Environmental information disclosure evaluation method based on environmental information disclosure text of banking industry

Abstract

The present invention relates to the technical field of environmental information disclosure assessment, and discloses an environmental information disclosure assessment method based on the environmental information disclosure text of the banking industry, comprising: obtaining the environmental information disclosure text of a bank to be assessed; using the environmental information disclosure text to calculate the basic score of a preset basic indicator in a preset environmental information disclosure indicator system; based on a funnel analysis method, calculating the funnel loss rate of the basic indicator; using the funnel loss rate and the basic score, calculating the first environmental information disclosure score of the basic indicator; based on a hierarchical analysis method, calculating the basic weight of the basic indicator; based on an entropy weight method, calculating the revised weight coefficient of the basic indicator, and using the revised weight coefficient and the basic weight to calculate the fitting weight of the basic indicator; using the fitting weight and the first environmental information disclosure score, calculating the second environmental information disclosure score of the basic indicator.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental information disclosure assessment, and in particular to an environmental information disclosure assessment method based on banking environmental information disclosure texts. Background Art

[0002] At present, the disclosure of environmental information in the banking industry is in its early stages. The field that can be used as a reference is the ESG disclosure assessment of listed companies. There are already some relevant ESG disclosure assessment methods in this field. However, simply referring to the aforementioned ESG disclosure assessment method is not suitable for the environmental information disclosure assessment of the banking industry. The specific reason is that the aforementioned ESG disclosure assessment method has the following limitations:

[0003] 1. ESG disclosure assessment uses a single weight calculation system, without considering the horizontal differences caused by the horizontal differences in the characteristics of the indicators;

[0004] 2. There is a lack of effective weighting improvement methods for ESG disclosure assessments of indicators with high disclosure value but low disclosure volume (e.g., carbon information);

[0005] 3. ESG disclosure assessment focuses on three dimensions (environment, society, and governance), but environmental information disclosure assessment only focuses on one dimension (environment); compared with the assessment of ESG disclosure level, the assessment of environmental information disclosure level requires more detailed and in-depth assessment requirements.

[0006] Therefore, there is currently a lack of effective assessment methods for the level of environmental information disclosure in the banking industry.

[0007] Therefore, the prior art needs to be improved. Summary of the invention

[0008] In view of the defects of the prior art, the present invention provides an environmental information disclosure evaluation method based on the environmental information disclosure text of the banking industry, aiming to solve the technical problem of the current lack of effective evaluation methods to evaluate the environmental information disclosure level of the banking industry.

[0009] The technical solution adopted by the present invention to solve the above technical problems is as follows:

[0010] In a first aspect, the present invention provides an environmental information disclosure evaluation method based on the environmental information disclosure text of the banking industry, comprising the steps of:

[0011] Obtain the environmental information disclosure text of the bank to be assessed;

[0012] Using the environmental information disclosure text, calculate and obtain a basic score for a preset basic indicator in a preset environmental information disclosure indicator system;

[0013] Based on the funnel analysis method, the funnel loss rate of the basic indicator is calculated;

[0014] Using the funnel loss rate and the basic score, calculate the first environmental information disclosure score of the basic indicator;

[0015] Based on the hierarchical analysis method, the basic weights of the basic indicators are calculated;

[0016] Based on the entropy weight method, a modified weight coefficient of the basic indicator is calculated, and the fitting weight of the basic indicator is calculated using the modified weight coefficient and the basic weight;

[0017] The second environmental information disclosure score of the basic indicator is calculated using the fitting weight and the first environmental information disclosure score.

[0018] In some embodiments, the method further comprises the step of: evaluating the environmental information disclosure level of the bank to be evaluated based on the second environmental information disclosure score.

[0019] In some embodiments, the basic indicators include: carbon footprint disclosure, the number of stress-tested industries, and whether carbon dioxide emission reduction information is disclosed.

[0020] In some embodiments, the calculation formula of the funnel loss rate is:

[0021] L j =(b j -b j-1 ) / b j-1 *100%,

[0022] Among them, L j is the funnel loss rate, b j-1 b) the total number of disclosures of all the basic indicators reaching level j-1; j The total number of disclosures of all the basic indicators reaching level j.

[0023] In some embodiments, the step of calculating the modified weight coefficient of the basic indicator based on the entropy weight method, and calculating the fitting weight of the basic indicator using the modified weight coefficient and the basic weight includes:

[0024] Based on the type of the bank to be evaluated, the bank to be evaluated is classified to obtain a first classification number of the bank to be evaluated classified by type; using the first classification number, based on the entropy weight method, a first weight coefficient of the basic indicator is calculated;

[0025] Based on the geographical area of ​​the bank to be evaluated, the bank to be evaluated is classified to obtain a second classification number of the bank to be evaluated classified by geographical area; using the second classification number, based on the entropy weight method, a second weight coefficient of the basic indicator is calculated; wherein the first weight coefficient and the second weight coefficient are the modified weight coefficients;

[0026] The fitting weight of the basic index is calculated using the first weight coefficient, the second weight coefficient, and the basic weight.

[0027] In some embodiments, the method further comprises:

[0028] Step A: integrating the environmental information disclosure text into a text to be processed; performing text preprocessing on the text to be processed to obtain a processed text; counting the words in the processed text and the word frequencies of the words; performing vectorization processing on the words and the word frequencies based on a text vectorization algorithm and storing them to obtain a disclosure dictionary;

[0029] Step B: Obtain the new environmental information disclosure text, repeat step A, and obtain the updated disclosure dictionary.

