first-order sensitivity index and the first-order sensitivity estimate of each evaluation index. The target evaluation index determination module is used to determine the target evaluation index based on the first-order sensitivity comprehensive index and the second-order sensitivity index of each of the evaluation indicators.

[0008] Thirdly, embodiments of the present invention also provide an indicator identification system for enterprise low-carbon evaluation, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described in any one of the embodiments of the present invention.

[0009] Fourthly, embodiments of the present invention also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the method described in any one of the embodiments of the present invention.

[0010] This invention employs a technical solution that calculates the weight of each evaluation indicator based on its numerical value in the enterprise low-carbon evaluation indicator table. Further, based on the indicator weights and numerical values, the corresponding enterprise low-carbon score is calculated, providing a unified and quantifiable evaluation output for subsequent sensitivity analysis. On this basis, the enterprise low-carbon scores and indicator values ​​are used as input variables to obtain the first-order and second-order sensitivity indices for each evaluation indicator. This allows for the assessment not only of the direct impact of individual indicators on score changes but also the quantification of the coupling effect of interactions between different indicators on the score. Simultaneously, the Monte Carlo method is used to estimate the sensitivity of each evaluation indicator, yielding more robust first-order sensitivity estimates. Based on the first-order sensitivity estimates and first-order sensitivity indices, a first-order comprehensive sensitivity index is determined. Finally, based on the first-order comprehensive sensitivity index and the second-order sensitivity index, target evaluation indicators with a dominant influence or significant interactive influence on the enterprise low-carbon score can be identified more accurately. Thus, this embodiment of the invention can significantly improve the accuracy of identifying key influencing indicators in enterprise low-carbon evaluation.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings are provided for a better understanding of this solution and do not constitute a limitation of the invention. Wherein: Figure 1 This is a flowchart of an indicator identification method for enterprise low-carbon evaluation according to an embodiment of the present invention; Figure 2 This is a structural block diagram of an indicator identification device for enterprise low-carbon evaluation according to an embodiment of the present invention; Figure 3 This is a schematic block diagram of an electronic device used to implement the methods of embodiments of the present invention. Detailed Implementation

[0013] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0014] Figure 1 This is a flowchart of an indicator identification method for enterprise low-carbon evaluation according to an embodiment of the present invention.

[0015] like Figure 1As shown, the method for identifying indicators in the enterprise's low-carbon assessment may include: S110, Calculate the weight of each evaluation indicator based on the values ​​of each indicator in the enterprise low-carbon evaluation indicator table. S120, calculate the enterprise's low-carbon score for each evaluation indicator based on the value and weight of each indicator. S130 uses the low-carbon scores of each enterprise and the values ​​of each indicator as input variables to conduct sensitivity analysis on each evaluation indicator, and obtains the first-order sensitivity index and the second-order sensitivity index of each evaluation indicator. S140, Sensitivity estimation of each evaluation index is performed using the Monte Carlo method to obtain the first-order sensitivity estimate of each evaluation index; S150, based on the first-order sensitivity index and the first-order sensitivity estimate of each evaluation indicator, determine the comprehensive first-order sensitivity index of each evaluation indicator. S160, based on the first-order sensitivity composite index and the second-order sensitivity index of each evaluation indicator, the target evaluation indicator is determined.

[0016] For example, firstly, based on pre-defined low-carbon evaluation dimensions, candidate evaluation indicators for five major aspects that enterprises may be involved in—energy management, environmental governance, carbon emissions, digital technology application, and green supply chain—are summarized, forming Table 1. In terms of energy management, candidate indicators include self-produced and self-consumed green electricity, self-produced and self-consumed green energy heat, energy consumption output rate, renewable energy usage ratio, green electricity usage ratio, green electricity supply, and the proportion of new energy vehicles among the enterprise's own vehicles; in terms of environmental governance, candidate indicators include green coverage rate and recycling rate of renewable resources; in terms of carbon emissions, candidate indicators include total carbon emissions, carbon emissions per unit of output value, and carbon dioxide emission reduction; in terms of digital technology application, candidate indicators include the proportion of green and intelligent technology R&D investment and the proportion of digital and low-carbon transformation of business processes; and in terms of green supply chain, candidate indicators include the coverage rate of supplier green performance evaluation, the proportion of green product procurement, and the proportion of green logistics and transportation.

[0017] Subsequently, based on the industry nature (e.g., manufacturing, energy, construction), production method, position in the industrial chain, and focus of low-carbon development of the enterprise under analysis, indicators applicable to the enterprise's low-carbon assessment are selected from Appendix 1 as evaluation indicators to determine the scope of evaluation indicators. For example, for power generation enterprises, indicators such as green electricity supply, renewable energy usage ratio, and total carbon emissions can be prioritized; for manufacturing enterprises, indicators such as energy consumption output rate, renewable resource recycling rate, and carbon emissions per unit of output value can be appropriately strengthened. Through indicator screening, it is ensured that the selected indicators not only cover the enterprise's main carbon emission sources and energy-saving and carbon-reduction measures, but also avoid redundant indicators that may lead to evaluation bias.

