Building material industry enterprise ESG evaluation method, electronic device and readable storage medium

Abstract

The invention discloses a building material industry enterprise ESG evaluation method, an electronic device and a readable storage medium, and the method comprises the steps: obtaining the parameter information of a to-be-evaluated target enterprise, determining the first evaluation data and second evaluation data of the to-be-evaluated target enterprise according to the parameter information, adjusting the first evaluation data according to the second evaluation data to obtain a final evaluation result of the to-be-evaluated target enterprise; the building material industry enterprise ESG evaluation model is established, evaluation is carried out according to the evaluation indexes of the industry and the relevant parameters of the enterprise, and evaluation is comprehensively carried out by fitting the evaluation factors of the enterprise and the evaluation factors of the enterprise in the whole industry in the evaluation process. In the evaluation process, all application enterprises can be quickly graded through a unified evaluation model, so that the grading efficiency is improved, the grading time is shortened, and the labor cost is reduced.

Description

Technical Field

[0001] The present application belongs to the field of data analysis technology, and in particular, relates to an ESG evaluation method, an electronic device and a readable storage medium for enterprises in the building materials industry. Background Art

[0002] Environmental, social and corporate governance (ESG) generally refers to the assessment of the sustainability of corporate operations and its impact on social values ​​from the three dimensions of environment, society and corporate governance. On November 1, 2023, the China Building Materials Federation organized a seminar on ESG (Environment, Social and Governance) in the building materials industry. The meeting systematically introduced the research background and work progress of the two documents, "Research Report on ESG Development in China's Building Materials Industry (2023)" and "Guidelines for Disclosure of Environmental, Social and Corporate Governance (ESG) Information in the Building Materials Industry", and required the building materials industry to strengthen the disclosure of ESG information and promote the market's transformation to "sustainable development".

[0003] At present, in the construction and building materials industry, most of the information in the ESG rating and award and related certificate review process is rated through active declarations by various enterprises and manual investigations by the review units. In the rating process, due to the large number of indicators and manufacturers involved in the construction and building materials industry, in most cases, the review agency needs to classify and rate the various parameter indicator sets and industry indicators reported by the enterprise one by one. The rating is completely dependent on manual work, and there is no effective solution for rapid rating of batches of enterprises. Patent CN116664016B discloses a screening method, device, electronic device and readable storage medium for ESG sub-topics. The main technology is to simplify the rating procedure; Patent CN117634997B discloses a deep neural network method for positioning and mapping the value chain assets of an enterprise organization, and discloses a method for evaluating enterprises through neural networks. However, none of the above technical solutions provide technical solutions for how to rate a large number of enterprises from the perspective of review. Summary of the invention

[0004] In order to make up for the above technical defects, this application proposes an ESG evaluation method, an electronic device and a readable storage medium for enterprises in the building materials industry, and the technical solution of the method includes:

[0005] A method for evaluating ESG of enterprises in the building materials industry, comprising: obtaining parameter information of a target enterprise to be evaluated, determining first evaluation data and second evaluation data of the target enterprise to be evaluated according to the parameter information, and adjusting the first evaluation data according to the second evaluation data to obtain a final evaluation result of the target enterprise to be evaluated; wherein the first evaluation data acquisition method comprises: constructing an industry evaluation database based on evaluation indicators; mapping the parameter information of the target enterprise to be evaluated to the evaluation database, obtaining standardized evaluation information of the target enterprise to be evaluated, and obtaining the first evaluation data according to the evaluation information; the second evaluation data acquisition method comprises: clustering and sorting the parameter information of all the enterprises to be evaluated according to clustering characteristics, and obtaining the normal distribution results of all the enterprises to be evaluated under each cluster; establishing a clustering database of all the enterprises to be evaluated according to the clustering characteristics and the normal distribution results, and assigning corresponding weights to each enterprise according to the normal distribution results of each enterprise under each cluster; substituting the target enterprise to be evaluated into the clustering database, obtaining the corresponding weight of the enterprise, and obtaining the second evaluation data according to the corresponding weight.

[0006] Furthermore, the clustering characteristic is meeting the ESG requirements of the building materials industry, and no less than one-fifth of the companies to be reviewed have this characteristic.

