Evaluation method for low-carbon transformation index of electricity-carbon market enterprise
By combining the structural entropy weight method and DS evidence theory, the quantitative and synergistic issues of evaluating the low-carbon transformation index of enterprises in the electricity carbon market are resolved. This enables objective quantification and comprehensive evaluation of the low-carbon transformation index of enterprises in the electricity carbon market, supporting enterprises in formulating effective low-carbon strategies.
Patent Information
- Application Number
- CN202410988675.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing evaluation system for the low-carbon transformation index of enterprises in the electricity carbon market has problems such as being mainly qualitative, having difficulty in quantifying indicators, lacking consideration of the synergy between electricity and carbon, and having strong subjectivity in indicator weights. These problems lead to subjective evaluation results and affect the actual effectiveness of enterprises' low-carbon strategies.
The structural entropy weight method is used to determine the index weights. Combining fuzzy comment sets and DS evidence theory, and through Gaussian membership functions and evidence source correction, an evaluation method for the low-carbon transformation index of enterprises in the electricity carbon market is established, integrating multiple information sources and considering the synergy between electricity and carbon.
It enables an objective and quantitative evaluation of the low-carbon transformation index of enterprises in the electricity carbon market, improves the objectivity and comprehensiveness of the evaluation, can truly reflect the low-carbon transformation status of enterprises, and supports enterprises in formulating effective low-carbon strategies.
Smart Images

Figure CN119005781A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of low-carbon development technology, and in particular to a method for evaluating the low-carbon transformation index of an enterprise in an electricity carbon market. Background Art
[0003] The enterprise low-carbon transformation index is an index that reflects the development of the enterprise's low-carbon industry and an indicator for evaluating the enterprise's low-carbon decision-making and behavior adjustment model. At present, there are some shortcomings in the evaluation of its low-carbon transformation index: ① The evaluation is mainly qualitative, and some indicators are difficult to quantify; ② The indicators lack consideration of the synergy of electricity and carbon, and the evaluation system lacks relevant indicators of electricity and carbon synergy, and lacks a comprehensive index evaluation system suitable for the electricity and carbon market; ③ The determination of indicator weights mostly adopts expert scoring, which makes the evaluation results more subjective. Based on the above problems, the current low-carbon transformation index evaluation system is difficult to truly reflect the situation and problems of the low-carbon transformation of enterprises in the electricity and carbon market, thereby affecting the actual operation effect of the enterprise's low-carbon strategy and the realization of the low-carbon transformation goals. Therefore, the key problem that needs to be solved is how to construct a comprehensive evaluation system for the enterprise low-carbon transformation index for the electricity and carbon market, and improve the objectivity of the entire evaluation system to provide a basis for the enterprise's low-carbon transformation decision. Therefore, it is crucial to develop a comprehensive evaluation system for the low-carbon transformation index of the electricity and carbon market. Summary of the invention
[0004] The purpose of the present invention is to provide a method for evaluating the low-carbon transformation index of enterprises in the electricity carbon market, to quantify the low-carbon transformation index of enterprises, and to objectively evaluate the low-carbon transformation index of enterprises.
[0005] To achieve the above objectives, the technical solution of the present invention is:
[0006] A method for evaluating a low-carbon transformation index of an electricity carbon market enterprise comprises the following steps:
[0007] S1: Determine the evaluation indicators included in the low-carbon transformation index evaluation system for electricity and carbon market enterprises;
[0008] S2: Use the structural entropy weight method to determine the weight coefficient W of each indicator in the index evaluation system of step S1 j ;
[0009] S3: Establish a fuzzy comment set and transform the fuzzy semantics into a mass function;
[0010] S4: Modify the mass function in step S3;
[0011] S5: The weight coefficient W of each indicator determined according to step S2 j , and the mass function corrected in step S4, calculate the final low-carbon transformation evaluation result P value of the enterprise.