[0030] In some embodiments, the method further comprises:

[0031] Based on the entity recognition algorithm, using the environmental information disclosure text of the bank A to be evaluated, the first specificity S1 of the bank A to be evaluated is calculated;

[0032] Counting the first occurrence frequency of the preset core disclosure words in the environmental information disclosure text of the bank A to be evaluated, and counting the second occurrence frequency of the core disclosure words in the environmental information disclosure texts of all the banks to be evaluated;

[0033] According to the value of the first occurrence frequency, n core disclosure words are selected from high to low, and the second specificity of the bank A to be evaluated is calculated using the first occurrence frequency and the second occurrence frequency; the calculation formula of the second specificity of the bank A to be evaluated is:

[0034]

[0035] Wherein, S2 is the second specificity of the bank A to be evaluated; c f is the first occurrence frequency of the core disclosure word c in the environmental information disclosure text of the bank A to be evaluated; C f is the second occurrence frequency of the core disclosure word c in the environmental information disclosure texts of all the banks to be evaluated; n is the total number of the core disclosure words;

[0036] The fitting specificity of the bank A to be evaluated is calculated using the first specificity and the second specificity; the calculation formula for the fitting specificity of the bank A to be evaluated is:

[0037]

[0038] Wherein, S is the fitting specificity of the bank A to be evaluated.

[0039] In a second aspect, the present invention provides an environmental information disclosure evaluation device based on a banking environmental information disclosure text, comprising:

[0040] An acquisition unit, used to acquire the environmental information disclosure text of the bank to be assessed;

[0041] A basic score calculation unit, used to calculate the basic score of a preset basic indicator in a preset environmental information disclosure indicator system using the environmental information disclosure text;

[0042] A funnel loss rate calculation unit, used to calculate the funnel loss rate of the basic indicator based on the funnel analysis method;

[0043] A first environmental information disclosure score calculation unit, configured to calculate a first environmental information disclosure score of the basic indicator by using the funnel loss rate and the basic score;

[0044] A basic weight calculation unit, used for calculating the basic weight of the basic indicator based on the hierarchical analysis method;

[0045] A fitting weight calculation unit, used to calculate the modified weight coefficient of the basic indicator based on the entropy weight method, and calculate the fitting weight of the basic indicator using the modified weight coefficient and the basic weight;

[0046] The second environmental information disclosure score calculation unit is used to calculate the second environmental information disclosure score of the basic indicator by using the fitting weight and the first environmental information disclosure score.

[0047] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the above-mentioned environmental information disclosure assessment method based on the environmental information disclosure text of the banking industry.

[0048] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned environmental information disclosure assessment method based on the banking industry environmental information disclosure text.

[0049] Beneficial effects: The present invention focuses on the proportion of hierarchical disclosure losses of indicators related to core carbon information, and uses this proportion to correct the normalization method of hierarchical indicators, so as to better measure the information value of difficult disclosure indicators in the early stage of disclosure; in terms of weight calculation, dual-system weight calculation is adopted, and the basic weight calculation in the hierarchical analysis method is improved by adding entropy value weighting of two dimensions (bank type and geographical area), and the final fitting weight is calculated, which not only measures the relative importance between basic indicators, but also combines the degree of disclosure difference of each basic indicator in the above two dimensions, so as to better overcome the problem of difficulty in evaluating the disclosure level caused by the disclosure characteristics of different basic indicators. Therefore, compared with the existing technology, this method can effectively quantify and evaluate the level of environmental information disclosure in the banking industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative work.

[0051] Figure 1 The present invention is a flowchart of the steps of an environmental information disclosure assessment method based on the environmental information disclosure text of the banking industry in some embodiments of the present invention.

[0052] Figure 2 This is a sub-step flowchart of step S600 of an environmental information disclosure assessment method based on banking environmental information disclosure text in some embodiments of the present invention.

[0053] Figure 3 The present invention is a block diagram of the principle of an environmental information disclosure assessment device based on the environmental information disclosure text of the banking industry in some embodiments of the present invention.

[0054] Figure 4 The present invention is a principle block diagram of a fitting weight calculation unit of an environmental information disclosure evaluation device based on banking environmental information disclosure text in some embodiments of the present invention.

[0055] Figure 5 The present invention is a block diagram of a computer device in some embodiments of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] Those skilled in the art will appreciate that, unless expressly stated, the singular forms "one", "above", "aforesaid", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when an element is referred to as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0058] Those skilled in the art will appreciate that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the field to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0059] Those skilled in the art will appreciate that the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0060] It should be understood that the sequence numbers and sizes of the steps in the present invention do not mean the order of execution. The execution order of each process is determined by its function and internal logic, and should not constitute any limitation to the present invention.

[0061] First, the present invention improves the traditional single-system weight evaluation system, uses a dual-system weight evaluation system, and adds funnel loss weight analysis considering the impact of carbon information and investment and financing activities on the environment, thereby measuring the performance of different types of banks and banks in different regions in regulating carbon emissions and achieving carbon neutrality. Secondly, the present invention produces a dynamically updated disclosure dictionary based on relevant environmental information disclosure texts. Finally, on the basis of evaluating the environmental information disclosure level of banks through a dual-system weight evaluation system, the present invention innovates the traditional natural language analysis (NLP) model based on relevant environmental information disclosure texts, adds an evaluation of the specificity of environmental information disclosure texts, and thus tracks the time trend of disclosure characteristics of different banks to analyze the dynamic development of environmental information disclosure in the national banking industry, thereby overcoming the problem that traditional text evaluation models only have static characteristics and capturing the dynamic development level of environmental information disclosure.

[0062] like Figure 1 As shown, the present invention provides an environmental information disclosure evaluation method based on the environmental information disclosure text of the banking industry, and the method comprises the steps of:

[0063] S100. Obtain the environmental information disclosure text of the bank to be assessed.

[0064] Furthermore, the banks to be assessed include all types of banks, such as state-owned banks, joint-stock banks, city commercial banks, rural commercial banks, foreign banks, village banks, and private banks, etc.; they also include banks at all levels, such as head offices, branches, and sub-branches, etc. The environmental information disclosure text is the report on the environmental information of the bank to be assessed, and the specific acquisition methods include bank website search, social media query, and online search engine search, etc., which are not limited here.

[0065] Furthermore, after obtaining the environmental information disclosure texts of the banks to be evaluated, each bank to be evaluated (including the head office, branches, and sub-branches) is recorded and stored to form a "List of Banks" including the information of each bank to be evaluated; and the environmental information disclosure text status of each bank to be evaluated (including whether the text has been published) is recorded and stored to form a "List of Environmental Information Disclosure Texts of Banks" including the information of each bank to be evaluated and its environmental information disclosure texts.

