CN117893063A - Enterprise reputation evaluation method and system based on big data - Google Patents
Enterprise reputation evaluation method and system based on big data Download PDFInfo
- Publication number
- CN117893063A CN117893063A CN202311772021.0A CN202311772021A CN117893063A CN 117893063 A CN117893063 A CN 117893063A CN 202311772021 A CN202311772021 A CN 202311772021A CN 117893063 A CN117893063 A CN 117893063A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- data
- characteristic data
- reputation
- dimension
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 60
- 238000012549 training Methods 0.000 claims abstract description 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 38
- 238000013210 evaluation model Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000004140 cleaning Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 20
- 238000012797 qualification Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 7
- 230000001502 supplementing effect Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 9
- 238000009826 distribution Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229940108461 rennet Drugs 0.000 description 1
- 108010058314 rennet Proteins 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an enterprise reputation evaluation method and system based on big data, wherein the method comprises the following steps: acquiring multi-dimensional characteristic data of each enterprise in a plurality of enterprises; cleaning the multidimensional characteristic data of each enterprise according to a consistency principle; preprocessing the characteristic data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme; taking the preprocessed characteristic data of each dimension as a training sample, training the established enterprise reputation evaluation model, and stopping training the enterprise reputation evaluation model until the training error reaches a preset critical value; and evaluating the reputation of the target enterprise through the trained enterprise reputation evaluation model to obtain the reputation score of the target enterprise.
Description
Technical Field
The invention relates to the technical field of big data analysis and processing, in particular to an enterprise reputation evaluation method and system based on big data.
Background
Enterprise reputation evaluation is a core problem in purchasing and selling throughout an enterprise. The traditional enterprise reputation evaluation method used by the enterprise at present mainly focuses on wind control evaluation formed in the enterprise operation process, and the method is difficult to realize due to huge manpower investment when the enterprise reputation evaluation is related to a reference factor for realizing sales will. Along with the upgrading of the daily operation mode of the enterprise, the blockchain collaborative platform upgrades and changes the daily operation mode of the enterprise, and the real-time dynamic enterprise reputation evaluation can quickly provide an enterprise reputation grade result in the blockchain collaborative platform. The invention utilizes the learning capability of big data algorithm, can extract effective evaluation information from the management data of each aspect in the daily operation of enterprises, and makes up the defects in the traditional enterprise reputation wind control evaluation, thereby comprehensively evaluating the enterprise reputation from multiple dimensions.
The prior art (application number: CN 111445307A) provides an enterprise product reputation authentication ordering method and an electronic transaction display platform, and the prior art discloses the enterprise product reputation authentication ordering method and the electronic transaction display platform, which comprise the following steps: when an enterprise applies for registering with a trading platform, receiving enterprise reputation proving information input by the enterprise applying for registering; verifying the authenticity of each item of enterprise reputation proving information input by the application resident enterprise; and (3) according to the verification information of each enterprise reputation certification information, scoring the registered enterprise with the high grade, and enabling the enterprise with the grade score reaching the standard to pass through the registered residence platform, wherein the enterprise with the grade score not reaching the standard does not pass through the residence platform.
However, in the prior art, the enterprise reputation proving information is mainly ordered, and the enterprise reputation cannot be evaluated in an omnibearing and multidimensional manner.
Disclosure of Invention
The technical scheme of the invention provides an enterprise reputation evaluation method and system based on big data, which are used for solving the problem of how to accurately evaluate enterprise reputation in multiple dimensions based on the big data.
In order to solve the problems, the invention provides an enterprise reputation evaluation method based on big data, which comprises the following steps:
acquiring multi-dimensional characteristic data of each enterprise in a plurality of enterprises;
cleaning the multidimensional characteristic data of each enterprise according to a consistency principle;
preprocessing the characteristic data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme;
taking the preprocessed characteristic data of each dimension as a training sample, training the established enterprise reputation evaluation model, and stopping training the enterprise reputation evaluation model until the training error reaches a preset critical value;
and evaluating the reputation of the target enterprise through the trained enterprise reputation evaluation model to obtain the reputation score of the target enterprise.
Preferably, the acquiring the multi-dimensional feature data of each enterprise in the plurality of enterprises includes:
established date, real-life capital, registered capital, taxpayer qualification, management anomaly information, administrative punishment information and serious illegal information.
Preferably, the cleaning the multidimensional feature data of each enterprise according to the consistency principle includes:
judging the rationality of the characteristic data, and removing or correcting unreasonable characteristic data;
carrying out consistency processing on the measurement units of the characteristic data;
and supplementing the missing key information in the characteristic data.
Preferably, the preprocessing is performed on the feature data of each dimension in the multi-dimension after cleaning according to a preset data preprocessing scheme, including:
the characteristic data of each dimension is given different weights;
assigning points to the time length of the enterprise duration in the characteristic data according to a preset assigning standard;
calculating sales growth rate in the feature data, comprising: (business current term invoice total/business upper term invoice total) -1;
calculating customer loyalty in the feature data, comprising: interval ratio (number of clients transacted/number of clients last year);
calculating a large customer ranking in the feature data, comprising: the number of clients with the transaction amount of the sales order being more than the expected amount accounts for the ranking interval of the whole industry;
calculating the product quality in the characteristic data comprises the following steps: (qualified lot/total lot) a value of 100%;
evaluating the price index in the characteristic data, comprising: (price of commodity/average price), and determining a price stability in a ranking interval in the industry after computing variance by price de-duplication of commodity in the past year;
and evaluating commodity acceptance rate, logistics acceptance rate, service attitude acceptance rate and after-sales service acceptance rate in the feature data.
