CN113487241A

CN113487241A - Method, device, equipment and storage medium for classifying enterprise environment-friendly credit grades

Info

Publication number: CN113487241A
Application number: CN202110952901.0A
Authority: CN
Inventors: 刘荣荣; 卢有靖
Original assignee: Ping An International Smart City Technology Co Ltd
Current assignee: Ping An International Smart City Technology Co Ltd
Priority date: 2021-08-19
Filing date: 2021-08-19
Publication date: 2021-10-08

Abstract

The invention relates to the technical field of artificial intelligence, is applied to the field of intelligent environment protection, and provides a method, a device, equipment and a storage medium for classifying an enterprise environment-friendly credit grade, which are used for improving the accuracy of analyzing the enterprise environment-friendly credit grade. The method for classifying the environmental protection credit level of the enterprise comprises the following steps: performing information matching and index calculation on the preprocessed enterprise information through an index scoring model based on enterprise environment-friendly behavior index factors to obtain an enterprise environment-friendly behavior index; acquiring target disposal process information in enterprise information to be processed from a preset disposal process block chain, and performing correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data; and carrying out environmental protection credit grade classification based on the historical enterprise information, the enterprise environmental protection behavior index and the enterprise credibility index data to obtain a target grade analysis result. In addition, the invention also relates to a block chain technology, and the enterprise information to be processed can be stored in the block chain.

Description

Method, device, equipment and storage medium for classifying enterprise environment-friendly credit grades

Technical Field

The invention relates to the field of intelligent decision making of artificial intelligence, in particular to a method, a device, equipment and a storage medium for classifying enterprise environment-friendly credit grades.

Background

In recent years, with the continuous development of various environmental protection policy and regulations, the supervision of waste production enterprises (i.e. enterprises producing waste) is continuously enhanced, and the environmental protection credit rating division of the waste production enterprises has an important guiding function on the local environment management. At present, the environmental protection credit rating analysis of enterprises generally adopts a double random investigation method.

However, the differences of a plurality of evaluation results obtained by the method are large, the factor of environmental protection credit rating analysis is single, the information islanding is serious, the data value of the information islanding cannot be exerted, the data use efficiency is low, and the reliability of the data cannot be ensured, so that the accuracy of the environmental protection credit rating analysis of enterprises is low.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for classifying an enterprise environmental protection credit grade, which are used for improving the accuracy of enterprise environmental protection credit grade analysis.

The invention provides a method for classifying environment-friendly credit grades of enterprises, which comprises the following steps:

acquiring enterprise information to be processed and enterprise environmental protection behavior index factors, and preprocessing the enterprise information to be processed to obtain preprocessed enterprise information;

performing information matching and index calculation on the preprocessed enterprise information and the enterprise environmental protection behavior index factors through a preset index scoring model to obtain an enterprise environmental protection behavior index;

acquiring target disposal process information in the enterprise information to be processed from a preset disposal process block chain, and performing correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data;

and acquiring historical enterprise information of enterprises in the to-be-processed enterprise information, and classifying the environmental protection credit level based on the historical enterprise information, the enterprise environmental protection behavior index and the enterprise credibility index data to obtain a target level analysis result.

Optionally, in a first implementation manner of the first aspect of the present invention, the enterprise environmental protection behavior index factor includes an enterprise environmental social behavior index factor, an enterprise environmental management behavior index factor, and an enterprise pollution control behavior index factor, and the obtaining the enterprise environmental protection behavior index by performing information matching and index calculation on the preprocessed enterprise information and the enterprise environmental protection behavior index factor through a preset index scoring model includes:

calling a preset index scoring model, and performing multi-level feature extraction on the preprocessed enterprise information to obtain enterprise feature information;

acquiring enterprise environmental protection behavior category information corresponding to the enterprise environmental social behavior index factors, and sequentially performing secondary classification and minimum value calculation on the enterprise characteristic information through the enterprise environmental protection behavior category information to obtain an enterprise environmental social behavior index;

acquiring judgment information corresponding to enterprise environment management behavior index factors, performing secondary classification on the enterprise characteristic information through the judgment information to obtain a plurality of classification results, and performing management index calculation based on the classification results to obtain enterprise environment management indexes;

according to the enterprise pollution control behavior index factors, carrying out characteristic selection of enterprise pollution control behavior categories on the enterprise characteristic information to obtain emission characteristic information, and sequentially carrying out pollution control index calculation, weighted superposition and percentage conversion of single indexes on the emission characteristic information to obtain an enterprise pollution control behavior index;

and determining the enterprise environmental social behavior index, the enterprise environmental management index and the enterprise pollution control behavior index as enterprise environmental protection behavior indexes.

Optionally, in a second implementation manner of the first aspect of the present invention, the obtaining historical enterprise information of an enterprise in the to-be-processed enterprise information, and performing environmental protection credit level classification based on the historical enterprise information, the enterprise environmental protection behavior index, and the enterprise credibility index data to obtain a target level analysis result includes:

calling a plurality of secondary classifiers in a preset deep convolutional neural network model, and carrying out secondary classification of the environmental protection credit level on the enterprise environmental protection behavior index and the enterprise credibility index data to obtain an initial level analysis result;

acquiring historical enterprise information of an enterprise in the enterprise information to be processed, and detecting the historical enterprise information according to preset bad information to obtain a detection result;

and adjusting the initial grade analysis result according to the detection result to obtain a target grade analysis result.

Optionally, in a third implementation manner of the first aspect of the present invention, the acquiring to-be-processed enterprise information and an enterprise environmental protection behavior index factor, and preprocessing the to-be-processed enterprise information to obtain preprocessed enterprise information includes:

acquiring enterprise information to be processed and enterprise environment-friendly behavior index factors, and classifying the enterprise information to be processed according to preset classification types to obtain enterprise information to be processed and non-processed enterprise information, wherein the enterprise information to be processed comprises information of one or more enterprises, and the enterprise environment-friendly behavior index factors comprise enterprise environment social behavior index factors, enterprise environment management behavior index factors and enterprise pollution control behavior index factors;

carrying out data cleaning, duplicate removal processing and standardization processing on the enterprise information to be processed to obtain candidate enterprise information;

and determining the non-processed enterprise information and the candidate enterprise information as the pre-processed enterprise information.