[0066] like Figure 1 As shown, the method also includes the steps of:

[0067] S200: Using the environmental information disclosure text, calculate and obtain a basic score of a preset basic indicator in a preset environmental information disclosure indicator system.

[0068] Furthermore, the preset environmental information disclosure indicator system may include but is not limited to three criteria layers: disclosure quality, disclosure willingness, and disclosure advancement.

[0069] Disclosure quality may include but is not limited to: whether to index the disclosure recommendations for the banking industry in the TCFD, whether to refer to the "Guidelines for Environmental Information Disclosure by Financial Institutions" (JR / T 0227-2021), carbon footprint disclosure, the proportion of disclosed green credit, the quantity described by the exact numbers in the indicators, whether to disclose carbon dioxide emission reduction information, and whether to disclose ammonia nitrogen emission reduction information and other basic indicators.

[0070] The willingness to disclose may include, but is not limited to, basic indicators such as whether the head office discloses, the number of cities where banks that publish environmental information reports in a certain year are located, whether disclosure is made for two consecutive years, the frequency of disclosure (quarterly, annual, semi-annual), whether the disclosure time is the first half of the following year, and whether it is an independent environmental information disclosure report.

[0071] Disclosure of advancement may include, but is not limited to: whether a specific methodology for carbon footprint measurement is provided (Partnership for Carbon Accounting Finance (PCAF) methodology), whether scenario analysis or stress testing of environmental impacts and risks of key industries is conducted, the number of stress test industries, whether it belongs to a regional innovation pilot institution or pilot frontier, disclosure of carbon emissions generated by investment and financing activities, and disclosure of basic indicators such as the number of industries covered by carbon emissions generated by investment and financing activities.

[0072] In some embodiments, disclosure quality may include but is not limited to three sub-dimensions: disclosure standards and specifications, the degree of quantification of basic information, and the degree of quantification of overall emission reduction information disclosure. Disclosure willingness may include but is not limited to three sub-dimensions: regional disclosure willingness, continuity of disclosure, and timeliness of disclosure. Disclosure advancement may include but is not limited to three sub-dimensions: advancement of disclosure methods, participation in the design of industry disclosure standards, and disclosure of environmental impacts of investment and financing activities. Each sub-dimension may include one or more basic indicators.

[0073] In some embodiments, disclosure quality may include 6 sub-dimensions and a total of 35 basic indicators, disclosure willingness may include 5 sub-dimensions and a total of 8 basic indicators, and disclosure advancement may include 6 sub-dimensions and a total of 21 basic indicators.

[0074] Furthermore, after obtaining the environmental information disclosure text, it is necessary to use the environmental information disclosure text to fill in the basic score of the basic indicator according to the type of the basic indicator. The types of basic indicators include: binary variables, segmented variables, and continuous variables. For example, the basic indicator "Whether to index the disclosure recommendations for the banking industry in TCFD" is a binary variable (yes, the value is 1; no, the value is 0); the basic indicator "carbon footprint disclosure" is a segmented variable (not disclosed, the value is 0; disclosure reaches scope 1, the value is 1; disclosure reaches scope 2, the value is 2; disclosure reaches scope 3, the value is 3); the basic indicator "disclosed green credit ratio" is a continuous variable (the range of values ​​is 0-100%, for example, 1.2%).

[0075] like Figure 1 As shown, the method also includes the steps of:

[0076] S300. Based on the funnel analysis method, the funnel loss rate of the basic indicator is calculated.

[0077] For banks as financial intermediaries, not only will the bank's own business activities have an impact on the environment, but the impact of the enterprises it invests in and finances on the environment is also related to the bank itself, so specific environmental information disclosure assessment requirements are required for the investment and financing environment of enterprises. Carbon emission information from investment and financing activities is a key indicator to measure the performance of banks in regulating carbon emissions and achieving carbon neutrality, so in environmental information disclosure, the most important thing is the disclosure and quantitative disclosure of indicators related to carbon information. For example, the basic indicator "carbon footprint disclosure" includes three levels: scope one, scope two, and scope three; carbon footprint disclosure reaching scope three is the most difficult but the most important, and the proportion of banks that reach scope three is relatively low. The less a bank discloses a basic indicator, the more difficult it is to disclose the basic indicator, and the greater the disclosure willingness and disclosure value measured by the disclosure of the indicator.

[0078] Therefore, the present invention focuses on the proportion of hierarchical disclosure losses of indicators related to core carbon information, and uses this proportion to correct the normalization method of hierarchical indicators, so as to better measure the information value of high-difficulty disclosure indicators in the early stage of disclosure.

[0079] Furthermore, if the disclosure of basic indicator i includes n levels: level zero (completely undisclosed), level one, level two, level three, ..., level j, ..., level n (for example, the basic indicator "carbon footprint disclosure" includes three levels: scope one, scope two, and scope three), then the normalized basic score S of the jth level of basic indicator i is j The calculation formula is:

[0080]

[0081] Where j = 0, 1, 2, ..., n; n is the number of levels; in addition, when j = 0 (that is, when the basic indicator i is not disclosed at all), S j =0.

[0082] The funnel loss rate L of the jth level of basic indicator i j The calculation formula is:

[0083] L j =(b j -b j-1 ) / b j-1 *100%,

[0084] Among them, b j-1 b is the total number of disclosures of all basic indicators i reaching level j-1; j It is the total number of disclosures of all basic indicators i reaching the jth level; in addition, L0=0.

[0085] Based on the funnel analysis method, the present invention adds a correction analysis of funnel loss in the process of calculating the normalized basic score of the stratified indicators, which not only avoids the subjectivity of manual assignment, but also avoids the limitation of the assumption failure of fixed distribution assignment, thereby achieving both the assignment of stratified indicators with uneven value distribution and the better measurement of the disclosed information value of the stratified indicators. Based on this step, the present invention not only considers the basic indicators with high disclosure value but small disclosure amount, but also realizes effective weight improvement for the subsequent evaluation of the disclosure level of these basic indicators.

[0086] like Figure 1 As shown, the method also includes the steps of:

[0087] S400. Calculate the first environmental information disclosure score of the basic indicator using the funnel loss rate and the basic score.