[0018] Next, for all evaluation indicators within the defined scope, a list of all data required for their quantitative calculation is provided, and the relevant data sources are clearly categorized. For data that needs to be obtained through enterprise-independent statistics, primary activity-level data such as annual statistical reports, energy consumption records, equipment operation ledgers, on-site monitoring data, and experimental simulation results can be collected. For indicators requiring external data support, secondary data sources can be utilized, including national or industry carbon emission databases, formally published literature or papers, various authoritative statistical yearbooks, and analytical data provided by industry associations. During the data collection process, the data types, units of measurement, collection cycles, and calculation methods for each indicator are standardized to obtain specific numerical values ​​for each evaluation indicator.

[0019] Through the above steps, a low-carbon evaluation index table for enterprise low-carbon assessment is established. This table can include various evaluation indicators adapted to the characteristics of enterprises and the specific values ​​of each evaluation indicator, providing a unified, standardized and quantifiable data foundation for subsequent indicator weight calculation, enterprise low-carbon score calculation and sensitivity analysis.

[0020] For example, the enterprise low-carbon evaluation index table is shown in Table 2: Table 2 In this example, the evaluation objects in Table 2 can be various projects of a company, or various companies.

[0021] According to the above implementation method, firstly, based on the indicator values ​​of each indicator in the enterprise low-carbon evaluation indicator table, the indicator weight of each indicator is calculated; then, combining the indicator values ​​and weights, the corresponding enterprise low-carbon score is obtained; subsequently, using the enterprise low-carbon score and the indicator values ​​as input, sensitivity analysis is performed to obtain the first-order and second-order sensitivity indices of each indicator; and then, the Monte Carlo method is used to further estimate the sensitivity of each indicator, obtaining the first-order sensitivity estimate; based on this, the first-order sensitivity index and the estimate are combined to obtain a more robust first-order sensitivity composite index; finally, combining the first-order sensitivity composite index and the second-order sensitivity index, the target evaluation indicator with the most significant impact on the enterprise low-carbon evaluation is determined. In this way, through multiple verifications of weight calculation, sensitivity analysis, and Monte Carlo estimation, the accuracy of identifying key influencing indicators in enterprise low-carbon evaluation is improved, making the evaluation results more scientific and objective, and providing more targeted decision-making basis for enterprise low-carbon management.

[0022] In one implementation, the weight of each evaluation indicator is calculated based on the numerical values ​​of each indicator in the enterprise low-carbon evaluation indicator table. This includes: constructing an indicator matrix based on the numerical values ​​of each evaluation indicator; standardizing the numerical values ​​of each indicator in the indicator matrix to update the indicator matrix and obtain a standardized indicator matrix, wherein the standardization process includes performing positive or negative standardization based on the indicator attributes of each evaluation indicator; normalizing each evaluation indicator based on the standard values ​​of each evaluation indicator in the standardized indicator matrix to obtain the proportion of each evaluation indicator; calculating the entropy of each evaluation indicator based on its proportion to obtain the information entropy value of each evaluation indicator; determining the difference coefficient of each evaluation indicator based on the difference between 1 and the information entropy value of the evaluation indicator; and determining the weight of each evaluation indicator based on the ratio of the difference coefficient of the evaluation indicator to the sum of the difference coefficients of all evaluation indicators.

[0023] For example, an indicator matrix refers to a numerical matrix obtained by arranging the original indicator values ​​of multiple evaluation objects (such as enterprises, projects, years, etc.) on various evaluation indicators. If there are m evaluation objects and n evaluation indicators, then the indicator matrix... In the formula, For the indicator matrix; Let m be the evaluation indicator in the i-th row and j-th column; m is the number of rows (i.e., the total number of evaluation objects), and n is the number of columns (i.e., the total number of evaluation indicators).

[0024] For example, a standardized indicator matrix refers to a matrix obtained by standardizing the values ​​of each indicator in the indicator matrix according to their attributes (positive indicator attributes / negative indicator attributes). The purpose of standardization is to eliminate differences in the dimensions of the indicators, so that all indicators are on the same order of magnitude, which facilitates the subsequent calculation of proportions and entropy values.

[0025] For example, positive indicators are normalized using Min-Max (minimum value - maximum value), and negative indicators are normalized using inverse normalization. After processing, the original indicator values ​​are replaced with the standardized indicator values, thereby updating and forming a standardized indicator matrix.

[0026] In this example, the forward normalization process can be represented by the following computational expression: In the formula, The standard value of the j-th positive indicator in the i-th row; The index value (original index value) of the j-th index in the i-th row; The minimum value of the j-th indicator; It represents the maximum value of the j-th indicator.

[0027] In this example, negative standardization can be represented by the following computational expression: In the formula, The standard value of the j-th negative index in the i-th row; The index value (original index value) of the j-th index in the i-th row; The minimum value of the j-th indicator; It represents the maximum value of the j-th indicator.

[0028] For example, the overall standard value of the evaluation indicator is obtained by summing the standard values ​​of each evaluation indicator in the standardized indicator matrix; then the weight of the evaluation indicator is obtained by dividing the standard value of the evaluation indicator corresponding to each evaluation object by the overall standard value of the evaluation indicator.