Optionally, in a fourth implementation manner of the first aspect of the present invention, the obtaining target disposal process information in the to-be-processed enterprise information from a preset disposal process block chain, and performing correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data includes:

sending a flow information reading request to a preset abandoned flow block chain so that the abandoned flow block chain verifies the flow information reading request, and receiving target disposal flow information corresponding to enterprises in the enterprise information to be processed, which is returned after verification is passed;

classifying the target disposal flow information to obtain waste production data and waste treatment data, calling a preset linear correlation coefficient algorithm, and performing correlation coefficient calculation on the waste production data and the waste treatment data to obtain enterprise correlation coefficients;

and carrying out identification and percentage conversion on the enterprise correlation coefficient to obtain enterprise credibility index data.

Optionally, in a fifth implementation manner of the first aspect of the present invention, before the acquiring the to-be-processed enterprise information and the enterprise environmental protection behavior index factor, and preprocessing the to-be-processed enterprise information to obtain the preprocessed enterprise information, the method further includes:

the method comprises the steps of obtaining enterprise disposal flow information, waste production information of waste production enterprises and waste treatment information of waste treatment enterprises, creating transaction records according to the enterprise disposal flow information, the waste production information of the waste production enterprises and the waste treatment information of the waste treatment enterprises, and establishing a waste treatment flow block chain according to the transaction records.

Optionally, in a sixth implementation manner of the first aspect of the present invention, after obtaining historical enterprise information of an enterprise in the to-be-processed enterprise information, and performing environmental protection credit level classification based on the historical enterprise information, the enterprise environmental protection behavior index, and the enterprise credibility index data to obtain a target level analysis result, the method further includes:

and acquiring a target back propagation neural network model according to the enterprise environmental protection behavior index factors, the enterprise credibility index data and the target grade analysis result, and performing risk grade identification and grading early warning according to the output result of the target back propagation neural network model.

The invention provides a device for classifying the environmental protection credit level of an enterprise, which comprises:

the system comprises a preprocessing module, a storage module and a processing module, wherein the preprocessing module is used for acquiring enterprise information to be processed and enterprise environmental protection behavior index factors and preprocessing the enterprise information to be processed to obtain preprocessed enterprise information;

the first calculation module is used for performing information matching and index calculation on the preprocessed enterprise information and the enterprise environmental protection behavior index factor through a preset index scoring model to obtain an enterprise environmental protection behavior index;

the second calculation module is used for acquiring target disposal process information in the enterprise information to be processed from a preset disposal process block chain, and performing correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data;

and the classification module is used for acquiring historical enterprise information of enterprises in the to-be-processed enterprise information, and performing environmental protection credit level classification on the basis of the historical enterprise information, the enterprise environmental protection behavior index and the enterprise credibility index data to obtain a target level analysis result.

Optionally, in a first implementation manner of the second aspect of the present invention, the first computing module is specifically configured to:

Optionally, in a second implementation manner of the second aspect of the present invention, the classification module is specifically configured to:

Optionally, in a third implementation manner of the second aspect of the present invention, the preprocessing module is specifically configured to:

Optionally, in a fourth implementation manner of the second aspect of the present invention, the second calculating module is specifically configured to:

Optionally, in a fifth implementation manner of the second aspect of the present invention, the apparatus for classifying an enterprise environmental protection credit level further includes:

the system comprises a creating module and a waste disposal flow block chain establishing module, wherein the creating module is used for acquiring enterprise disposal flow information, waste production information of a waste production enterprise and waste disposal information of a waste disposal enterprise, creating a transaction record according to the enterprise disposal flow information, the waste production information of the waste production enterprise and the waste disposal information of the waste disposal enterprise, and establishing the waste disposal flow block chain according to the transaction record.

Optionally, in a sixth implementation manner of the second aspect of the present invention, the apparatus for classifying an enterprise environmental protection credit level further includes:

and the recognition early warning module is used for acquiring a target back propagation neural network model according to the enterprise environmental protection behavior index factors, the enterprise credibility index data and the target level analysis result, and performing risk level recognition and grading early warning according to the output result of the target back propagation neural network model.

The third aspect of the present invention provides a classification device for enterprise environmental protection credit rating, comprising: a memory and at least one processor, the memory having stored therein a computer program; the at least one processor invokes the computer program in the memory to cause the classification device of enterprise environmental protection credit classes to perform the above-described method of classifying enterprise environmental protection credit classes.

A fourth aspect of the present invention provides a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to execute the above-described method for classifying an enterprise environmental protection credit level.

According to the technical scheme provided by the invention, enterprise information to be processed is preprocessed to obtain preprocessed enterprise information; performing information matching and index calculation on the preprocessed enterprise information and enterprise environment-friendly behavior index factors through a preset index scoring model to obtain an enterprise environment-friendly behavior index; acquiring target disposal process information in enterprise information to be processed from a preset disposal process block chain, and performing correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data; and carrying out environmental protection credit grade classification based on the historical enterprise information, the enterprise environmental protection behavior index and the enterprise credibility index data to obtain a target grade analysis result. In the embodiment of the invention, the factor diversity of the environmental protection credit rating analysis is enriched, the transparency of the target disposal process information is ensured, the credibility of the target disposal process information is improved, the problems that an information island is serious and the data value of the information island cannot be exerted are solved, the data use efficiency and the credibility of the data are improved, and the accuracy of the environmental protection credit rating analysis of an enterprise is further improved.