[0088] The modified score R of the jth level of basic indicator i j The calculation formula is:

[0089] R j =R j-1 +(S j -S j-1 )×(1+L j-1 ),

[0090] in, When j = 1, R j-1 =R0=0, and R1=S1.

[0091] Based on the normalization method, the first environmental information disclosure score F of the jth level of basic indicator i jThe calculation formula of (i.e., the first environmental information disclosure score in step S400) is:

[0092]

[0093] This step is based on the normalization method to ensure that the first environmental information disclosure scores of each basic indicator of the bank to be evaluated are all in the interval of [0,1].

[0094] like Figure 1 As shown, the method also includes the steps of:

[0095] S500: Based on the analytic hierarchy process, the basic weights of the basic indicators are calculated.

[0096] Furthermore, firstly, a hierarchical model is constructed with the level of environmental information disclosure as the target layer, the disclosure quality, disclosure willingness, and disclosure advancement as the criterion layer, and one or more basic indicators corresponding to each criterion layer as the solution layer.

[0097] Secondly, a judgment matrix is ​​constructed. The consistent matrix method can be used to assign values ​​to the elements in the judgment matrix. The specific construction process of the judgment matrix can be referred to in the prior art and will not be described in detail here.

[0098] Again, after constructing and obtaining the judgment matrix, the judgment matrix is ​​tested for consistency. The consistency index CI and consistency ratio CR of the judgment matrix can be calculated by the following formula:

[0099]

[0100]

[0101] Among them, λ is the maximum eigenvalue of the judgment matrix; n is the dimension of the judgment matrix; RI is the average random consistency index, which is associated with n.

[0102] Then, it is determined whether the consistency ratio CR is less than 0.1. If so, the consistency test is passed; if not, the judgment matrix is ​​reconstructed and the above consistency test steps are repeated until CR is less than 0.1.

[0103] Finally, for the judgment matrix that passes the consistency test, the basic weights of the basic indicators can be calculated based on the normalization method through the arithmetic mean method, the geometric mean method, or the eigenvalue method. The specific calculation process of the basic weights refers to the existing technology and is not described in detail here.

[0104] like Figure 1 As shown, the method also includes the steps of:

[0105] S600: Based on the entropy weight method, a modified weight coefficient of the basic indicator is calculated, and the fitting weight of the basic indicator is calculated using the modified weight coefficient and the basic weight.

[0106] like Figure 2 As shown, further, step S600 also includes sub-steps:

[0107] S610: Classify the bank to be evaluated based on the type of the bank to be evaluated to obtain a first classification number of the bank to be evaluated classified by type; and calculate a first weight coefficient of the basic indicator based on the entropy weight method using the first classification number.

[0108] Banks have different system types, including but not limited to: state-owned banks, joint-stock banks, city commercial banks, rural commercial banks, foreign banks, village banks, and private banks. Different types of banks often face different customer groups and geographical business scopes, which leads to differences in the environmental information disclosed by different types of banks. For example, rural commercial banks and village banks mainly face county economic entities and village economic entities respectively. These two types of economic entities involve more agricultural industries and have lower technological content, which makes it difficult to calculate the carbon footprint indicators of these two types of banks (especially those that reach scope 3), because the calculation of carbon footprint indicators requires the calculation of carbon emissions of customers in the relevant industrial chain and requires a continuous data system to support the disclosure of carbon footprints. When the differences in environmental information disclosure of different types of banks are relatively dispersed, the information content is low, and the information value of some basic indicators (for example, whether the head office discloses) is low; when the differences in environmental information disclosure of different types of banks are relatively concentrated (for example, the disclosure rate of these basic indicators of some types of banks is much higher than that of other types of banks), the information content is high, and the information value of these basic indicators is high. Therefore, the present invention pays full attention to the disclosure characteristics of each basic indicator, considers the horizontal differences caused by the horizontal differences in the indicator characteristics, uses the entropy weight method to measure the difference concentration of environmental information disclosure of different types of banks, and then fits them into the final weight system.

[0109] Furthermore, the entropy E of the basic indicator A of the i-th bank (classified by bank type) Ai The calculation formula is:

[0110]

[0111]

[0112] Wherein, p is the probability of the classification of the disclosure results of the basic indicator A of the i-th bank (for example, the disclosure results of the basic indicator A of the i-th bank are: Type 1 disclosure, and Type 2 non-disclosure, then the probability of Type 1 p1=N1 / (N1+N2), N1 is the number of classifications of the disclosure results of Type 1, and N2 is the number of classifications of the disclosure results of Type 2; for another example, the disclosure results of the basic indicator A (carbon footprint disclosure) of the i-th bank are: Type 1 non-disclosure, Type 2 disclosure to Scope 1, Type 3 disclosure to Scope 2, and Type 4 disclosure to Scope 3, then the probability of Type 1 p1=N1 / (N1+N2+N3+N4), N1 is the number of classifications of the disclosure results of Type 1, N2 is the number of classifications of the disclosure results of Type 2, N3 is the number of classifications of the disclosure results of Type 3, and N4 is the number of classifications of the disclosure results of Type 4), and n is the total number of classifications of the disclosure results of the basic indicator A of the i-th bank.

[0113] In addition, for Where n is the number of categories of discrete variables, the entropy can be interpreted as a measure of the degree of disorder of the system under a given number of categories. Specifically, This is equivalent to normalizing the entropy so that when the probability of all classifications is equal (i.e., the maximum chaotic state), the entropy value is 1. In this case, entropy can be understood as relative entropy, reflecting the degree of chaos of the current state of the system relative to the maximum chaotic state. Such normalized entropy can facilitate comparison of the degree of chaos of different systems or at different time points.

[0114] Furthermore, the entropy E of the basic indicator A of the i-th bank Ai Weight correction factor V EAi (that is, the first weight coefficient) is calculated as follows:

[0115]

[0116] Among them, m1 is the first classification number, that is, the banks to be evaluated are divided into m1 categories according to bank types.