[0012] Furthermore, the weight coefficient W of each indicator in step S2 is j The determination method includes the following steps:
[0013] S21: Collect expert opinions and form a subjective typical ranking table;
[0014] Experts rank the importance of each indicator. The ranking array of the five first-level indicators given by the i-th expert is:
[0015] (a i1 ,a i2 ,...a i5 )
[0016] Among them: a in ,n=1,2...,5 represents the sorting order corresponding to the nth indicator after the i-th expert sorts the five first-level indicators;
[0017] For each of the six secondary indicators under the first-level indicator, the sorted array of the six secondary indicators under each of the first-level indicators given by the i-th expert is
[0018]
[0019] in: It indicates the sorting order of the mth indicator after the i-th expert sorts the six secondary indicators under the first-level indicator;
[0020] Sort the six secondary indicators under each primary indicator to form a typical ranking table of primary and secondary indicators;
[0021] S22: Perform blind analysis on the typical ranking table of step S21, use entropy method to correct it, reduce subjectivity, and quantitatively transform the typical ranking table through membership function. The formula is as follows:
[0022]
[0023] Among them, χ(Ι) is the membership function; I is the expert's ranking value for a certain indicator; n is the actual maximum ranking number in the ranking group.
[0024] The number of experts ranking the index is a ij Substitute into the formula χ(Ι) to obtain the membership data table b of the sorted number ij =χ(a ij ), data set b j It can be regarded as the expert's understanding of indicator t j The right to speak of k experts for indicator t j The average recognition degree is recorded as 1-b j , where bj The formula is as follows:
[0025] b j =(b 1j +b 2j +...+b kj ) / k
[0026] Define the expert for indicator t j Uncertainty of knowledge, also known as cognitive blindness, is denoted by R j , where the formula is as follows:
[0027] R j =max(b 1j +b 2j +...+b kj )
[0028] Define k experts for indicator t j The overall recognition degree is denoted as x j , the formula is as follows:
[0029] x j =(1-b j )(1-R j )
[0030] Perform normalization to obtain the weight W of the indicator j , the formula is as follows:
[0031]
[0032] Furthermore, the method for determining the mass function in step S3 is:
[0033] A fuzzy comment set is established, and a Gaussian membership function is used to represent the fuzziness of each indicator level of the low-carbon transformation index of the electricity carbon market enterprise. The Gaussian membership function is:
[0034]
[0035] Among them, x is the fuzzy state quantification value of the node given by the expert, i.e., the score, μ is the center of the function, and σ is the standard deviation;
[0036] The index level is expressed in five levels, which are divided into N according to the index level. 1 (very bad), N 2 (poor), N 3 (Qualified), N 4 (Good), N 5 (Excellent), the mean values corresponding to the five different evaluation levels are μ = (1, 0.75, 0.5, 0.25, 0);
[0037] According to the Gaussian membership function, the degree to which the expert's evaluation of the evaluation index belongs to each index level is determined, and the center of the Gaussian membership function corresponding to the level level is substituted, and the membership functions are obtained as follows:
[0038]
[0039] By normalizing the membership function, we can get the mass function as follows:
[0040]
[0041] In the above formula, h = (1, 2, 3, 4, 5) represents five evaluation levels, m s is the sth expert pair index X k The mass function generated by the evaluation of .
[0042] Furthermore, the mass function correction method in step S4 includes:
[0043] Assume m i and m j are two independent pieces of evidence on the same recognition framework θ, namely, the mass function generated by the evaluation of a certain indicator by the i-th expert and the j-th expert, m 1 and m 2 The similarity coefficient is:
[0044]
[0045] Through the above function, the evidence m is calculated i The degree of support is:
[0046]
[0047] The evidence i The support of is compared with the evidence with the highest support among all the evidences, and the evidence m is obtained. i The credibility is:
[0048]
[0049] The calculated value of the evidence credibility Rel i As the correction coefficient, the modified mass function m' i (X k )as follows:
[0050] m′ i (X k )=Rel i ·m i (X k )
[0051] In the formula, i represents the i-th expert.
[0052] Furthermore, the calculation method of the P value of the enterprise low-carbon transformation evaluation result in step S5 is:
[0053] According to the DS evidence theory method, the evaluation information of each indicator is fused, and the fusion results are as follows:
[0054]
[0055] After integrating the underlying indicator comment information, the comprehensive evaluation performance is obtained through linear weighting according to the obtained indicator weights at all levels and the evidence fusion results, and the final evaluation level P value is determined according to the maximum membership principle:
[0056]
[0057] Among them, p is the final low-carbon transformation evaluation result of the enterprise, w k is the weight coefficient of each indicator calculated in step S2, m(X k ) is the mass function corresponding to each indicator.