Drawings

FIG. 1 is a diagram illustrating an exemplary classification method for environmental credit levels of an enterprise according to an embodiment of the present invention;

FIG. 2 is a diagram of another embodiment of a method for classifying environmental credit levels of an enterprise according to an embodiment of the present invention;

FIG. 3 is a diagram of an exemplary embodiment of a device for classifying environmental credit levels of an enterprise according to an exemplary embodiment of the present invention;

FIG. 4 is a schematic diagram of another embodiment of the apparatus for classifying the environmental credit rating of an enterprise according to an embodiment of the present invention;

fig. 5 is a schematic diagram of an embodiment of a classification device for enterprise eco-credit levels in an embodiment of the present invention.

Detailed Description

The embodiment of the invention provides a method, a device, equipment and a storage medium for classifying enterprise environment-friendly credit grades, and improves the accuracy of enterprise environment-friendly credit grade analysis.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For understanding, a detailed flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of the method for classifying enterprise environmental credit levels according to an embodiment of the present invention includes:

101. and acquiring enterprise information to be processed and enterprise environmental protection behavior index factors, and preprocessing the enterprise information to be processed to obtain preprocessed enterprise information.

It is understood that the executing subject of the present invention may be a classification device of the enterprise environmental protection credit rating, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The server sends an enterprise information acquisition request to a preset supervision block chain, analyzes and authorizes the enterprise information acquisition request through the preset supervision block chain, and returns initial enterprise information corresponding to the enterprise information acquisition request after the verification is passed, wherein the preset supervision block chain is a block chain formed by each enterprise private chain and a supervision agency private chain, each enterprise private chain can be a block chain formed by a main company, a subsidiary company, an affiliated company and a cooperative company, the supervision agency private chain can be a block chain formed by a unit and a mechanism for managing and controlling the environmental protection behavior of the enterprise, the initial enterprise information comprises information of one or more than one enterprise, the initial enterprise information comprises initial enterprise production waste information (namely information of waste produced by the enterprise) and other related information, and the initial enterprise production waste information can be obtained by uploading the waste monitoring station of the enterprise after processing, the initial enterprise waste information includes but is not limited to the waste monitoring station data, the common waste treatment method, the waste production volume (or weight) per unit time and the like of the enterprise, and other related information includes but is not limited to the geographical position of the enterprise, the waste treatment unit information, the waste transportation unit information and the like; identifying the production waste type of the initial enterprise production waste information to obtain the production waste type, calling a preset Principal Component Analysis (PCA) to analyze the production waste information of the initial enterprise to obtain the production waste principal component information, and adding the production waste type and the production waste principal component information to the production waste information of the initial enterprise to obtain the production waste information of the target enterprise; and determining the production and waste information and other related information of the target enterprise as the information of the enterprise to be processed, wherein the information of the enterprise to be processed comprises the information of one or more enterprises.

The server extracts enterprise environment-friendly behavior index factors from a preset database, wherein the enterprise environment-friendly behavior index factors comprise enterprise environment social behavior index factors, enterprise environment management behavior index factors and enterprise pollution control behavior index factors, the enterprise environment social behavior index factors comprise pollution accident index factors, public complaint index factors and illegal behavior index factors, the enterprise environment management behavior index factors comprise environment management basic requirement factors, clean production audit assessment factors and environment management certification (ISO14000 certification) factors, and the enterprise pollution control behavior index factors are used for evaluating enterprise pollution behaviors from four environment factors of water, gas, sound and solid waste.

The server carries out data anomaly detection, missing value filling, duplicate removal and unification processing on the enterprise information to be processed so as to realize preprocessing of the enterprise information to be processed, obtain the preprocessed enterprise information and guarantee the quality of the preprocessed enterprise information.

102. And performing information matching and index calculation on the preprocessed enterprise information and enterprise environment-friendly behavior index factors through a preset index scoring model to obtain an enterprise environment-friendly behavior index.

The server calls a preset index scoring model to perform feature extraction on the preprocessed enterprise information to obtain enterprise feature information, wherein an artificial intelligence-based neural network is adopted in the embodiment of the application, the index scoring model can be formed by connecting a plurality of neural network structures in a specific connection mode (parallel connection, series connection or series-parallel connection combination), the plurality of neural network structures can be a plurality of classification network structures, and the plurality of neural network structures can also be a plurality of feature extraction network structures combined with a plurality of classification networks.

The server respectively traverses the structure trees (namely a decision tree based on artificial intelligence) corresponding to the enterprise environmental social behavior index factor, the enterprise environmental management behavior index factor and the enterprise pollution control behavior index factor in the enterprise environmental protection behavior index factors according to the enterprise characteristic information through the index scoring model to obtain enterprise environmental protection behavior matching information, enterprise environmental management behavior matching information and enterprise pollution control behavior matching information, the enterprise environmental protection behavior matching information comprises an enterprise environmental protection behavior category and a grade score corresponding to the enterprise environmental protection behavior category, the enterprise environmental management behavior matching information comprises a judgment result and a judgment result statistical information of the enterprise environmental management behavior category, and the enterprise pollution control behavior matching information comprises an enterprise pollution control behavior category and an actual emission and a compliance emission corresponding to the enterprise pollution control behavior category.

The server performs index calculation on the enterprise environmental protection behavior matching information through a calculation formula corresponding to an enterprise environmental social behavior index factor in the index scoring model to obtain an enterprise environmental social behavior index, performs index calculation on the enterprise environmental management behavior matching information through a calculation formula corresponding to an enterprise environmental management behavior index factor in the index scoring model to obtain an enterprise environmental management index, and performs calculation on the enterprise pollution control behavior matching information through a calculation formula corresponding to an enterprise pollution control behavior index factor in the index scoring model to obtain an enterprise pollution control behavior index, wherein the enterprise environmental protection behavior index comprises the enterprise environmental social behavior index, the enterprise environmental management index and the enterprise pollution control behavior index.