[0117] like Figure 2 As shown, step S600 also includes the steps of:

[0118] S620. Classify the bank to be evaluated based on the geographical area of ​​the bank to be evaluated to obtain a second classification number of the bank to be evaluated classified by geographical area; use the second classification number to calculate the second weight coefficient of the basic indicator based on the entropy weight method; wherein the first weight coefficient and the second weight coefficient are the modified weight coefficients.

[0119] Some basic indicators, such as stress measurement indicators, require a leading talent team to perform simulation calculations. The disclosure of this indicator depends not only on the bank's willingness to disclose and the quality of disclosure, but also on the talent cost in different regions. For some banks located in less developed economic regions, the cost of building a corresponding talent team is much greater than that of banks located in more developed economic regions, so the disclosure of this indicator shows a strong regional disclosure difference. When the differences in environmental information disclosure of banks in different regions are relatively dispersed, the information content is low, and the information value of some basic indicators (for example, stress measurement indicators) is low at this time; when the differences in environmental information disclosure of banks in different regions are relatively concentrated (for example, the disclosure rate of these basic indicators by banks in some regions is much higher than that of banks in other regions), the information content is high, and the information value of these basic indicators is high at this time. Therefore, the present invention pays full attention to the disclosure characteristics of each basic indicator, considers the horizontal differences caused by the horizontal differences in the characteristics of the indicators, and uses the entropy weight method to measure the difference concentration of environmental information disclosure of banks in different regions, and then fits into the final weight system.

[0120] Furthermore, the entropy E of the basic indicator A of the c-th bank (classified by the geographical region where the bank is located, for example, by the province where it is located) is Ac The calculation formula is:

[0121]

[0122]

[0123] Wherein, p is the probability of the disclosure result classification of the basic indicator A of the c-th bank (for example, the disclosure results of the basic indicator A of the c-th bank are: type 1 disclosure, and type 2 non-disclosure, then the probability of type 1 p1 = N1 / (N1+N2), N1 is the number of disclosure result classifications of type 1, and N2 is the number of disclosure result classifications of type 2; for another example, the disclosure results of the basic indicator A (carbon footprint disclosure) of the i-th bank are: type 1 non-disclosure, type 2 disclosure to scope 1, type 3 disclosure to scope 2, and type 4 disclosure to scope 3, then the probability of type 1 p1 = N1 / (N1+N2+N3+N4), N1 is the number of disclosure result classifications of type 1, N2 is the number of disclosure result classifications of type 2, N3 is the number of disclosure result classifications of type 3, and N4 is the number of disclosure result classifications of type 4), and n is the total number of disclosure result classifications of the basic indicator A of the c-th bank.

[0124] In addition, for Where n is the number of categories of discrete variables, the entropy can be interpreted as a measure of the degree of disorder of the system under a given number of categories. Specifically, This is equivalent to normalizing the entropy so that when the probability of all classifications is equal (i.e., the maximum chaotic state), the entropy value is 1. In this case, entropy can be understood as relative entropy, reflecting the degree of chaos of the current state of the system relative to the maximum chaotic state. Such normalized entropy can facilitate comparison of the degree of chaos of different systems or at different time points.

[0125] Furthermore, the entropy E of the basic indicator A of the c-th bank Ac Weight correction factor V EAc (that is, the second weight coefficient) is calculated as follows:

[0126]

[0127] Among them, m2 is the second classification number, that is, the banks to be evaluated are divided into m2 categories according to the geographical areas where the banks are located.

[0128] like Figure 2 As shown, step S600 also includes the steps of:

[0129] S630: Calculate the fitting weight of the basic indicator using the first weight coefficient, the second weight coefficient, and the basic weight.

[0130] Furthermore, the fitting weight W of the basic indicator A of the bank B to be evaluated is BA The calculation formula is:

[0131]

[0132] Among them, W A is the basic weight of basic indicator A; k is the kth basic indicator; N is the total number of basic indicators; W k is the basic weight of the kth basic indicator; V Eki is the entropy E of the kth basic indicator of the i-th bank (classified by bank type) ki Weight correction coefficient; V Ekc is the entropy E of the kth basic indicator of the cth bank (classified according to the geographical region where the bank is located) kc This step not only completes the weight correction to obtain the fitting weight, but also uses the normalization method to ensure that the sum of the fitting weights of the N basic indicators of the evaluated bank B is 1.

[0133] The present invention adopts dual-system weight calculation in weight calculation, and improves the basic weight calculation in the hierarchical analysis method by adding entropy weighting of two dimensions (bank type and geographical area), and calculates the final fitting weight, which not only measures the relative importance between the basic indicators, but also combines the degree of disclosure difference of each basic indicator in the above two dimensions, thereby better overcoming the problem of difficulty in evaluating the disclosure level caused by the disclosure characteristics of different basic indicators. In summary, compared with the existing technology, this method can effectively quantify and evaluate the environmental information disclosure level of the banking industry, and effectively quantify and evaluate the performance of each bank in environmental information disclosure.

[0134] like Figure 1 As shown, the method also includes the steps of:

[0135] S700: Calculate a second environmental information disclosure score of the basic indicator using the fitting weight and the first environmental information disclosure score.

[0136] Furthermore, the second environmental information disclosure score of the kth basic indicator of the bank B to be evaluated = W Bk *F Bk ,

[0137] Among them, W Bk is the fitting weight of the kth basic indicator of the bank B to be evaluated; F Bk It is the first environmental information disclosure score of the kth basic indicator of the bank B to be evaluated.

[0138] After obtaining the second environmental information disclosure score, the environmental information disclosure level of the bank to be assessed can be assessed based on the second environmental information disclosure score.

[0139] Furthermore, the second environmental information disclosure scores of all basic indicators of each bank to be evaluated are summed up to obtain the final environmental information disclosure score of the bank to be evaluated.

[0140] The final environmental information disclosure score of Bank B to be assessed is S B The calculation formula is:

[0141]

[0142] Wherein, M is the total number of basic indicators, which is optional, M=64; a is a constant, which is optional, a=100.

[0143] The environmental information disclosure level of each bank to be assessed is evaluated based on the final environmental information disclosure score of each bank to be assessed. The higher the final environmental information disclosure score of the bank to be assessed, the higher its environmental information disclosure level.