[0058] The beneficial effects of the present invention are:
[0059] The method of the present invention avoids the high subjectivity that exists in the traditional method when evaluating the low-carbon transformation index of enterprises. The weight of each indicator is calculated by the structural entropy method, and the evidence source is corrected through the evidence theory and the evaluation of each indicator given by each expert, thereby ensuring the objectivity of the evaluation result to the greatest extent. At the same time, the method of the present invention introduces improved evidence theory, integrates the information sources of enterprises participating in the electricity market and the carbon market, fully considers the synergy between electricity and carbon, and realizes a comprehensive evaluation of the low-carbon transformation index of enterprises in the electricity-carbon market, and obtains the low-carbon transformation index value of enterprises in the electricity-carbon market, which can understand the low-carbon transformation effect of enterprises in the electricity-carbon market, and is conducive to promoting enterprises to carry out low-carbon transformation. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] Figure 1 These are the specific indicators included in the low-carbon transformation index evaluation system for electric carbon market enterprises of the present invention. DETAILED DESCRIPTION
[0061] In order to make the purpose, technical solutions and advantages of the invention clearer, the present invention is further described below with reference to the accompanying drawings.
[0062] The key terms in the present invention are described as follows:
[0063] Enterprise Low Carbon Transformation Index: It is an index that reflects the development of an enterprise’s low-carbon industry and an indicator for evaluating an enterprise’s low-carbon decision-making and behavior adjustment models.
[0064] Electricity-carbon joint market: is a concept involving electricity and carbon trading markets, mainly involving energy trading in the electricity market and carbon trading activities in the carbon emission market, as well as the relationship and joint development between the two.
[0065] Entropy weight method: It is an objective weighting method based on the principle of information entropy. It determines the weight of each indicator in the comprehensive evaluation by calculating its information entropy value. The method is not affected by subjective factors and mainly allocates weights based on the objective situation of the data.
[0066] DS Evidence Theory Method: Dempster / Shafer Evidence Theory (DS Evidence Theory), where DS is the abbreviation of the inventor's name. The method belongs to the field of artificial intelligence and was first applied in expert systems. It has the ability to process uncertain information. As an uncertain reasoning method, it meets weaker conditions than Bayesian probability theory and has the ability to directly express "uncertainty" and "not knowing".
[0067] mass function: mass is translated as mass. The function is a mass function or a basic probability distribution function, which is divided into a probability mass function and an initial mass function. In probability theory, the probability mass function (PMF) is the probability of a discrete random variable at each specific value. The difference between the probability mass function and the probability density function is that the probability density function is defined for continuous random variables.
[0068] The scheme of the present invention first constructs an enterprise low-carbon transformation index evaluation system, establishes a comprehensive evaluation system from the two aspects of enterprise carbon emission status and enterprise transformation potential, uses the structural entropy weight method to determine the weight of each indicator, and integrates the low-carbon transformation index of enterprises participating in multiple markets through the DS evidence theory method, thereby completing the comprehensive evaluation of the enterprise low-carbon transformation index. This method not only evaluates the various low-carbon transformation indicators of enterprises participating in the electricity market and the carbon market, but also takes into account the characteristics of the mutual correlation and mutual influence of various evaluation indicators of enterprises in the electricity-carbon joint market, and integrates the information of various indexes to obtain a comprehensive evaluation result. Compared with the qualitative evaluation method, this technical solution adopts evidence theory to evaluate the enterprise low-carbon transformation index more diversely. In addition, compared with the method that only considers the low-carbon transformation performance of enterprises, this technical solution comprehensively considers the synergy of electricity and carbon, integrates multiple information sources, and realizes the comprehensive evaluation of the low-carbon transformation index of enterprises in the electricity-carbon market.
[0069] A method for evaluating the low-carbon transformation index of electric carbon market enterprises specifically includes the following steps:
[0070] S1: Determine the low-carbon transformation index evaluation system for electricity carbon market enterprises.
[0071] The present invention focuses on the two key goals of promoting clean energy power generation and reducing carbon emissions, and establishes a low-carbon transformation index evaluation system from two dimensions: the current status of corporate carbon emissions and the potential for corporate transformation.
[0072] like Figure 1 As shown, in a specific embodiment, the low-carbon transformation index evaluation system of the present invention sets a total of sixteen evaluation indicators, and the sixteen evaluation indicators specifically include: carbon emissions from green electricity consumption, carbon emissions from thermal power consumption, carbon emissions from fossil energy consumption, carbon emissions from enterprise production, carbon capture and carbon storage, energy consumption, enterprise output value, free quota of carbon trading market, paid quota of carbon trading market, performance of carbon trading market, ability of green electricity trading market enterprises to independently produce renewable energy, green electricity in green electricity trading market, green certificates in green electricity trading market, performance of green electricity trading market, and forward-looking emission reduction plans of enterprises.