[0029] In this example, the calculation process for the weight of the evaluation indicators can be expressed as follows: In the formula, The weight of the j-th evaluation indicator in the i-th row (evaluation object); Let be the standard value of the j-th evaluation indicator in the i-th row; n is the total number of evaluation indicators.

[0030] Understandably, if the evaluation objects are used as rows and the evaluation indicators are used as columns when constructing the matrix, then each row corresponds to one evaluation object.

[0031] For example, entropy calculation can be expressed as: In the formula, Let be the information entropy of evaluation index j; and n be the total number of evaluation indexes. The weight of the j-th evaluation indicator in the i-th row.

[0032] For example, the calculation process of the difference coefficient can be expressed as follows: In the formula, The information entropy for evaluating index j; The coefficient of variation is used to evaluate index j.

[0033] For example, the calculation process of the indicator weights of the evaluation indicators can be expressed as follows: In the formula, The weight of indicator j is used to evaluate the indicator. The coefficient of variation is used to evaluate index j.

[0034] According to the above implementation method, an indicator matrix is ​​constructed based on the numerical values ​​of each evaluation indicator. A standardized indicator matrix is ​​then formed by performing positive or negative standardization on the indicator matrix. Furthermore, each evaluation indicator is normalized based on the standardized indicator matrix to obtain its weight. The information entropy value of each evaluation indicator is then calculated based on its weight, and the difference coefficient is determined accordingly. Finally, the indicator weight of each evaluation indicator is determined based on the ratio of the difference coefficient to the sum of all difference coefficients. In this way, indicator weights can be automatically determined based on the dispersion of the indicator data without subjective intervention, making weight allocation more objective and reliable, and improving the credibility and scientific rigor of the low-carbon evaluation results.

[0035] In one implementation, the enterprise low-carbon score corresponding to each evaluation indicator is calculated based on the value and weight of each evaluation indicator, including: calculating the weight of each evaluation indicator value based on the value of each evaluation indicator value; and weighting and summing the weights of each evaluation indicator value based on the weight of each indicator value to obtain the enterprise low-carbon score corresponding to each evaluation indicator.

[0036] For example, the calculation process of the enterprise's low-carbon score corresponding to the evaluation indicators can be expressed by a functional expression as follows: In the formula, , where n is the enterprise's low-carbon score corresponding to the evaluation indicators; n is the total number of evaluation indicators; The weight of indicator j is used to evaluate the indicator. This represents the weight of the j-th evaluation indicator in the i-th row (evaluation object).

[0037] In this example, three evaluation indicators are selected for a specific enterprise: Evaluation Indicator A: Renewable Energy Usage Ratio; Evaluation Indicator B: Energy Consumption per Unit of Output; Evaluation Indicator C: Total Carbon Emissions. Each evaluation indicator includes two evaluation objects (two projects): Project P1 and Project P2. Examples of their standard values ​​are shown in Table 3 below. Table 3 For example, in order to calculate the weight of the indicator values, the indicator values ​​of each item under the same indicator are first standardized according to the standardization method given in the previous example to eliminate the difference in dimensions, and the standard values ​​are obtained as shown in Table 3.

[0038] Subsequently, the standard values ​​are normalized to reflect their numerical weights. Taking indicator A as an example, the sum of the standard values ​​is 1.60, so the weights of P1 and P2 are 0.60 / 1.60 = 0.375 and 1.00 / 1.60 = 0.625, respectively. Similarly, the weights of P1 and P2 under indicator B are 0.333 and 0.667, respectively, and the weights of P1 and P2 under indicator C are 0.375 and 0.625, respectively.

[0039] Assuming the weights of the three indicators are: Indicator A: 0.40; Indicator B: 0.35; Indicator C: 0.25, then the weighted summation of each item under the same evaluation indicator can be performed to obtain the enterprise's low-carbon score for each indicator. Taking Indicator A as an example, its score is: 0.375 × 0.40 + 0.625 × 0.40 = 0.40; performing the same weighted summation operation on Indicator B yields its low-carbon score: 0.333 × 0.35 + 0.667 × 0.35 = 0.35. This allows for standardized weighted calculation and scoring of different evaluation objects (projects) within the same enterprise, making the contribution of each project to each evaluation indicator clearer and facilitating subsequent low-carbon performance analysis and key project identification.

[0040] According to the above implementation method, the weight of each indicator value is calculated based on the value of each evaluation indicator. Then, a weighted summation operation is performed on the weights of each indicator value to obtain the enterprise's low-carbon score for each evaluation indicator. Thus, based on the "weighted weighting" calculation method, the enterprise's low-carbon score can more accurately reflect the importance and actual contribution of each indicator, thereby improving the discriminability and accuracy of the low-carbon evaluation results.