103. And acquiring target disposal process information in the enterprise information to be processed from a preset disposal process block chain, and performing correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data.

The server sends a flow information reading request to a preset abandoned flow block chain, so that the abandoned flow block chain verifies the flow information reading request, and target disposal flow information corresponding to the enterprise in the enterprise information to be processed is returned after the verification is passed; classifying the target disposal flow information to obtain waste production data and waste treatment data, calling a preset linear correlation coefficient algorithm, and performing correlation coefficient calculation on the waste production data and the waste treatment data to obtain enterprise correlation coefficients; and performing percentage conversion and identification on the enterprise correlation coefficient to obtain enterprise credibility index data. The transparency of the target disposal process information is ensured, and the reliability of the target disposal process information is improved, so that the accuracy of the environmental protection credit level analysis of enterprises is improved.

104. And obtaining historical enterprise information of the enterprise in the enterprise information to be processed, and performing environmental protection credit grade classification based on the historical enterprise information, the enterprise environmental protection behavior index and the enterprise credibility index data to obtain a target grade analysis result.

The historical enterprise information of the enterprise in the to-be-processed enterprise information is the behavior information of the previous year of the current year of the target level analysis result. And the server performs primary environmental protection credit grade classification through the enterprise environmental protection behavior index and the enterprise credibility index data, and adjusts the primary environmental protection credit grade classification result by combining historical enterprise information to obtain a target grade analysis result. Further, calling a plurality of secondary classifiers in a preset deep convolutional neural network model, and carrying out secondary classification on the environmental protection behavior index and the enterprise credibility index data of the enterprise to obtain an initial grade analysis result; acquiring historical enterprise information of an enterprise in enterprise information to be processed, and detecting the historical enterprise information according to preset bad information to obtain a detection result; and adjusting the initial grade analysis result according to the detection result to obtain a target grade analysis result.

In the embodiment of the invention, the factor diversity of the environmental protection credit rating analysis is enriched, the transparency of the target disposal process information is ensured, the credibility of the target disposal process information is improved, the problems that an information island is serious and the data value of the information island cannot be exerted are solved, the data use efficiency and the credibility of the data are improved, and the accuracy of the environmental protection credit rating analysis of an enterprise is further improved. This scheme can be applied to in the wisdom environmental protection field to promote the construction in wisdom city.

Referring to fig. 2, another embodiment of the method for classifying the environmental credit level of the enterprise according to the embodiment of the present invention includes:

201. the method comprises the steps of obtaining enterprise disposal flow information, waste production information of waste production enterprises and waste treatment information of waste treatment enterprises, creating transaction records according to the enterprise disposal flow information, the waste production information of the waste production enterprises and the waste treatment information of the waste treatment enterprises, and establishing a waste treatment flow block chain according to the transaction records.

The method comprises the steps that a server acquires enterprise processing flow information, waste production information of a waste production enterprise (namely an enterprise producing waste) and waste processing information of a waste disposal enterprise (namely an enterprise disposing waste), wherein the enterprise processing flow information is used for indicating flow information of disposal of waste information of each small micro-production waste enterprise; creating a transaction record according to the enterprise processing flow information, the waste production information of the waste production enterprise and the waste processing information of the waste disposal enterprise; establishing a waste flow block chain according to the transaction records, wherein the waste flow block chain is an ordered linked list formed by one transaction block, each block records a series of transactions, and each block points to the previous block so as to form a chain; and performing chain linking verification, chain linking registration and chain linking authorization on the enterprise processing flow information, the waste production information of the waste enterprise and the waste processing information of the waste enterprise to obtain the enterprise processing flow information after chain linking, the waste production information of the waste enterprise and the waste processing information of the waste enterprise, and storing the enterprise processing flow information after chain linking, the waste production information of the waste enterprise and the waste processing information of the waste enterprise to the nodes of the waste processing flow block chain.

The waste disposal flow block chain is a continuously-increased total account book of the whole network, each complete node has a complete block chain, the node always trusts the longest block chain, the forged block chain needs to have more than 51% of total network computing power, the waste disposal flow block chain is used for recording transaction information of small micro-production waste enterprises, each waste is recorded into the waste disposal flow block chain from the production-disposal flow, the transaction information is more transparent, and the waste production information and the waste treatment information are prevented from being falsified and forged.

202. And acquiring enterprise information to be processed and enterprise environmental protection behavior index factors, and preprocessing the enterprise information to be processed to obtain preprocessed enterprise information.

Specifically, the server acquires enterprise information to be processed and enterprise environmental protection behavior index factors, classifies the enterprise information to be processed according to preset classification types to obtain enterprise information to be processed and non-processed enterprise information, wherein the enterprise information to be processed comprises information of one or more enterprises, and the enterprise environmental protection behavior index factors comprise enterprise environmental social behavior index factors, enterprise environmental management behavior index factors and enterprise pollution control behavior index factors; carrying out data cleaning, duplicate removal processing and standardization processing on enterprise information to be processed to obtain candidate enterprise information; and determining the non-processed enterprise information and the candidate enterprise information as the pre-processed enterprise information.

After obtaining enterprise information to be processed and enterprise environment-friendly behavior index factors (the enterprise environment-friendly behavior index factors comprise enterprise environment social behavior index factors, enterprise environment management behavior index factors and enterprise pollution control behavior index factors), the server extracts the characteristics of the enterprise information to be processed to obtain extracted characteristic information, the enterprise information to be processed comprises information of one or more enterprises, a preset classifier is called, classification type probability value calculation and type output are carried out on the extracted characteristic information based on preset classification types to obtain target classification types, and the preset classification types comprise but are not limited to scattered, disordered and non-uniform types; and dividing the enterprise information to be processed into enterprise information to be processed and non-processed enterprise information according to the target classification type, wherein the enterprise information to be processed is used for indicating the enterprise information to be processed corresponding to the target classification type, and the non-processed enterprise information is used for the enterprise information to be processed corresponding to the non-target classification type.