[0073] S2: The structural entropy weight method is used to determine the weight of each indicator in the index evaluation system.
[0074] The structural entropy weight method combines the Delphi method and the fuzzy analysis method with the entropy value method, thereby combining qualitative analysis with quantitative analysis to determine the indicator weights.
[0075] S21: First, collect expert opinions and form a subjective typical ranking table.
[0076] The experts first rank the importance of each indicator, specifically the importance of five first-level indicators. In a specific embodiment, the five first-level indicators include carbon emission indicators, energy consumption indicators, carbon market trading potential indicators, green electricity market trading potential indicators, and enterprise transformation potential indicators.
[0077] For the five first-level indicators of carbon emission index, energy consumption index, carbon market trading potential index, green electricity market trading potential index, and enterprise transformation potential index, the sorting array of the five first-level indicators given by the i-th expert is:
[0078] (a i1 ,a i2 ,...a i5 )
[0079] Among them: a in ,n=1,2...,5 represents the sorting order corresponding to the nth indicator after the i-th expert sorts the five first-level indicators.
[0080] For the six secondary indicators under the primary indicator carbon emission index, namely, carbon emission from green electricity consumption, carbon emission from thermal power consumption, carbon emission from fossil energy consumption, carbon emission from enterprise production, carbon capture & storage, and carbon emission quota, the sorted array of the six secondary indicators under the primary indicator carbon emission index given by the i-th expert is:
[0081]
[0082] in: It indicates the sorting order corresponding to the mth indicator after the i-th expert sorts the six secondary indicators under the first-level indicator carbon emission indicator.
[0083] The same goes for the other secondary indicators under the other primary indicators, forming a typical ranking table of primary and secondary indicators.
[0084] S22: Perform blind analysis on the typical ranking table and use entropy method to correct it to reduce subjectivity. The typical ranking table is quantitatively transformed through membership function, and the formula is as follows:
[0085]
[0086] Among them, χ(Ι) is the membership function; I is the expert's ranking value for a certain indicator; n is the actual maximum ranking number in the ranking group.
[0087] The number of experts ranking the index is a ij Substitute into formula (1) to obtain the membership data table b of the ranking number ij =χ(a ij ), data set b j It can be regarded as the expert's understanding of indicator t j The right to speak of k experts for indicator t j The average recognition degree is recorded as 1-b j , where formula (2) is as follows:
[0088] b j =(b 1j +b 2j +...+b kj ) / k
[0089] Define the expert for indicator t j Uncertainty of knowledge, also known as cognitive blindness, is denoted by R j , where the formula is as follows:
[0090] R j =max(b 1j +b 2j +...+b kj )
[0091] Define k experts for indicator t j The overall recognition degree is denoted as x j , where the formula is as follows:
[0092] x j =(1-b j )(1-Rj )
[0093] Finally, normalization is performed to obtain the weight W of the indicator. j , where the formula is as follows:
[0094]
[0095] S3: Establish a fuzzy comment set and transform the fuzzy semantics into a mass function.
[0096] In step S3, it is necessary to first establish a fuzzy comment set and construct a membership function. The membership function is to enhance the association between different system indicators. According to fuzzy set theory, the membership function can be used to determine the degree to which an object belongs to a certain concept, convert the evaluation language given by experts into fuzzy interval values, and defuzzify its evaluation. Therefore, the Gaussian membership function is used to represent the fuzziness of each indicator level of the low-carbon transformation index of the electricity carbon market enterprise. The Gaussian membership function is:
[0097]
[0098] Among them, e is a natural constant taking the value of 2.72, x is the fuzzy state quantization value of the node given by the expert (i.e., score), μ is the center of the function. In the present invention, the function center can be understood as the mean, σ is the standard deviation, and the standard deviation is calculated by combining the existing formula with the expert rating and the mean. The larger the σ value is, the higher the uncertainty of the risk level evaluation value given by the expert.
[0099] The index level is expressed in five levels, which are divided into N according to the index level. 1 (very bad), N 2 (poor), N 3 (Qualified), N 4 (Good), N 5 (Excellent), the corresponding mean is μ=(1, 0.75, 0.5, 0.25, 0).