[0041] In one implementation, the low-carbon scores of each enterprise and the values ​​of each indicator are used as input variables. Sensitivity analysis is performed on each evaluation indicator to obtain the first-order and second-order sensitivity indices of each evaluation indicator. This includes: calculating the variance based on the low-carbon scores of each enterprise to obtain the total variance; decomposing the total variance into the variance caused by the value of a single evaluation indicator and the variance caused by the interaction of the values ​​of any two evaluation indicators; determining the first-order sensitivity index of each evaluation indicator based on the ratio of the variance caused by the value of a single evaluation indicator to the total variance; and determining the second-order sensitivity index of each evaluation indicator based on the ratio of the variance caused by the interaction of the values ​​of any two evaluation indicators to the total variance.

[0042] For example, the mean of each company's low-carbon score is calculated based on the company's low-carbon score, and the total variance of all companies' low-carbon scores is obtained by dividing the sum of squares of the differences between each company's low-carbon score and the mean by the number of scores. For example, if the low-carbon scores of three companies are 0.30, 0.45 and 0.60 respectively, their mean is 0.45. The total variance can be obtained by calculating (0.30-0.45)² + (0.45-0.45)² + (0.60-0.45)² and then dividing by 3, which gives a value of 0.015, serving as the basis for the total variance in subsequent variance decomposition.

[0043] For example, by establishing a multivariate function model of the enterprise's low-carbon score with respect to the values ​​of each evaluation indicator, and based on the Sobol variance decomposition principle, the values ​​of all indicators except one of the evaluation indicators are fixed sequentially and simulated for sampling. This yields the change in the low-carbon score caused by the change of only that single evaluation indicator, and the variance corresponding to this change is calculated. Subsequently, with the values ​​of the remaining indicators fixed except for any two evaluation indicators, the change in the low-carbon score caused by the interaction between these two indicators is obtained through simulation sampling again, and the corresponding interaction variance is calculated. For instance, when three evaluation indicators A, B, and C are involved, three first-order variance contributions can be obtained by simulating "only A changes," "only B changes," and "only C changes," respectively. Three second-order interaction variance contributions can be obtained by simulating "A and B change together," "A and C change together," and "B and C change together," respectively. For example, the score variance caused by only A changing is 0.006, and the interaction variance caused by A and B changing simultaneously is 0.003.

[0044] For example, for each evaluation indicator, the variance caused solely by the change in that indicator's value is divided by the total variance to obtain the first-order sensitivity index of that indicator, which represents the strength of the indicator's direct impact on the company's low-carbon score. For instance, with a total variance of 0.015, if the first-order variance of evaluation indicator A is 0.006, then its first-order sensitivity index is 0.006 / 0.015 = 0.40, indicating that 40% of the change in the company's low-carbon score can be explained solely by indicator A.

[0045] For example, for any two evaluation indicators, the variance caused by the interaction of these two indicators is divided by the total variance to obtain their corresponding second-order sensitivity indices, which represent the degree of influence of their interaction on the company's low-carbon score. For instance, with a total variance of 0.015, if the interaction variance between evaluation indicator A and evaluation indicator B is 0.003, then the second-order sensitivity index is 0.003 / 0.015 = 0.20, indicating that approximately 20% of the variance in the company's low-carbon score is determined by the joint changes of A and B.

[0046] According to the above implementation method, when conducting sensitivity analysis based on enterprise low-carbon scores, the overall score variance is first calculated using the low-carbon score results of each enterprise, resulting in the total variance. This total variance is then decomposed into two sources: the variance contribution caused by fluctuations in the values ​​of individual evaluation indicators, and the variance contribution caused by the interaction between any two evaluation indicators. Based on this, the ratio of the variance contribution of a single indicator to the total variance is used as the first-order sensitivity index of that indicator, and the ratio of the variance contribution of the interaction between any two indicators to the total variance is used as the second-order sensitivity index between the indicators. This yields a sensitivity quantification result reflecting the degree of independent and joint influence of each indicator. In this way, key evaluation indicators affecting enterprise low-carbon scores can be accurately identified, and the interaction effects between indicators can be captured, making the sources of low-carbon evaluation results clearer and more interpretable.

[0047] In one implementation, the Monte Carlo method is used to perform sensitivity estimation on each evaluation index to obtain the first-order sensitivity estimate of each evaluation index. This includes: performing multiple random samplings on the value space of each evaluation index to obtain multiple input variable sample sets; calculating the enterprise's low-carbon score for each input variable sample set based on the index weights of each evaluation index and the sample values ​​of each input variable in the input variable sample set to obtain multiple output results; and calculating the variance of the output results contributed by the change in the index value of a single evaluation index based on each input variable sample set and each output result to obtain the first-order sensitivity estimate of the evaluation index.

[0048] For example, for each evaluation index, a reasonable range of values ​​or probability distribution is determined (e.g., based on historical observations, upper and lower limits given by experts, or assumed normal / uniform distribution). A sampling method such as Monte Carlo random sampling or Sobol low-difference sequence is selected and the sample size N is determined. N sets of input variable samples are generated independently from the value space of each evaluation index according to the selected method, forming an input sample matrix.