[0144] To illustrate the beneficial effects of the present invention, the above method embodiment of the present invention is applied to banks A, B, and C to be evaluated (the types of bank systems and geographical regions of the three banks A, B, and C to be evaluated are different from each other), and the application example is as follows:

[0145] The environmental information disclosure texts of the banks A, B, and C to be evaluated within a certain statistical period are collected to obtain the basic scores of the basic indicators of each bank to be evaluated (taking the three basic indicators of carbon footprint disclosure (scope 1, scope 2, scope 3), the number of stress-tested industries, and whether to disclose carbon dioxide emission reduction information as examples), as shown in Table 1.

[0146] Table 1: Basic scores of basic indicators of banks to be assessed

[0147]

[0148]

[0149] Based on the funnel analysis method, the funnel loss rate of the basic indicators is calculated, as shown in Table 2.

[0150] Table 2: Funnel loss rate of basic indicators

[0151]

[0152] Using the funnel loss rate and basic score, the first environmental information disclosure score of the basic indicator is calculated, as shown in Table 3.

[0153] Table 3: First environmental information disclosure scores of basic indicators

[0154]

[0155] Based on the hierarchical analysis method, the basic weights of basic indicators are calculated.

[0156] Based on the entropy weight method, the revised weight coefficient of the basic indicator is calculated (as shown in Table 4), and the fitting weight of the basic indicator is calculated using the revised weight coefficient and the basic weight (as shown in Table 5).

[0157] Table 4: Modified weight coefficients of basic indicators

[0158]

[0159] Table 5: Fitting weights of basic indicators

[0160]

[0161] Using the fitting weights and the first environmental information disclosure score, the second environmental information disclosure score of the basic indicator is calculated, as shown in Table 6.

[0162] Table 6: Second environmental information disclosure scores of basic indicators

[0163]

[0164] Using the second environmental information disclosure score, the final environmental information disclosure score of the bank to be assessed is calculated, as shown in Table 7.

[0165] Table 7: Final environmental information disclosure scores of banks to be assessed

[0166]

[0167] As can be seen from Table 7, the evaluation results of the environmental information disclosure level are that Bank B is better than Bank A and Bank C. Similarly, to calculate the final environmental information disclosure score of a bank to be evaluated, it is necessary to add up the second environmental information disclosure scores of all basic indicators of the bank to be evaluated. Here, only the second environmental information disclosure scores of the three basic indicators are added to show the process of this evaluation method.

[0168] In some embodiments, after step S700, the method further includes the steps of:

[0169] S1. Integrate the environmental information disclosure text into the text to be processed;

[0170] S2, performing text preprocessing on the text to be processed to obtain a processed text;

[0171] Furthermore, the text preprocessing process includes removing stop words and punctuation marks, and performing word segmentation (segmenting sentences into words).

[0172] S3, counting each word in the processed text and the frequency of each word;

[0173] S4, based on a text vectorization algorithm, vectorize and store each of the words and the word frequency to obtain a disclosure dictionary;

[0174] S5. Obtain the new environmental information disclosure text, repeat the above steps S1-S4, and obtain the updated disclosure dictionary.

[0175] This step obtains a dynamically updated disclosure dictionary based on the environmental information disclosure text of the aforementioned bank to be evaluated and the continuously updated and learned text vectorization algorithm.

[0176] In some embodiments, after step S700, the method further includes the steps of:

[0177] S11. Based on an entity recognition algorithm, the first specificity S1 (ie, baseline specificity) of the bank A to be evaluated is calculated using the environmental information disclosure text of the bank A to be evaluated.

[0178] Furthermore, the calculation formula of the first specificity S1 of the bank A to be evaluated is:

[0179] S1 = (total number of words recognized by entity / total number of words in related sentences) * 100%,

[0180] Among them, the words of entity recognition refer to the words obtained by performing entity recognition on the environmental information disclosure text through the entity recognition algorithm, and the words of the relevant sentences refer to the words of the environmental information disclosure text.

[0181] S12. Count the first occurrence frequency of preset core disclosure words in the environmental information disclosure text of the bank A to be evaluated, and count the second occurrence frequency of the core disclosure words in the environmental information disclosure texts of all the banks to be evaluated.

[0182] S13. Select n core disclosure words from high to low according to the value of the first occurrence frequency, and calculate the second specificity of the bank A to be evaluated by using the first occurrence frequency and the second occurrence frequency; the calculation formula of the second specificity of the bank A to be evaluated is:

[0183]

[0184] Wherein, S2 is the second specificity of the bank A to be evaluated; c f is the first occurrence frequency of the core disclosure word c in the environmental information disclosure text of the bank A to be evaluated; C f is the second occurrence frequency of the core disclosure word c in the environmental information disclosure texts of all the banks to be evaluated; n is the total number of the core disclosure words, optionally, n=100.

[0185] S14. Using the first specificity and the second specificity, calculate the fitting specificity of the bank A to be evaluated; the calculation formula of the fitting specificity of the bank A to be evaluated is:

[0186]

[0187] Wherein, S is the fitting specificity (fitting frequency) of the bank A to be evaluated; the lower the value of the fitting frequency S, the stronger the specificity of the environmental information disclosure text of the bank A to be evaluated.

[0188] The present invention firstly calculates the first specificity of the bank A to be evaluated based on the entity recognition algorithm. The lower the value of the first specificity, the stronger the specificity. Secondly, the n core disclosure words with the highest first occurrence frequency are selected for weighted average to obtain the second specificity. The lower the value of the second specificity, the stronger the specificity. The weights are: It is the ratio of the frequency of occurrence of the core disclosure word c in the environmental information disclosure text of the bank to be evaluated to the total frequency of occurrence of n core disclosure words. The higher the ratio, the more representative the core disclosure word is in the environmental information disclosure text. Finally, the traditional first specificity and the innovative second specificity are fitted to obtain the fitted specificity. The lower the value of the fitted specificity, the stronger the specificity. Therefore, the entity recognition of the present invention can realize specific entity measurement, and then the specificity of the environmental information disclosure text of each bank to be evaluated itself in all texts can be expressed.