[0100] According to the Gaussian membership function, the degree to which the expert's evaluation of the evaluation index belongs to each index level is determined, and the center of the Gaussian membership function corresponding to the level level is substituted into it, and the membership functions are obtained as follows:
[0101]
[0102] According to the membership function, a membership matrix can be obtained. The grade given by each expert for each indicator forms a scoring matrix. The membership function is combined with the scoring matrix to obtain a membership matrix. The membership matrix is used to calculate the degree to which the evaluation given by each expert belongs to a certain grade. For example, if an expert gives 1.6 points, the expert is more inclined to the second level. After substituting the scoring data into the membership function, the membership function is normalized.
[0103] Finally, the fuzzy semantics is converted into a mass function, and the membership function is normalized to obtain the mass function as follows:
[0104]
[0105] In the above formula, h = (1, 2, 3, 4, 5) represents five evaluation levels, m s is the sth expert pair index X k The mass function generated by the evaluation of .
[0106] S4: Evidence source correction.
[0107] When conducting evidence synthesis, evidence theory assumes that the importance of each evidence source is the same. However, in the evaluation of the enterprise low-carbon transformation index, due to the differences in expert knowledge and experience and subjective preferences, the contribution of different evidence sources to the performance level is different. Therefore, before conducting evidence fusion, it is necessary to correct the evidence source of qualitative evaluation information, that is, to correct the mass function of each indicator given by different experts.
[0108] This paper introduces the idea of Tanimoto measure and proposes a formula for measuring evidence similarity:
[0109] Assume m i and m j are two independent pieces of evidence on the same recognition framework θ, i.e., the mass function generated by the evaluation of a certain indicator by two experts, m 1 and m 2 The similarity coefficient is, where i and j represent the i-th expert and j-th expert respectively.
[0110]
[0111] Through the above function, the evidence m can be calculated i The degree of support is:
[0112]
[0113] The evidence i The support of is compared with the evidence with the highest support among all the evidences, then we can get evidence m iThe credibility is:
[0114]
[0115] The calculated value of the evidence credibility Rel i As the correction coefficient, the original evidence source is corrected as follows to obtain the corrected mass function m′ i (X k ):
[0116]
[0117] In the formula, i and j are used to represent the i-th and j-th experts.
[0118] S5: Improve DS evidence fusion and complete the evaluation model construction.
[0119] In response to the problems of Dempster's rule in the process of synthesizing evidence, Smarandache and Dezert believed that conflicting information is caused by conflicts between focal elements in the identification framework, and proposed a series of proportional conflict redistribution rules to redistribute conflicts in a certain proportion. Among them, PCR5 is currently considered to have better mathematical logic and synthesis effects, and has the best ability to handle conflicting information. The fusion results are as follows:
[0120]
[0121] After integrating the underlying indicator comment information, the comprehensive evaluation performance is obtained through linear weighting according to the obtained indicator weights at all levels and the evidence fusion results, and the final evaluation level is determined according to the maximum membership principle:
[0122] Among them, p is the final low-carbon transformation evaluation result of the enterprise, w k is the weight coefficient of each indicator calculated in step S2, m(X k ) is the mass function corresponding to each indicator.
[0123] After obtaining the P value of the enterprise's low-carbon transformation evaluation result, the enterprise's low-carbon transformation benefits can be learned based on the P value.
[0124] Finally, it should be noted that the contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field. The above description is only the preferred embodiment of the present invention and is not used to limit the present invention. Although the present invention is described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A method for evaluating the low-carbon transformation index of electricity and carbon market enterprises, characterized by: The method comprises the following steps: S1: Determine the evaluation indicators included in the low-carbon transformation index evaluation system for electricity and carbon market enterprises; S2: Use the structural entropy weight method to determine the weight coefficient W of each indicator in the index evaluation system of step S1 j ; S3: Establish a fuzzy comment set and convert the fuzzy semantics into a mass function; S4: Modify the mass function in step S3; S5: The weight coefficient W of each indicator determined according to step S2 j , and the mass function corrected in step S4, calculate the final low-carbon transformation evaluation result P value of the enterprise.