[0049] For example, if there are three evaluation indicators, the value ranges for each indicator can be set as indicator 1. [0, 1], Index 2 [0.2, 1.2], Indicator 3 [600, 1200], and select the Monte Carlo method to generate N=5000 sets of samples, then a 5000×3 input sample matrix can be obtained, with each row being a set of input samples.

[0050] For example, for each group of samples in the input sample matrix, the sample values ​​are first standardized / normalized according to the indicator attributes to obtain standardized indicator values ​​or proportions. Then, the low-carbon score of the group of samples is calculated according to the predetermined indicator weights, and the output result set corresponding to all samples is saved.

[0051] For example, for each index j, the Monte Carlo sampling method is used to employ a "sampling-freeze" or conditional expectation estimation method to construct a set of auxiliary samples for estimation (e.g., generating matrices A and B, and calculating the evaluation function value S_A of the k-th sample in matrix A for each of the two independent sets of samples). {(k)} The evaluation function value S_B of the k-th sample in matrix B {(k)} Replace the j-th column of A with the j-th column of B to obtain the matrix A_B after replacement. {(j)} And use the replaced matrix A_B {(j)} The output set calculated from the k-th sample is S. {A_B{(j)}} {(k)} Based on the output set, the variance component V_j caused by the univariate change of X_j is estimated by using the Monte Carlo effect estimator, or by calculating the conditional expectation E[S|X_j] after binning the input variable X_j and further calculating the variance Var(E[S|X_j]) of the conditional expectation. Finally, the ratio of V_j to the total variance Var(S) is used as the first-order sensitivity estimate of the index.

[0052] For example, after obtaining the corresponding output sets by using two groups of 5000 samples each, the contribution variance V_A of indicator A is calculated as 0.005 using the pick-freeze estimator, and the total variance Var(S) of all sample outputs is 0.015. Then the first-order sensitivity estimate of indicator A is 0.005 / 0.015≈0.333.

[0053] In one implementation, the first-order sensitivity comprehensive index of each evaluation indicator is determined based on its first-order sensitivity index and first-order sensitivity estimate. This includes: calculating the relative deviation between the first-order sensitivity index and the first-order sensitivity estimate of each evaluation indicator; if the relative deviation is less than or equal to a preset threshold, determining the first-order sensitivity comprehensive index of the evaluation indicator based on the mean of its first-order sensitivity index and first-order sensitivity estimate; if the relative deviation is greater than the threshold, performing sensitivity analysis on the evaluation indicator using a third-party sensitivity analysis method to obtain the third-party sensitivity index of the evaluation indicator; calculating the difference between the third-party sensitivity index and the first-order sensitivity index and the first-order sensitivity estimate, respectively, and taking the absolute value of each calculation result, selecting the value corresponding to the minimum value of the calculation result as the first-order sensitivity comprehensive index of the evaluation indicator.

[0054] For example, the absolute value of the difference between the first-order sensitivity index of the evaluation index and the first-order sensitivity estimate of the evaluation index is taken to obtain the first calculation result; the minimum value between the first-order sensitivity index of the evaluation index and the first-order sensitivity estimate is determined as the second calculation result; and the relative deviation of the evaluation index is determined based on the ratio of the first calculation result and the second calculation result.

[0055] For example, based on a relative deviation greater than a threshold (the threshold can be set according to actual needs, for example, 0.1), a third-party sensitivity analysis method is used to perform sensitivity analysis on the evaluation index to obtain the third-party sensitivity index of the evaluation index. The third-party sensitivity analysis method can be, for example, the Morris method, local sensitivity analysis based on partial derivatives, or other known sensitivity analysis methods that are different from the aforementioned methods.

[0056] For example, the relative deviation Δ j When the value is less than or equal to a preset threshold δ, the first-order sensitivity composite index of the evaluation index is determined based on the mean of the first-order sensitivity index and the first-order sensitivity estimate. Specifically, this involves calculating... In the formula, This is a first-order sensitivity composite index for evaluating indicators; The first-order sensitivity index for the evaluation indicator; This is a first-order sensitivity estimate.

[0057] In this example, let the third-party sensitivity index be S. j (3) The first-order sensitivity index is S. j (1) The first-order sensitivity estimate is S. j (2) If |S j (3) -S j (1) ∣<∣S j (3) -S j (2) |, then take If the two are equal, the result can be determined according to preset rules (such as taking the average or prioritizing the one with smaller statistical fluctuations).

[0058] In one implementation, target evaluation indicators are determined based on the first-order sensitivity composite index and the second-order sensitivity index of each evaluation indicator. This includes: if there is no need to meet the preset enterprise low-carbon evaluation requirements, the evaluation indicator corresponding to the maximum value among the first-order sensitivity composite indices is taken as the target evaluation indicator; if it is necessary to meet the enterprise low-carbon evaluation requirements, the two evaluation indicators corresponding to the maximum values ​​among the second-order sensitivity indices are taken as target evaluation indicators respectively; wherein, the enterprise low-carbon evaluation requirements include identifying the coupling correlation between different evaluation indicators in order to formulate a carbon reduction plan that includes multiple synergistic measures.