[0189] In summary, the present invention discloses an environmental information disclosure assessment method based on the environmental information disclosure text of the banking industry, comprising the steps of: obtaining the environmental information disclosure text of the bank to be assessed; using the environmental information disclosure text to calculate the basic score of the preset basic indicator in the preset environmental information disclosure indicator system; based on the funnel analysis method, calculating the funnel loss rate of the basic indicator; using the funnel loss rate and the basic score, calculating the first environmental information disclosure score of the basic indicator; based on the hierarchical analysis method, calculating the basic weight of the basic indicator; based on the entropy weight method, calculating the modified weight coefficient of the basic indicator, and using the modified weight coefficient and the basic weight to calculate the fitting weight of the basic indicator; using the fitting weight and the first environmental information disclosure score, calculating the second environmental information disclosure score of the basic indicator. The present invention focuses on the proportion of hierarchical disclosure losses of indicators related to core carbon information, and uses this proportion to correct the normalization method of hierarchical indicators, so as to better measure the information value of difficult disclosure indicators in the early stage of disclosure; in terms of weight calculation, dual-system weight calculation is adopted, and the basic weight calculation in the hierarchical analysis method is improved by adding entropy weighting of two dimensions (bank type and geographical area), and the final fitting weight is calculated, which not only measures the relative importance between basic indicators, but also combines the disclosure difference degree of each basic indicator in the above two dimensions, so as to better overcome the problem of difficulty in evaluating the disclosure level caused by the disclosure characteristics of different basic indicators. Therefore, compared with the prior art, this method can effectively quantify and evaluate the level of environmental information disclosure in the banking industry.

[0190] Based on the above embodiments, the present invention also provides an environmental information disclosure evaluation device based on the banking environmental information disclosure text, such as Figure 3 As shown, the device comprises:

[0191] An acquisition unit 11 is used to acquire the environmental information disclosure text of the bank to be evaluated;

[0192] A basic score calculation unit 12, used to calculate the basic score of a preset basic indicator in a preset environmental information disclosure indicator system using the environmental information disclosure text;

[0193] A funnel loss rate calculation unit 13, used to calculate the funnel loss rate of the basic indicator based on the funnel analysis method;

[0194] A first environmental information disclosure score calculation unit 14, configured to calculate a first environmental information disclosure score of the basic indicator by using the funnel loss rate and the basic score;

[0195] A basic weight calculation unit 15 is used to calculate the basic weight of the basic indicator based on the hierarchical analysis method;

[0196] A fitting weight calculation unit 16, used to calculate a modified weight coefficient of the basic indicator based on an entropy weight method, and to calculate a fitting weight of the basic indicator using the modified weight coefficient and the basic weight;

[0197] The second environmental information disclosure score calculation unit 17 is used to calculate the second environmental information disclosure score of the basic indicator by using the fitting weight and the first environmental information disclosure score.

[0198] In some embodiments, Figure 4 As shown, the fitting weight calculation unit 16 also includes:

[0199] The first weight coefficient calculation subunit 161 is used to classify the bank to be evaluated based on the type of the bank to be evaluated, and obtain a first classification number of the bank to be evaluated classified by type; and calculate the first weight coefficient of the basic indicator based on the entropy weight method using the first classification number;

[0200] The second weight coefficient calculation subunit 162 is used to classify the bank to be evaluated based on the geographical area of ​​the bank to be evaluated, and obtain a second classification number of the bank to be evaluated classified by geographical area; using the second classification number, based on the entropy weight method, calculate the second weight coefficient of the basic indicator; wherein the first weight coefficient and the second weight coefficient are the modified weight coefficients;

[0201] The fitting weight calculation subunit 163 calculates the fitting weight of the basic index using the first weight coefficient, the second weight coefficient, and the basic weight.

[0202] Through this device, users can query the final environmental information disclosure scores of banks of different types and regions, the words and word frequencies in the disclosure dictionary of different periods, and the environmental information disclosure specificity of banks of different types and regions.

[0203] The working principles of each unit in the environmental information disclosure assessment device based on the banking environmental information disclosure text of this embodiment are the same as the principles of each step in the environmental information disclosure assessment method based on the banking environmental information disclosure text in the above embodiment, and will not be repeated here.

[0204] Based on the above embodiments, the present invention further provides a computer device, the principle block diagram of the computer device can be as follows: Figure 5 The computer device may include: one or more processors 100 ( Figure 5 Only one is shown in the figure), memory 101, and computer program 102 (for example, a program for environmental information disclosure assessment based on environmental information disclosure text of the banking industry) stored in memory 101 and executable on one or more processors 100. When one or more processors 100 execute computer program 102, various steps of the environmental information disclosure assessment method based on environmental information disclosure text of the banking industry in the above-mentioned embodiment can be implemented. Alternatively, when one or more processors 100 execute computer program 102, the functions of various units of the environmental information disclosure assessment device based on environmental information disclosure text of the banking industry in the above-mentioned embodiment can be implemented, which is not limited here.

[0205] Based on the above embodiments, the present invention further provides a computer-readable storage medium on which a computer program (e.g., a program for environmental information disclosure assessment based on the environmental information disclosure text of the banking industry) is stored. When the computer program is executed by a processor, the various steps of the environmental information disclosure assessment method based on the environmental information disclosure text of the banking industry in the above embodiments can be implemented. Alternatively, when the computer program is executed by a processor, the functions of the various units of the environmental information disclosure assessment device based on the environmental information disclosure text of the banking industry in the above embodiments can be implemented, which is not limited here.