2. The method for evaluating the low-carbon transformation index of electric carbon market enterprises according to claim 1 is characterized in that: The weight coefficient W of each indicator in the S2 step j The determination method includes the following steps: S21: Collect expert opinions and form a subjective typical ranking table; Experts rank the importance of each indicator. The ranking array of the five first-level indicators given by the i-th expert is: (a i1 ,a i2 ,...a i5 ) Among them: a in ,n=1,2...,5 represents the sorting order corresponding to the nth indicator after the i-th expert sorts the five first-level indicators; For each of the six secondary indicators under the first-level indicator, the sorted array of the six secondary indicators under each of the first-level indicators given by the i-th expert is in: It represents the sorting order of the mth indicator after the i-th expert sorts the six secondary indicators under the first-level indicator; Sort the six secondary indicators under each primary indicator to form a typical ranking table of primary and secondary indicators; S22: Perform blind analysis on the typical ranking table of step S21, use entropy method to correct it, reduce subjectivity, and quantitatively transform the typical ranking table through membership function. The formula is as follows: Among them, χ(Ι) is the membership function; I is the expert's ranking value for a certain indicator; n is the actual maximum ranking number in the ranking group. The ranking number a of the experts for the indicator ij Substitute into the formula χ(Ι) to obtain the membership data table b of the sorted number ij =χ(a ij ), data group b j It can be regarded as the expert's j The right to speak of k experts for indicator t j The average recognition degree is recorded as 1-b j , where b j The formula is as follows: b j =(b 1j +b 2j +...+b kj ) / k Define expert for indicator t j Uncertainty of knowledge, also known as cognitive blindness, is denoted by R j , where the formula is as follows: R j =max(b 1j +b 2j +...+b kj ) Define k experts for indicator t j The overall recognition degree is recorded as x j , the formula is as follows: x j =(1-b j )(1-R j ) Perform normalization to obtain the weight W of the indicator j , the formula is as follows:
3. The method for evaluating the low-carbon transformation index of electric carbon market enterprises according to claim 1 is characterized in that: The method for determining the mass function in step S3 is: A fuzzy comment set is established, and a Gaussian membership function is used to represent the fuzziness of each indicator level of the low-carbon transformation index of electricity carbon market enterprises. The Gaussian membership function is: Among them, x is the fuzzy state quantitative value of the node given by the expert, i.e., the score, μ is the center of the function, and σ is the standard deviation; The five-level index level is used for expression, and is divided into N1 (very poor), N2 (poor), N3 (qualified), N4 (good), and N5 (excellent) according to the index level. The mean value corresponding to the five different evaluation levels is μ = (1, 0.75, 0.5, 0.25, 0); According to the Gaussian membership function, the degree to which the experts' evaluation of the evaluation indicators belongs to each index level is determined, and the center of the Gaussian membership function corresponding to the level level is substituted into the membership function, and the membership functions are: Normalize the membership function and get the mass function as follows: In the above formula, h = (1, 2, 3, 4, 5) represents five evaluation levels, m s is the sth expert pair index X k The mass function generated by the evaluation of .
4. The method for evaluating the low-carbon transformation index of electric carbon market enterprises according to claim 1 is characterized in that: The mass function correction method in step S4 includes: Let m i and m j They are two independent pieces of evidence on the same recognition framework θ, namely, the mass function generated by the evaluation of a certain indicator by the i-th expert and the j-th expert. The similarity coefficient of m1 and m2 is: Through the above function, we can calculate the evidence m i The degree of support is: The evidence i The support degree of the evidence is compared with the evidence with the highest support degree among all the evidences, and the evidence m is obtained. i Credibility is: The calculated value of the evidence credibility Rel i As the correction coefficient, the corrected mass function m' i (X k )as follows: m’ i (X k )=Rel i ·m i (X k ) Where i represents the i-th expert.
5. The method for evaluating the low-carbon transformation index of electric carbon market enterprises according to claim 1 is characterized in that: The calculation method of the P value of the enterprise low-carbon transformation evaluation result in step S5 is: Based on the DS evidence theory method, the evaluation information of each indicator is fused, and the fusion results are as follows: After integrating the underlying indicator comment information, calculate the enterprise low-carbon transformation evaluation index P value: Among them, p is the final low-carbon transformation evaluation result of the enterprise, w k is the weight coefficient of each indicator calculated in step S2, m(X k ) is the mass function corresponding to each indicator.
Citation Information
Patent Citations
Comprehensive risk assessment method and system for expressway operating enterprises
CN114936735A
Enterprise benefit level determination method and system and electronic equipment
CN115907563A
Low-carbon transformation service business model evaluation method based on BWM and improved entropy-TOPSIS method
CN116485240A