[0007] Furthermore, the corresponding weights are assigned to the various enterprises in the manner of: the top 10% are assigned a weight of 1.2, the middle 80% are assigned a weight of 1.0, and the bottom 10% are assigned a weight of 0.8.

[0008] Furthermore, the first evaluation data acquisition process also includes: determining a mapping ratio between the target enterprise parameter information to be evaluated and the evaluation database, using the mapping ratio as an evaluation factor, and using the evaluation information×the evaluation factor as the first evaluation data.

[0009] Furthermore, the process of adjusting the first evaluation factor according to the second evaluation factor includes: converting the value of the second evaluation factor into a percentage and then multiplying the percentage by the first evaluation factor.

[0010] Furthermore, the review information includes the number of review indicators corresponding to the target enterprise to be reviewed and the review results of each review indicator; the second evaluation factor includes the cluster type of the target enterprise to be reviewed, the number of review indicators under each cluster and the weight score under each cluster.

[0011] Furthermore, in the process of adjusting the first evaluation data according to the second evaluation data to obtain the final evaluation result of the target enterprise to be evaluated, it also includes a process of adjusting the second evaluation data through a compensation factor, and the compensation parameter acquisition process includes: performing weight compensation for 5% of enterprises with the largest number of evaluation indicators and cluster types.

[0012] Furthermore, the weight compensation X range includes 1.2<X≤1.5.

[0013] An electronic device comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of any of the methods described above are implemented.

[0014] A readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of any of the methods described above are implemented.

[0015] This application establishes an ESG evaluation model for building materials industry enterprises, conducts evaluations based on the industry's evaluation indicators and the company's own relevant parameters, and conducts a comprehensive evaluation by fitting the company's own evaluation factors and the company's evaluation factors in the entire industry. During the evaluation process, a unified evaluation model can be used to quickly rate all applicant companies, improve rating efficiency, and shorten rating time and labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a schematic diagram of a method flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0018] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0019] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0020] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0021] This application proposes an ESG evaluation method, electronic device and readable storage medium for enterprises in the building materials industry. The evaluation is conducted based on the industry's evaluation indicators and the enterprise's own relevant parameters. During the evaluation process, the evaluation is conducted comprehensively by fitting the enterprise's own evaluation factors and the enterprise's evaluation factors in the entire industry. During the evaluation process, a unified evaluation model can be used to quickly rate all applicant enterprises, thereby improving rating efficiency and shortening rating time and labor costs.

[0022] Reference Figure 1 , a method for evaluating ESG of building materials industry enterprises, obtaining parameter information of target enterprises to be evaluated, determining first evaluation data and second evaluation data of the target enterprises to be evaluated according to the parameter information, adjusting the first evaluation data according to the second evaluation data to obtain the final evaluation result of the target enterprises to be evaluated; wherein, the first evaluation data acquisition method includes: constructing an industry evaluation database based on evaluation indicators; mapping the parameter information of the target enterprises to be evaluated to the evaluation database, obtaining standardized evaluation information of the target enterprises to be evaluated, and obtaining the first evaluation data according to the evaluation information; the second evaluation data acquisition method includes: clustering and sorting the parameter information of all enterprises to be evaluated according to clustering characteristics, obtaining the normal distribution results of all enterprises to be evaluated under each cluster; establishing a clustering database of all enterprises to be evaluated according to the clustering characteristics and the normal distribution results, and assigning corresponding weights to each enterprise according to the normal distribution results of each enterprise under each cluster; substituting the target enterprise to be evaluated into the clustering database, obtaining the corresponding weight of the enterprise, and obtaining the second evaluation data according to the corresponding weight. In this embodiment, in order to improve the review rate in the process of enterprise ESG review and reduce the cost of human audit, this embodiment adopts the method of establishing a corresponding review model for rating. During the modeling process, a corresponding industry review database is established based on the characteristics of the building materials industry. The industry review indicators generally refer to the national standards, industry standards or enterprise standards in this field. Generally speaking, the main key review indicator framework in the building materials industry rating includes 3 themes, 13 topics and 33 special topics, as shown in Table 1.