[0206] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating environmental information disclosure based on environmental information disclosure texts of the banking industry, characterized in that: include: Obtain the environmental information disclosure text of the bank to be assessed; Using the environmental information disclosure text, calculate and obtain a basic score for a preset basic indicator in a preset environmental information disclosure indicator system; Based on the funnel analysis method, the funnel loss rate of the basic indicator is calculated; Using the funnel loss rate and the basic score, calculate the first environmental information disclosure score of the basic indicator; Based on the hierarchical analysis method, the basic weights of the basic indicators are calculated; Based on the entropy weight method, a modified weight coefficient of the basic indicator is calculated, and the fitting weight of the basic indicator is calculated using the modified weight coefficient and the basic weight; Using the fitting weight and the first environmental information disclosure score, a second environmental information disclosure score of the basic indicator is calculated; Among them, it also includes: Based on the entity recognition algorithm, using the environmental information disclosure text of the bank A to be evaluated, the first specificity S1 of the bank A to be evaluated is calculated; Counting the first occurrence frequency of the preset core disclosure words in the environmental information disclosure text of the bank A to be evaluated, and counting the second occurrence frequency of the core disclosure words in the environmental information disclosure texts of all the banks to be evaluated; According to the value of the first occurrence frequency, n core disclosure words are selected from high to low, and the second specificity of the bank A to be evaluated is calculated using the first occurrence frequency and the second occurrence frequency; the calculation formula of the second specificity of the bank A to be evaluated is: Wherein, S2 is the second specificity of the bank A to be evaluated; c f is the first occurrence frequency of the core disclosure word c in the environmental information disclosure text of the bank A to be evaluated; C f is the second occurrence frequency of the core disclosure word c in the environmental information disclosure texts of all the banks to be evaluated; n is the total number of the core disclosure words; The fitting specificity of the bank A to be evaluated is calculated using the first specificity and the second specificity; the calculation formula for the fitting specificity of the bank A to be evaluated is: Wherein, S is the fitting specificity of the bank A to be evaluated.

2. The environmental information disclosure evaluation method based on the environmental information disclosure text of the banking industry according to claim 1 is characterized in that: Also includes: Based on the second environmental information disclosure score, the environmental information disclosure level of the bank to be assessed is assessed.

3. The environmental information disclosure evaluation method based on the environmental information disclosure text of the banking industry according to claim 2 is characterized in that: The basic indicators include: carbon footprint disclosure, number of stress-tested industries, and whether carbon dioxide emission reduction information is disclosed.

4. The environmental information disclosure evaluation method based on the environmental information disclosure text of the banking industry according to claim 2 is characterized in that: The calculation formula of the funnel loss rate is: L j =(b j -b j-1 ) / b j-1 *100%, Among them, L j is the funnel loss rate, b j-1 b) the total number of disclosures of all the basic indicators reaching level j-1; j The total number of disclosures of all the basic indicators reaching level j.

5. The environmental information disclosure evaluation method based on the environmental information disclosure text of the banking industry according to claim 2 is characterized in that: The step of calculating the modified weight coefficient of the basic indicator based on the entropy weight method, and calculating the fitting weight of the basic indicator using the modified weight coefficient and the basic weight includes: Based on the type of the bank to be evaluated, the bank to be evaluated is classified to obtain a first classification number of the bank to be evaluated classified by type; using the first classification number, based on the entropy weight method, a first weight coefficient of the basic indicator is calculated; Based on the geographical area of ​​the bank to be evaluated, the bank to be evaluated is classified to obtain a second classification number of the bank to be evaluated classified by geographical area; using the second classification number, based on the entropy weight method, a second weight coefficient of the basic indicator is calculated; wherein the first weight coefficient and the second weight coefficient are the modified weight coefficients; The fitting weight of the basic index is calculated using the first weight coefficient, the second weight coefficient, and the basic weight.

6. The environmental information disclosure evaluation method based on the environmental information disclosure text of the banking industry according to claim 1 is characterized in that: Also includes: Step A: Integrate the environmental information disclosure text into the text to be processed; Performing text preprocessing on the text to be processed to obtain a processed text; Counting the words in the processed text and the frequency of the words; Based on a text vectorization algorithm, the words and the word frequencies are vectorized and stored to obtain a disclosure dictionary; Step B: Obtain the new environmental information disclosure text, repeat step A, and obtain the updated disclosure dictionary.

7. An environmental information disclosure evaluation device based on the environmental information disclosure text of the banking industry, characterized in that: include: An acquisition unit, used to acquire the environmental information disclosure text of the bank to be assessed; A basic score calculation unit, used to calculate the basic score of a preset basic indicator in a preset environmental information disclosure indicator system using the environmental information disclosure text; A funnel loss rate calculation unit, used to calculate the funnel loss rate of the basic indicator based on the funnel analysis method; A first environmental information disclosure score calculation unit, configured to calculate a first environmental information disclosure score of the basic indicator by using the funnel loss rate and the basic score; A basic weight calculation unit, used for calculating the basic weight of the basic indicator based on the hierarchical analysis method; A fitting weight calculation unit, used to calculate the modified weight coefficient of the basic indicator based on the entropy weight method, and calculate the fitting weight of the basic indicator using the modified weight coefficient and the basic weight; A second environmental information disclosure score calculation unit, configured to calculate a second environmental information disclosure score of the basic indicator by using the fitting weight and the first environmental information disclosure score; Wherein, the device further comprises: Based on the entity recognition algorithm, using the environmental information disclosure text of the bank A to be evaluated, the first specificity S1 of the bank A to be evaluated is calculated; Counting the first occurrence frequency of the preset core disclosure words in the environmental information disclosure text of the bank A to be evaluated, and counting the second occurrence frequency of the core disclosure words in the environmental information disclosure texts of all the banks to be evaluated; According to the value of the first occurrence frequency, n core disclosure words are selected from high to low, and the second specificity of the bank A to be evaluated is calculated using the first occurrence frequency and the second occurrence frequency; the calculation formula of the second specificity of the bank A to be evaluated is: Wherein, S2 is the second specificity of the bank A to be evaluated; c f is the first occurrence frequency of the core disclosure word c in the environmental information disclosure text of the bank A to be evaluated; C f is the second occurrence frequency of the core disclosure word c in the environmental information disclosure texts of all the banks to be evaluated; n is the total number of the core disclosure words; The fitting specificity of the bank A to be evaluated is calculated using the first specificity and the second specificity; the calculation formula for the fitting specificity of the bank A to be evaluated is: Wherein, S is the fitting specificity of the bank A to be evaluated.

8. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the environmental information disclosure assessment method based on the environmental information disclosure text of the banking industry as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the environmental information disclosure assessment method based on the banking environmental information disclosure text as described in any one of claims 1 to 6 are implemented.

Images