[0059] For example, target evaluation indicators refer to key indicators selected from multiple candidate evaluation indicators through sensitivity analysis during the enterprise's low-carbon evaluation process, which serve as the basis for subsequent decision-making or optimization scheme formulation. Target evaluation indicators can reflect the factors that have the greatest impact on an enterprise's carbon emissions or low-carbon performance.

[0060] For example, if the evaluation index set includes "energy consumption intensity," "renewable energy utilization rate," "carbon emissions per unit of output," and "process energy efficiency," and the first-order sensitivity composite index shows that "carbon emissions per unit of output" has the highest sensitivity, then this index will be selected as the target evaluation index. If the low-carbon collaborative needs of enterprises are considered, and the second-order sensitivity analysis shows that the combined sensitivity of "energy consumption intensity" and "renewable energy utilization rate" is the highest, then both of these indicators will be used as target evaluation indicators.

[0061] In this example, we assume that the company has four evaluation indicators with first-order sensitivity composite indices of [0.15, 0.42, 0.28, 0.33], where the maximum value is 0.42, corresponding to the indicator "carbon emissions per unit of output". Therefore, "carbon emissions per unit of output" is determined as the target evaluation indicator.

[0062] In this example, assuming the second-order sensitivity indices of the four evaluation indicators are [0.12, 0.33, 0.25, 0.30], with a maximum value of 0.33, the corresponding indicator combination is "energy consumption intensity" and "renewable energy usage ratio," and these two indicators are used as target evaluation indicators. This allows us to identify the coupling correlation between different evaluation indicators, providing a basis for developing carbon reduction plans that include multiple synergistic measures.

[0063] For example, a company's low-carbon assessment needs may also include multiple assessment indicators whose first-order sensitivity composite indices are close in magnitude, making it impossible to identify a single key assessment indicator through the first-order sensitivity composite index; the preset carbon reduction target cannot be achieved by improving a single assessment indicator, but must be achieved through a combination of multiple measures.

[0064] Figure 2This is a structural block diagram of an indicator identification device for enterprise low-carbon evaluation according to an embodiment of the present invention.

[0065] like Figure 2 As shown, the indicator identification device for the enterprise's low-carbon assessment may include: The indicator weight calculation module 510 is used to calculate the indicator weight of each evaluation indicator based on the indicator values ​​of each evaluation indicator in the enterprise low-carbon evaluation indicator table. The enterprise low-carbon score calculation module 520 is used to calculate the enterprise low-carbon score corresponding to each of the evaluation indicators based on the value and weight of each indicator. Sensitivity analysis module 530 is used to take the low-carbon score of each enterprise and the value of each indicator as input variables, perform sensitivity analysis on each evaluation indicator, and obtain the first-order sensitivity index and second-order sensitivity index of each evaluation indicator. Sensitivity estimation module 540 is used to perform sensitivity estimation on each of the evaluation indicators using the Monte Carlo method to obtain the first-order sensitivity estimate value of each of the evaluation indicators. The first-order sensitivity comprehensive index determination module 550 is used to determine the first-order sensitivity comprehensive index of each evaluation index based on the first-order sensitivity index and the first-order sensitivity estimate of each evaluation index. The target evaluation index determination module 560 is used to determine the target evaluation index based on the first-order sensitivity comprehensive index and the second-order sensitivity index of each of the evaluation indicators.

[0066] In one embodiment, the indicator weight calculation module includes: The indicator matrix construction unit is used to construct an indicator matrix based on the values ​​of each of the evaluation indicators. A standardization processing unit is used to standardize the values ​​of each indicator in the indicator matrix to update the indicator matrix and obtain a standardized indicator matrix. The standardization processing includes performing positive standardization processing or negative standardization processing based on the indicator attributes of each evaluation indicator. The normalization unit is used to normalize each evaluation indicator based on the standard value of each evaluation indicator in the standardized indicator matrix to obtain the weight of each evaluation indicator. The entropy calculation unit is used to calculate the entropy of each evaluation indicator based on the weight of each evaluation indicator, and obtain the information entropy value of each evaluation indicator. The difference coefficient determination unit is used to determine the difference coefficient of each evaluation index based on the difference between 1 and the information entropy value of the evaluation index; and The indicator weight determination unit is used to determine the indicator weight of the evaluation indicator based on the ratio of the difference coefficient of the evaluation indicator to the sum of the difference coefficients of each of the evaluation indicators.

[0067] In one embodiment, the enterprise low-carbon score calculation module includes: The indicator value weight calculation unit is used to calculate the indicator value weight of each of the evaluation indicators based on the indicator values ​​of each of the evaluation indicators. The weighted summation unit is used to perform weighted summation of the numerical proportions of each of the evaluation indicators based on the weights of each indicator, so as to obtain the enterprise low-carbon score corresponding to each of the evaluation indicators.