[0023] Table 1 Hierarchical structure and weights of key issues in ESG rating of building materials industry

[0024]

[0025] On the basis of the above framework, the various indicators of enterprises are further refined, and classified and reviewed according to the individual conditions of each enterprise. For details, please refer to relevant standard documents such as "T / CBMF 268.2-2024 Environmental, Social and Corporate Governance (ESG) Guidelines for Building Materials Industry Enterprises". In the process of obtaining the first evaluation data, there are two ways: the review unit can actively collect or the reporting enterprise can submit. If the review unit actively collects, artificial intelligence can be used for auxiliary collection, such as establishing a special review model, setting up corresponding model libraries according to the type of enterprise, and establishing matching relationships for relevant words in the model library. Based on the collected public information, according to the frequency of occurrence of the subject words, they are mapped with the important issues of the industry to form effective information, and then the first evaluation data is extracted based on the effective information. In this process, there are many artificial intelligence related models, which will not be repeated here. In the process of obtaining the first evaluation data from the effective information, it can be automatically extracted by training a neural network or manually extracted by artificial denoising, which shall prevail.

[0026] The review indicators of this application are used as the basis of the industry review database in this field. On the basis of the previous manual review and scoring, a database model is further established. The review results of the enterprise to be reviewed are obtained according to the model indicators and review standards, and the parameter information of the target enterprise to be reviewed is mapped to the review database to obtain the standardized review information of the target enterprise to be reviewed. However, this application is not a search model, and it is not a table review after the enterprise submits the relevant parameter filling form. Since the enterprises to be reviewed are different in terms of geographical location, scale, number of people, turnover, R&D investment, environmental protection investment, etc. in the industry, the simple table review and scoring method can reflect the ESG standards of the enterprises to be reviewed to a certain extent, but it cannot rule out the situation that some indicators of individual enterprises are vacant, and only the superior indicators are reported to get a better evaluation, but all indicators of all enterprises must be met at this stage and are not displayed. Blind deductions will reduce the accuracy of the entire ESG review. Therefore, this application further introduces invisible evaluation data, i.e., the second evaluation data, based on the current indicator review of the first evaluation data. The second evaluation data is obtained by clustering, classifying and sorting the enterprises, extracting clustering features according to industry characteristics and sorting them under each feature, obtaining each enterprise under each cluster according to the enterprise score, obtaining the enterprise normal distribution under the clustering feature index according to the enterprise score interval, and establishing a clustering database of all enterprises to be reviewed based on the clustering features and normal distribution results, and assigning corresponding weights to each enterprise according to the normal distribution results of each enterprise under each cluster. On the basis of the above embodiment, the clustering feature meets the ESG requirements of the building materials industry, and no less than one-fifth of the enterprises to be reviewed have this feature. In this embodiment, the distribution of each enterprise under each clustering feature is obtained through multiple clustering, and each enterprise is satisfied as much as possible that it has a suitable classification and scoring interval, which is convenient for evaluating the overall strength of the enterprise. This application changes the original subjective judgment review method to an objective indicator such as the enterprise's own indicators and the specific position of the enterprise in the industry, eliminating subjective influences and improving the objectivity of the review.

[0027] Based on one or more of the above embodiments, the method of assigning corresponding weights to each enterprise includes: assigning a weight of 1.2 to the top 10% of the ranking, a weight of 1.0 to the middle 80% of the ranking, and a weight of 0.8 to the bottom 10%. In this embodiment, the corresponding industry ranking position of each enterprise under the clustering feature is obtained according to the clustering result, that is, the normal distribution interval, and the weight is assigned to the enterprise according to the distribution interval of the industry.

[0028] On the basis of one or more of the above embodiments, the first evaluation data acquisition process further includes: determining the mapping ratio of the parameter information of the target enterprise to be reviewed and the review database, using the mapping ratio as the review factor, and using the review information × the review factor as the first evaluation data. In this implementation, in order to further reflect the implementation strength and coverage of the ESG standards by the enterprise to be reviewed, this application further uses the proportion of the enterprise's satisfaction rate for the review indicators as the review factor to further improve the accuracy of the review.

[0029] Based on one or more of the above embodiments, the process of adjusting the first evaluation factor according to the second evaluation factor includes: converting the value of the second evaluation factor into a percentage and then multiplying the percentage by the first evaluation factor.

[0030] Based on one or more of the above embodiments, the review information includes the number of review indicators corresponding to the target enterprise to be reviewed and the review results of each review indicator; the second evaluation factor includes the cluster type of the target enterprise to be reviewed, the number of review indicators under each cluster and the weight score under each cluster.