The server carries out abnormal value detection and missing value filling on the enterprise information to be processed so as to realize data cleaning on the enterprise information to be processed, carries out repeated value detection and repeated value combination on the enterprise information to be processed in sequence so as to realize duplicate removal processing on the enterprise information to be processed, carries out data conversion in a preset format on statistical information units on the enterprise information to be processed so as to realize standardized processing on the enterprise information to be processed, and thus obtains candidate enterprise information; the non-processed enterprise information and the candidate enterprise information are determined as the preprocessed enterprise information, so that the quality of the preprocessed enterprise information is guaranteed, and the accuracy of the environmental protection credit level analysis of the preprocessed enterprise information is further guaranteed.

203. And performing information matching and index calculation on the preprocessed enterprise information and enterprise environment-friendly behavior index factors through a preset index scoring model to obtain an enterprise environment-friendly behavior index.

Specifically, the enterprise environmental protection behavior index factors comprise enterprise environmental social behavior index factors, enterprise environmental management behavior index factors and enterprise pollution control behavior index factors, the server calls a preset index scoring model, and multi-level feature extraction is carried out on the preprocessed enterprise information to obtain enterprise feature information; acquiring enterprise environmental protection behavior category information corresponding to the enterprise environmental social behavior index factors, and sequentially performing secondary classification and minimum value calculation on the enterprise characteristic information through the enterprise environmental protection behavior category information to obtain an enterprise environmental social behavior index; acquiring judgment information corresponding to the enterprise environment management behavior index factors, performing secondary classification on the enterprise characteristic information through the judgment information to obtain a plurality of classification results, and performing management index calculation based on the classification results to obtain enterprise environment management indexes; according to the enterprise pollution control behavior index factors, carrying out characteristic selection of enterprise pollution control behavior categories on the enterprise characteristic information to obtain emission characteristic information, and carrying out pollution control index calculation, weighted superposition and percentage system conversion of single indexes on the emission characteristic information in sequence to obtain an enterprise pollution control behavior index; and determining the enterprise environmental social behavior index, the enterprise environmental management index and the enterprise pollution control behavior index as enterprise environmental protection behavior indexes.

The server calls a target detection algorithm yolov5 in a preset index scoring model, and performs multi-level operation on the preprocessed enterprise information to obtain multi-level features, namely enterprise feature information, wherein the operation of each level comprises vector convolution operation processing, batch normalization processing, activation function processing and splicing processing.

The server generates a key value of an enterprise environmental social behavior index factor in the enterprise environmental protection behavior index factors, retrieves a preset database through the key value to obtain corresponding enterprise environmental protection behavior category information, wherein the enterprise environmental protection behavior category information comprises enterprise environmental protection behavior categories (pollution accident categories, public complaint categories and illegal behavior categories) and judgment standards corresponding to the enterprise environmental protection behavior categories, and the judgment standards corresponding to the enterprise environmental protection behavior categories comprise judgment contents and judgment scores, for example: taking level 1 in the evaluation criteria corresponding to the pollution accident category as an example, LV1 (100): the enterprise meets the requirements of national or local pollutant release standards and environmental management, conforms to the environmental protection laws and regulations in a standard manner by ISO14000 certification or by clean production auditing, is in a level of 1 in LV1, is in a judgment score in 100, conforms to the requirements of the national or local pollutant release standards and environmental management, conforms to the environmental protection laws and regulations in a standard manner by ISO14000 certification or by clean production auditing, and is in judgment content.

Creating an environment-friendly behavior judgment decision tree set of enterprise environment-friendly behavior category information, wherein one enterprise environment-friendly behavior category corresponds to one environment-friendly behavior judgment decision tree, traversing the environment-friendly behavior judgment decision tree set through enterprise characteristic information to obtain corresponding target environment-friendly behavior judgment scores, and the target environment-friendly behavior judgment scores comprise environment-friendly behavior judgment scores respectively corresponding to a pollution accident category, a public complaint category and an illegal behavior category; and calculating the minimum value of the judgment value of the target environmental protection behavior through an environmental protection behavior judgment calculation formula in the index grading model to obtain an enterprise environmental social behavior index, wherein the environmental protection behavior judgment calculation formula is as follows: f1 is min (p1, p2 and p3), F1 represents the social behavior index of the enterprise environment, and p1, p2 and p3 respectively represent judgment scores corresponding to the pollution accident category, the public complaint category and the illegal behavior category in the target environmental protection behavior judgment score.

The server obtains judgment information corresponding to the enterprise environment management behavior index factor, the judgment information is used for indicating a plurality of judgment conditions for judgment, a management behavior decision tree set of the judgment information can be created, one judgment condition corresponds to one management behavior decision tree, and the judgment information is obtained according to the judgment conditionsTraversing the management behavior decision tree set by the enterprise characteristic information to realize the binary classification of the enterprise characteristic information to obtain a plurality of corresponding classification results, screening and counting the classification results to obtain the number of target classification results, obtaining the total number of evaluation indexes (namely the total number of judgment conditions) of judgment information, and calculating the number of the target classification results and the total number of the evaluation indexes through a preset environment management index calculation formula to obtain an enterprise environment management index, wherein the environment management index calculation formula is as follows:

f2 denotes the enterprise environment management index, N denotes the number of target classification results, and M denotes the total number of evaluation indexes. For example, the plurality of judgment conditions of judgment in the judgment information are "whether a license or a temporary license is provided; whether the pollution discharge fee is paid on schedule or not; whether pollution discharge is declared according to time; if the environmental statistics are filled in timely and faithfully; whether the waste production type is consistent with enterprise qualification or not is judged, the total number of evaluation indexes is 5, a management behavior decision tree set of evaluation information is created, the management behavior decision tree set is traversed according to the enterprise characteristic information to realize binary classification of the enterprise characteristic information, a plurality of corresponding classification results (corresponding to yes, no and no) are obtained, the classification result with the classification result being yes in the classification results is screened, the classification result (corresponding to yes and yes) is obtained, the number of the classification results (corresponding to yes and yes) is counted, the number of target classification results is obtained, and then the enterprise environment management index is:

the enterprise pollution control behavior index factors comprise four categories of water, gas, sound and solid waste, the server selects and classifies the characteristics of the enterprise characteristic information according to the enterprise pollution control behavior categories in the enterprise pollution control behavior index factors to obtain the characteristic information, namely a discharge characteristic information set, corresponding to the four categories of water, gas, sound and solid waste, and one enterprise pollution control behavior category corresponds to one discharge characteristic information setThe method comprises the steps of obtaining discharge characteristic information, wherein the discharge characteristic information comprises actual discharge information and compliant discharge information of enterprise pollution control behavior categories, calculating pollution control indexes of single indexes of each discharge characteristic information in a discharge characteristic information set through a preset pollution control behavior index calculation formula to obtain pollution control behavior indexes corresponding to the enterprise pollution control behavior categories, and performing weighted superposition and percentage conversion on the pollution control behavior indexes corresponding to the enterprise pollution control behavior categories to obtain the enterprise pollution control behavior indexes, wherein the pollution control behavior index calculation formula is as follows:

f3 denotes an enterprise pollution control behavior index, q denotes the number of pollutants that a waste producing enterprise has permitted to discharge, G denotes actual discharge amount information of an enterprise pollution control behavior class, H denotes compliant discharge amount information of an enterprise pollution control behavior class,

pollution control behavior index, w, representing the correspondence of a category of pollution control behavior for an enterprise_iAnd representing the pollution control weight corresponding to the enterprise pollution control behavior category. And determining the enterprise environmental social behavior index, the enterprise environmental management index and the enterprise pollution control behavior index as enterprise environmental protection behavior indexes. And performing information matching and index calculation on the preprocessed enterprise information through a preset index scoring model based on the enterprise environment-friendly behavior index factors to obtain an enterprise environment-friendly behavior index, so that the accuracy of the enterprise environment-friendly behavior index is ensured.

204. And acquiring target disposal process information in the enterprise information to be processed from a preset disposal process block chain, and performing correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data.

Specifically, the server sends a flow information reading request to a preset abandoned flow block chain, so that the abandoned flow block chain verifies the flow information reading request, and receives target disposal flow information corresponding to the enterprise in the enterprise information to be processed, which is returned after the verification is passed; classifying the target disposal flow information to obtain waste production data and waste treatment data, calling a preset linear correlation coefficient algorithm, and performing correlation coefficient calculation on the waste production data and the waste treatment data to obtain enterprise correlation coefficients; and carrying out identification and percentage conversion on the enterprise correlation coefficient to obtain enterprise credibility index data.

The method comprises the steps that a server sends a flow information reading request to a preset abandoned flow block chain, the abandoned flow block chain analyzes and authorizes the flow information reading request, after verification is passed, an index of an enterprise in enterprise information to be processed is generated, a block chain database is retrieved through the index, target disposal flow information corresponding to the enterprise in the enterprise information to be processed is obtained, and the target disposal flow information corresponding to the enterprise in the enterprise information to be processed is returned to the server; identifying and classifying the target disposal flow information according to the characteristics and the fields of the waste production data and the characteristics and the fields of the waste treatment data to obtain waste production data and waste treatment data; calling a calculation formula in a preset linear correlation coefficient algorithm, and performing correlation coefficient calculation on waste production data and waste treatment data to obtain enterprise correlation coefficients, wherein the calculation formula is as follows:

ρ represents the business correlation coefficient, ρ is between (-1.0, 1.0), X represents waste production data, Y represents waste treatment data, Cov (X, Y) represents the covariance of X, Y, var (X) represents the variance of X, and var (Y) represents the variance of Y.

And carrying out absolute value dereferencing on the enterprise correlation coefficient to obtain the enterprise correlation coefficient after the absolute value dereferencing, acquiring corresponding identification content according to the dereferencing, and identifying the enterprise correlation coefficient according to the identification content to obtain the identified enterprise correlation coefficient. The identification content includes the business relevance coefficient, and the relevance level and the business credit level corresponding to the business relevance coefficient, for example: the enterprise correlation coefficient 0-0.09 is no correlation, the enterprise correlation coefficient 0.1-0.3 is weak correlation, the enterprise correlation coefficient 0.3-0.5 is medium correlation, the enterprise correlation coefficient 0.5-1.0 is strong correlation, the enterprise credit rating with the enterprise correlation coefficient less than 0.3 is a credit general enterprise, the enterprise credit rating with the enterprise correlation coefficient 0.3-0.5 is a credit good enterprise, and the enterprise credit rating with the enterprise correlation coefficient more than 0.5 is a credit good enterprise. And multiplying the identified enterprise relevance coefficient by 100 (namely, percent conversion) to obtain enterprise credibility index data. By adding the enterprise credibility index data, the accuracy of the environmental protection credit level analysis of the enterprise is improved.

205. And obtaining historical enterprise information of the enterprise in the enterprise information to be processed, and performing environmental protection credit grade classification based on the historical enterprise information, the enterprise environmental protection behavior index and the enterprise credibility index data to obtain a target grade analysis result.

Specifically, the server calls a plurality of secondary classifiers in a preset deep convolutional neural network model to perform secondary classification of environmental protection credit levels on the enterprise environmental protection behavior indexes and the enterprise credibility index data to obtain an initial level analysis result; acquiring historical enterprise information of an enterprise in enterprise information to be processed, and detecting the historical enterprise information according to preset bad information to obtain a detection result; and adjusting the initial grade analysis result according to the detection result to obtain a target grade analysis result.