[0068] In one implementation, the sensitivity analysis module includes: The variance calculation unit is used to calculate the variance based on the low-carbon score of each of the aforementioned enterprises to obtain the total variance. The total variance decomposition unit is used to decompose the total variance into the variance caused by the index value of a single evaluation index and the variance caused by the interaction of the index values ​​of any two evaluation indices. A first-order sensitivity index calculation unit is used to determine the first-order sensitivity index of each evaluation index based on the ratio of the variance caused by the index value of a single evaluation index to the total variance. The second-order sensitivity index calculation unit is used to determine the second-order sensitivity index of each of the evaluation indicators based on the ratio of the variance caused by the interaction of the numerical values ​​of any two of the evaluation indicators to the total variance.

[0069] In one implementation, the sensitivity estimation module includes: The random sampling unit is used to perform multiple random samplings on the value space of each of the evaluation indicators to obtain multiple sets of input variable samples. The enterprise low-carbon score calculation unit is used to calculate the enterprise low-carbon score for each of the input variable sample sets based on the index weights of each of the evaluation indicators and the sample values ​​of each input variable in the input variable sample sets, and to obtain multiple output results. The statistical unit is used to calculate the variance of the output result contributed by the change in the value of a single evaluation index based on the sample sets of each input variable and each output result, so as to obtain the first-order sensitivity estimate of the evaluation index.

[0070] In one embodiment, the first-order sensitivity composite index determination module includes: The relative deviation calculation unit is used to calculate the relative deviation between the first-order sensitivity index of the evaluation index and the estimated first-order sensitivity value of the evaluation index. The first judgment unit is used to determine the first-order sensitivity comprehensive index of the evaluation index based on the mean of the first-order sensitivity index and the first-order sensitivity estimate of the evaluation index if the relative deviation is less than or equal to a preset threshold. The second judgment unit is used to perform sensitivity analysis on the evaluation index by a third-party sensitivity analysis method if the relative deviation is greater than the threshold, and obtain the third-party sensitivity index of the evaluation index; calculate the difference between the third-party sensitivity index and the first-order sensitivity index and the first-order sensitivity estimate respectively, and take the absolute value of each calculation result, and select the value corresponding to the minimum value of the calculation result as the first-order sensitivity comprehensive index of the evaluation index.

[0071] In one embodiment, the target evaluation index determination module includes: The first unit is used to take the evaluation index corresponding to the maximum value among the first-order sensitivity comprehensive indices as the target evaluation index if there is no need to meet the preset enterprise low-carbon evaluation requirements. The second unit is used to, if it is necessary to meet the enterprise's low-carbon assessment requirements, take the two evaluation indicators corresponding to the maximum values ​​of the second-order sensitivity indices as the target evaluation indicators respectively; wherein, the enterprise's low-carbon assessment requirements include identifying the coupling correlation between different evaluation indicators in order to formulate a carbon reduction plan that includes multiple synergistic measures.

[0072] The specific functions and examples of each module and submodule of the system in this embodiment of the invention can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0073] The acquisition, storage, and application of user personal information involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0074] This invention also provides an indicator identification system for enterprise low-carbon assessment, comprising: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method described in any one of the embodiments of the present invention.

[0075] The beneficial effects of the enterprise low-carbon assessment indicator identification system in this embodiment of the invention are equivalent to the beneficial effects of the enterprise low-carbon assessment indicator identification method described above, and will not be repeated here.

[0076] This invention also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the method described in any one of the embodiments of this invention.

[0077] The beneficial effects of the storage medium of the present invention are equivalent to the beneficial effects of the above-mentioned enterprise low-carbon evaluation index identification method, and will not be elaborated here.

[0078] Figure 3 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present invention is shown. Electronic device 800 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 800 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0079] like Figure 3 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 may also store various programs and data required for the operation of the electronic device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0080] Multiple components in electronic device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows electronic device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0081] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the indicator identification method for enterprise low-carbon assessment. For example, in some embodiments, the indicator identification method for enterprise low-carbon assessment can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the indicator identification method for enterprise low-carbon assessment described above can be performed. Alternatively, in other embodiments, the computing unit 801 may be configured, by any other suitable means (e.g., by means of firmware), to perform an indicator identification method for corporate low-carbon assessment.

[0082] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0083] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0084] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0085] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0086] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0087] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0088] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0089] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying indicators for low-carbon evaluation of enterprises, characterized in that, The method comprises the following steps: According to the index values of each evaluation index in the enterprise low-carbon evaluation index table, the index weight of each evaluation index is calculated; According to the index values and index weights of each evaluation index, the enterprise low-carbon score corresponding to each evaluation index is calculated; The enterprise low-carbon score and the index value of each evaluation index are taken as input variables for sensitivity analysis of each evaluation index, and the first-order sensitivity index and the second-order sensitivity index of each evaluation index are obtained; The sensitivity of each evaluation index is estimated by the Monte Carlo method, and the first-order sensitivity estimate value of each evaluation index is obtained; Based on the first-order sensitivity index and the first-order sensitivity estimate value of each evaluation index, the first-order sensitivity comprehensive index of each evaluation index is determined; Based on the first-order sensitivity comprehensive index of each evaluation index and the second-order sensitivity index of each evaluation index, the target evaluation index is determined.