[0031] On the basis of one or more of the above embodiments, in the process of adjusting the first evaluation data according to the second evaluation data to obtain the final evaluation result of the target enterprise to be reviewed, the process of adjusting the second evaluation data by a compensation factor is also included, and the compensation parameter acquisition process includes: weight compensation for the 5% of enterprises with the largest number of review indicators and cluster types. On the basis of the above review, in order to further encourage enterprises in this industry to develop comprehensively, balanced but not outstanding, this application further adopts the method of compensation weights to make overall adjustments to enterprises with relatively comprehensive industry indicators, and use review factors to comprehensively compensate enterprise scores. As an evaluation factor that reflects the degree of fit between enterprises and industry indicators, the review factor can comprehensively compensate for the weight of relatively comprehensive enterprises to improve the comprehensiveness of the review dimension.

[0032] Based on one or more of the above embodiments, the range of the weight compensation X includes 1.2<X≤1.5.

[0033] The present application also proposes an electronic device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in any of the above embodiments are implemented.

[0034] The present application also proposes a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0035] The protection scope of the present invention is not limited thereto, and any change or replacement of the technical solution that can be thought of without creative work should be included in the protection scope of the present invention. The protection scope of the present invention shall be based on the protection scope defined in the claims.

Claims

1. An ESG evaluation method for building materials industry enterprises, characterized in that: Acquire parameter information of the target enterprise to be reviewed, determine first evaluation data and second evaluation data of the target enterprise to be reviewed according to the parameter information, and adjust the first evaluation data according to the second evaluation data to obtain a final evaluation result of the target enterprise to be reviewed; Wherein, the first evaluation data acquisition method includes: Build an industry review database based on review indicators; Mapping the parameter information of the target enterprise to be reviewed to the review database, obtaining standardized review information of the target enterprise to be reviewed, and obtaining first evaluation data according to the review information; The second evaluation data acquisition method includes: The parameter information of all the enterprises to be reviewed is clustered and sorted according to the clustering characteristics, and the normal distribution results of all the enterprises to be reviewed under each cluster are obtained; A clustering database of all enterprises to be reviewed is established based on clustering characteristics and normal distribution results, and corresponding weights are assigned to each enterprise based on the normal distribution results of each enterprise under each cluster; The target enterprise to be reviewed is substituted into the clustering database, the corresponding weight of the enterprise is obtained, and the second evaluation data is obtained according to the corresponding weight.

2. The method according to claim 1, characterized in that The clustering characteristic is meeting the ESG requirements of the building materials industry, and no less than one-fifth of the companies to be reviewed have this characteristic.

3. The method according to claim 1, characterized in that The method of allocating corresponding weights to each enterprise includes: allocating a weight of 1.2 to the top 10% in the ranking, a weight of 1.0 to the middle 80% in the ranking, and a weight of 0.8 to the bottom 10% in the ranking.

4. The method according to claim 1, characterized in that: The first evaluation data acquisition process also includes: determining the mapping ratio between the target enterprise parameter information to be evaluated and the evaluation database, using the mapping ratio as the evaluation factor, and using the evaluation information×the evaluation factor as the first evaluation data.

5. The method according to claim 3, characterized in that: The process of adjusting the first evaluation factor according to the second evaluation factor includes: converting the value of the second evaluation factor into a percentage and then multiplying the percentage by the first evaluation factor.

6. The method according to claim 5, characterized in that The review information includes the number of review indicators corresponding to the target enterprise to be reviewed and the review result of each review indicator; the second evaluation factor includes the cluster type of the target enterprise to be reviewed, the number of review indicators under each cluster and the weight score under each cluster.

7. The method according to claim 6, characterized in that The process of adjusting the first evaluation data according to the second evaluation data to obtain the final evaluation result of the target enterprise to be evaluated also includes a process of adjusting the second evaluation data through a compensation factor. The compensation parameter acquisition process includes: performing weight compensation for 5% of enterprises with the largest number of evaluation indicators and cluster types.

8. The method according to claim 7, characterized in that The weight compensation X range includes 1.2<X≤1.

5.

9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores a program or an instruction that can be run on the processor, and when the program or the instruction is executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images