The server calls a plurality of two classifiers in a preset deep convolutional neural network model to perform two classification of environment-friendly credit levels on enterprise environment-friendly behavior indexes and enterprise credibility index data respectively to obtain classification probability values of each two classifiers for each environment-friendly credit level, the classification probability values of the two classifiers for each environment-friendly credit level are subjected to weighted summation to obtain classification probability values of each environment-friendly credit level, the classification probability values of each environment-friendly credit level are compared with a preset threshold to obtain classification probability values larger than the preset threshold, the classification probability values larger than the preset threshold are subjected to maximum value dereferencing to obtain target classification probability values, and the environment-friendly credit level corresponding to the target classification probability values is determined as an initial level analysis result, wherein the environment-friendly credit levels include but are not limited to environment-friendly credit enterprises, environment-friendly good enterprises, environment-friendly credit-level data and the like, Environmental protection warning enterprises and enterprises with poor environmental protection.

Wherein, the default bad information is, for example: the crimes are not built in batches and are maliciously stolen and constitute an environmental crime. The server extracts historical enterprise information of enterprises in the enterprise information to be processed from a preset database, judges whether the historical enterprise information has preset bad information or not and obtains a detection result; if the detection result is yes, updating the initial grade analysis result to an environmentally-friendly and bad enterprise to obtain a target grade analysis result, and if the detection result is not, determining the initial grade analysis result as the target grade analysis result to adjust the initial grade analysis result according to the detection result to obtain the target grade analysis result. The factor diversity of the environmental protection credit rating analysis is improved, and the accuracy of the environmental protection credit rating analysis of enterprises is improved.

206. And acquiring a target back propagation neural network model according to the enterprise environmental protection behavior index factors, the enterprise credibility index data and the target grade analysis result, and performing risk grade identification and grading early warning according to the output result of the target back propagation neural network model.

The method comprises the steps that a server constructs an initial back propagation neural network model according to enterprise environment-friendly behavior index factors, enterprise credibility index data and target grade analysis results, the initial back propagation neural network model comprises an input layer, a hidden layer and an output layer, the input layer corresponds to enterprise environment social behavior index factors, enterprise environment management behavior index factors and enterprise pollution control behavior index factors in the enterprise environment-friendly behavior index factors, and data input of the enterprise credibility index data, the hidden layer is used for calculating indexes based on the index data of the input layer, and the output layer is used for classifying the grades according to the calculated indexes; acquiring monitoring station data and actual gate data, and performing network training on the initial back propagation neural network model through the monitoring station data and the actual gate data to obtain a target back propagation neural network model; acquiring enterprise data to be evaluated, and classifying the enterprise data to be evaluated by an enterprise environmental protection credit level through a target back propagation neural network model to obtain an output result of the enterprise environmental protection credit level; and matching the output result of the enterprise environmental protection credit grade with the risk grade to obtain a matching result, and performing early warning according to early warning modes corresponding to different risk grades in the matching result to realize risk grade identification and grading early warning. The method enriches the use ways of the target grade analysis result, improves the usability of the target grade analysis result, and improves the accuracy of risk grade identification and grading early warning based on the accuracy of the target grade analysis result.

In the embodiment of the invention, the factor diversity of the environment-friendly credit grade analysis is enriched, the transparency of the target disposal process information is ensured, the credibility of the target disposal process information is improved, the problems that an information island is serious and the data value of the information island cannot be exerted are solved, the data use efficiency and the credibility of the data are improved, the environment-friendly credit grade analysis accuracy of an enterprise is further improved, the risk grade identification and the grading early warning are carried out through the output result of the target back propagation neural network model, the use way of the target grade analysis result is enriched, the usability of the target grade analysis result is improved, and the accuracy of the risk grade identification and the grading early warning is improved based on the accuracy of the target grade analysis result. This scheme can be applied to in the wisdom environmental protection field to promote the construction in wisdom city.

In the above description of the method for classifying the enterprise environmental protection credit level in the embodiment of the present invention, referring to fig. 3, a device for classifying the enterprise environmental protection credit level in the embodiment of the present invention is described below, where an embodiment of the device for classifying the enterprise environmental protection credit level in the embodiment of the present invention includes:

the preprocessing module 301 is configured to acquire enterprise information to be processed and enterprise environmental protection behavior index factors, and preprocess the enterprise information to be processed to obtain preprocessed enterprise information;

the first calculation module 302 is configured to perform information matching and index calculation on the preprocessed enterprise information and enterprise environmental protection behavior index factors through a preset index scoring model to obtain an enterprise environmental protection behavior index;

the second calculating module 303 is configured to obtain target disposal process information in the to-be-processed enterprise information from a preset disposal process block chain, and perform correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data;

the classification module 304 is configured to obtain historical enterprise information of an enterprise in the to-be-processed enterprise information, and perform environmental protection credit level classification based on the historical enterprise information, the enterprise environmental protection behavior index, and the enterprise credibility index data to obtain a target level analysis result.

The function implementation of each module in the classification apparatus for enterprise environmental protection credit levels corresponds to each step in the classification method embodiment for enterprise environmental protection credit levels, and the function and implementation process thereof are not described in detail herein.

Referring to fig. 4, another embodiment of the apparatus for classifying the environmental credit level of an enterprise according to the embodiment of the present invention includes:

the creating module 305 is configured to obtain enterprise disposal flow information, waste production information of a waste production enterprise, and waste processing information of a waste disposal enterprise, create a transaction record according to the enterprise disposal flow information, the waste production information of the waste production enterprise, and the waste processing information of the waste disposal enterprise, and create a waste disposal flow block chain according to the transaction record;

the classification module 304 is used for acquiring historical enterprise information of an enterprise in the to-be-processed enterprise information, and performing environmental protection credit level classification based on the historical enterprise information, the enterprise environmental protection behavior index and the enterprise credibility index data to obtain a target level analysis result;

and the recognition early warning module 306 is used for acquiring the target back propagation neural network model according to the enterprise environmental protection behavior index factors, the enterprise credibility index data and the target grade analysis result, and performing risk grade recognition and grading early warning according to the output result of the target back propagation neural network model.