2. The method of claim 1, wherein, The method comprises the following steps: Based on the index values of each evaluation index, an index matrix is constructed; The index values in the index matrix are standardized to update the index matrix, and a standardized index matrix is obtained, wherein the standardization process includes performing positive or negative standardization on each evaluation index based on the index properties of each evaluation index; Based on the standard values of each evaluation index in the standardized index matrix, the proportion of each evaluation index is normalized to obtain the proportion of each evaluation index; Based on the proportion of each evaluation index, the entropy of each evaluation index is calculated to obtain the information entropy value of each evaluation index; For each evaluation index, the difference coefficient of the evaluation index is determined based on the difference between 1 and the information entropy value of the evaluation index; and Based on the difference coefficient of the evaluation index and the ratio of the sum of the difference coefficients of each evaluation index, the index weight of the evaluation index is determined.

3. The method of claim 1, wherein, The method comprises the following steps: Based on the index values of each evaluation index, the index value proportion of each evaluation index is calculated; Based on the index weight of each evaluation index, the index value proportion of each evaluation index is weighted and summed to obtain the enterprise low-carbon score corresponding to each evaluation index.

4. The method of claim 1, wherein, The method comprises the following steps: Based on the enterprise low-carbon score, the total variance is calculated; The total variance is decomposed into variance caused by the index value of a single evaluation index and variance caused by the interaction of the index values of any two evaluation indexes; The first-order sensitivity index of each evaluation index is determined based on a ratio of a variance caused by an index value of a single evaluation index to the total variance; The second-order sensitivity index of each evaluation index is determined based on a ratio of a variance caused by an interaction of index values of any two evaluation indices to the total variance.

5. The method of claim 1, wherein, The first-order sensitivity estimation value of each evaluation index is obtained by performing sensitivity estimation on each evaluation index through the Monte Carlo method, and includes: The value space of the index value of each evaluation index is randomly sampled multiple times to obtain multiple input variable sample sets; For each input variable sample set, an enterprise low-carbon score is calculated based on the index weight of each evaluation index and each input variable sample value in the input variable sample set to obtain multiple output results; The output result variance contributed by the change of the index value of a single evaluation index is counted based on each input variable sample set and each output result to obtain the first-order sensitivity estimation value of the evaluation index.

6. The method of claim 1, wherein, The first-order sensitivity comprehensive index of each evaluation index is determined based on the first-order sensitivity index and the first-order sensitivity estimation value of each evaluation index, and includes: The relative deviation of the first-order sensitivity index of the evaluation index and the first-order sensitivity estimation value of the evaluation index is calculated; If the relative deviation is less than or equal to a preset threshold, the first-order sensitivity comprehensive index of the evaluation index is determined based on the mean of the first-order sensitivity index and the first-order sensitivity estimation value of the evaluation index; If the relative deviation is greater than the threshold, the third-party sensitivity analysis method is used to perform sensitivity analysis on the evaluation index to obtain a third-party sensitivity index of the evaluation index; the difference between the third-party sensitivity index and the first-order sensitivity index and the first-order sensitivity estimation value is calculated respectively, and the absolute value of each calculation result is taken, and the value corresponding to the minimum calculation result is selected as the first-order sensitivity comprehensive index of the evaluation index.

7. The method of claim 1, wherein, The target evaluation index is determined based on the first-order sensitivity comprehensive index of each evaluation index and the second-order sensitivity index of each evaluation index, and includes: If the preset enterprise low-carbon evaluation requirement does not need to be met, the evaluation index corresponding to the maximum value in each first-order sensitivity comprehensive index is taken as the target evaluation index; If the enterprise low-carbon evaluation requirement needs to be met, the two evaluation indices corresponding to the maximum value in each second-order sensitivity index are taken as the target evaluation indices; wherein, the enterprise low-carbon evaluation requirement includes identifying the coupling correlation between different evaluation indices to develop a carbon reduction scheme including multiple collaborative measures.

8. An index identification device for low-carbon evaluation of a business, characterized by It includes: An index weight calculation module is configured to calculate the index weight of each evaluation index according to each index value of each evaluation index in an enterprise low-carbon evaluation index table; An enterprise low-carbon score calculation module is configured to calculate the enterprise low-carbon score corresponding to each evaluation index according to each index value and index weight of each evaluation index. a sensitivity analysis module, configured to perform sensitivity analysis on each evaluation index by taking each enterprise low-carbon score and each index value as an input variable, and obtain a first-order sensitivity index and a second-order sensitivity index of each evaluation index; a sensitivity estimation module, configured to perform sensitivity estimation on each evaluation index by using a Monte Carlo method, and obtain a first-order sensitivity estimation value of each evaluation index; a first-order sensitivity comprehensive index determination module, configured to determine a first-order sensitivity comprehensive index of each evaluation index based on the first-order sensitivity index and the first-order sensitivity estimation value of each evaluation index; a target evaluation index determination module, configured to determine a target evaluation index based on the first-order sensitivity comprehensive index of each evaluation index and the second-order sensitivity index of each evaluation index.

9. An index identification system for low-carbon evaluation of an enterprise, characterized by, comprise: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-7.

Images