Optionally, the first calculating module 302 may be further specifically configured to:

acquiring judgment information corresponding to the enterprise environment management behavior index factors, performing secondary classification on the enterprise characteristic information through the judgment information to obtain a plurality of classification results, and performing management index calculation based on the classification results to obtain enterprise environment management indexes;

according to the enterprise pollution control behavior index factors, carrying out characteristic selection of enterprise pollution control behavior categories on the enterprise characteristic information to obtain emission characteristic information, and carrying out pollution control index calculation, weighted superposition and percentage system conversion of single indexes on the emission characteristic information in sequence to obtain an enterprise pollution control behavior index;

Optionally, the classification module 304 may be further specifically configured to:

calling a plurality of secondary classifiers in a preset deep convolutional neural network model, and carrying out secondary classification of environmental protection credit levels on the enterprise environmental protection behavior indexes and the enterprise credibility index data to obtain an initial level analysis result;

acquiring historical enterprise information of an enterprise in enterprise information to be processed, and detecting the historical enterprise information according to preset bad information to obtain a detection result;

Optionally, the preprocessing module 301 may be further specifically configured to:

carrying out data cleaning, duplicate removal processing and standardization processing on enterprise information to be processed to obtain candidate enterprise information;

Optionally, the second calculating module 303 may be further specifically configured to:

sending a flow information reading request to a preset abandoned flow block chain so that the abandoned flow block chain verifies the flow information reading request, and receiving target disposal flow information which is returned after the verification and corresponds to enterprises in the enterprise information to be processed;

The functional implementation of each module and each unit in the classification apparatus for enterprise environmental protection credit levels corresponds to each step in the classification method embodiment for enterprise environmental protection credit levels, and the functions and implementation processes are not described in detail herein.

Fig. 3 and 4 describe the classification apparatus of the enterprise environmental protection credit rating in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the classification apparatus of the enterprise environmental protection credit rating in the embodiment of the present invention is described in detail from the perspective of hardware processing.

Fig. 5 is a schematic structural diagram of an enterprise environmental protection credit rating classifying device according to an embodiment of the present invention, where the enterprise environmental protection credit rating classifying device 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of computer program operations in the classification device 500 for enterprise environmental protection credit ratings. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of computer program operations in the storage medium 530 on the enterprise environmental credit rating classification device 500.

The enterprise environmental credit rating classification device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the configuration of the enterprise environmental protection credit rating classification device illustrated in FIG. 5 does not constitute a limitation of the enterprise environmental protection credit rating classification device and may include more or fewer components than illustrated, or some components may be combined, or a different arrangement of components.

The application also provides a classification equipment of enterprise's environmental protection credit rating, includes: a memory having a computer program stored therein and at least one processor, the memory and the at least one processor interconnected by a line; the at least one processor invokes the computer program in the memory to cause the classification device of enterprise environmental protection credit classes to perform the steps of the method of classifying enterprise environmental protection credit classes described above. The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, or a volatile computer-readable storage medium, having stored thereon a computer program, which, when run on a computer, causes the computer to perform the steps of the method for classifying an enterprise environmental credit rating.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several computer programs to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A method for classifying an enterprise environmental protection credit level is characterized in that the method for classifying the enterprise environmental protection credit level comprises the following steps:

2. The method for classifying the environmental credit rating of an enterprise according to claim 1, wherein the environmental behavior index factors of an enterprise include social behavior index factors of an enterprise environment, environmental management behavior index factors of an enterprise and pollution control behavior index factors of an enterprise, and the environmental behavior index of an enterprise is obtained by performing information matching and index calculation on the preprocessed enterprise information and the environmental behavior index factors of an enterprise through a preset index scoring model, including:

3. The method for classifying the environmental protection credit levels of the enterprises according to claim 2, wherein the obtaining historical enterprise information of the enterprises in the to-be-processed enterprise information and the classifying the environmental protection credit levels based on the historical enterprise information, the environmental protection behavior index of the enterprises and the reliability index data of the enterprises to obtain the target level analysis result comprises:

4. The method for classifying the environmental protection credit rating of the enterprise according to claim 2, wherein the step of obtaining the enterprise information to be processed and the environmental protection behavior index factor of the enterprise and preprocessing the enterprise information to be processed to obtain the preprocessed enterprise information comprises:

5. The method for classifying an enterprise environmental credit rating according to claim 1, wherein the step of obtaining the target disposal process information in the to-be-processed enterprise information from a preset disposal process block chain, and performing correlation coefficient calculation on the target disposal process information to obtain enterprise credibility index data comprises:

6. The method for classifying the environmental protection credit rating of the enterprise according to claim 1, wherein before the obtaining the enterprise information to be processed and the environmental protection behavior index factor of the enterprise and preprocessing the enterprise information to be processed to obtain the preprocessed enterprise information, the method further comprises:

7. The method for classifying the environmental protection credit rating of the enterprise according to any one of claims 1 to 6, wherein the obtaining of the historical enterprise information of the enterprise in the to-be-processed enterprise information, the environmental protection credit rating classification based on the historical enterprise information, the environmental protection behavior index of the enterprise, and the reliability index data of the enterprise, and after obtaining the target rating analysis result, further comprises:

8. The utility model provides a sorter of enterprise environmental protection credit rating which characterized in that, sorter of enterprise environmental protection credit rating includes:

9. An enterprise environmental protection credit rating classification device, the enterprise environmental protection credit rating classification device comprising: a memory and at least one processor, the memory having stored therein a computer program;

the at least one processor invokes the computer program in the memory to cause the enterprise environmental protection credit rating classification device to perform the enterprise environmental protection credit rating classification method of any one of claims 1-7.

10. A computer-readable storage medium, having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method for classifying an enterprise environmental credit rating according to any one of claims 1-7.