Based on another aspect of the invention, the invention provides an enterprise reputation evaluation system based on big data, the system comprising:
the initial unit is used for acquiring multidimensional characteristic data of each enterprise in the plurality of enterprises;
the processing unit is used for cleaning the multidimensional characteristic data of each enterprise according to a consistency principle; preprocessing the characteristic data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme;
the training unit is used for training the established enterprise reputation evaluation model by taking the preprocessed feature data of each dimension as a training sample until the training error reaches a preset critical value, and stopping training the enterprise reputation evaluation model;
and the result unit is used for evaluating the reputation of the target enterprise through the trained enterprise reputation evaluation model to acquire the reputation score of the target enterprise.
Preferably, the acquiring the multi-dimensional feature data of each enterprise in the plurality of enterprises includes:
established date, real-life capital, registered capital, taxpayer qualification, management anomaly information, administrative punishment information and serious illegal information.
Preferably, the processing unit is configured to clean the multidimensional feature data of each enterprise according to a consistency principle, and includes:
judging the rationality of the characteristic data, and removing or correcting unreasonable characteristic data;
carrying out consistency processing on the measurement units of the characteristic data;
and supplementing the missing key information in the characteristic data.
Preferably, the processing unit is configured to perform preprocessing on the feature data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme, and includes:
the characteristic data of each dimension is given different weights;
assigning points to the time length of the enterprise duration in the characteristic data according to a preset assigning standard;
calculating sales growth rate in the feature data, comprising: (business current term invoice total/business upper term invoice total) -1;
calculating customer loyalty in the feature data, comprising: interval ratio (number of clients transacted/number of clients last year);
calculating a large customer ranking in the feature data, comprising: the number of clients with the transaction amount of the sales order being more than the expected amount accounts for the ranking interval of the whole industry;
calculating the product quality in the characteristic data comprises the following steps: (qualified lot/total lot) a value of 100%;
evaluating the price index in the characteristic data, comprising: (price of commodity/average price), and determining a price stability in a ranking interval in the industry after computing variance by price de-duplication of commodity in the past year;
and evaluating commodity acceptance rate, logistics acceptance rate, service attitude acceptance rate and after-sales service acceptance rate in the feature data.
Based on another aspect of the present invention, the present invention provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for executing an enterprise reputation evaluation method based on big data.
Based on another aspect of the present invention, the present invention provides an electronic device, which is characterized in that the electronic device includes: a processor and a memory; wherein,
the memory is used for storing the processor executable instructions;
the processor is used for reading the executable instructions from the memory and executing the instructions to realize an enterprise reputation evaluation method based on big data.
The technical scheme of the invention provides an enterprise reputation evaluation method and system based on big data, wherein the method comprises the following steps: acquiring multi-dimensional characteristic data of each enterprise in a plurality of enterprises; cleaning the multidimensional characteristic data of each enterprise according to a consistency principle; preprocessing the characteristic data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme; taking the preprocessed characteristic data of each dimension as a training sample, training the established enterprise reputation evaluation model until the training error reaches a preset critical value, and stopping training the enterprise reputation evaluation model; and evaluating the reputation of the target enterprise through the trained enterprise reputation evaluation model to obtain the reputation score of the target enterprise. The invention provides an enterprise reputation evaluation method based on big data analysis, which utilizes enterprise public data such as enterprise establishment date, real-time payment capital, registered capital, tax payer qualification and other enterprise comprehensive information, combines with whether negative information evaluation exists in a national enterprise credit display system, links real-time generated collaboration platform uplink data to enterprise operation analysis, customer analysis and product quality through big data algorithm, combines with price index and customer satisfaction, and finally realizes enterprise reputation evaluation from multiple data dimensions. And with the increase of data, the enrichment of enterprise uplink data and the increasingly compact enterprise collaboration, the large data analysis learning model can evaluate the enterprise reputation more accurately.
Drawings
Exemplary embodiments of the present invention may be more completely understood in consideration of the following drawings:
FIG. 1 is a flow chart of an enterprise reputation evaluation method based on big data in accordance with a preferred embodiment of the present invention;
FIG. 2 is a flow chart of an enterprise reputation evaluation method based on big data in accordance with a preferred embodiment of the present invention;
FIG. 3 is a diagram of enterprise reputation evaluation index weights in accordance with a preferred embodiment of the present invention;
FIG. 4 is a block diagram of an enterprise reputation evaluation system based on big data in accordance with a preferred embodiment of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the examples described herein, which are provided to fully and completely disclose the present invention and fully convey the scope of the invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, like elements/components are referred to by like reference numerals.
Unless otherwise indicated, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. In addition, it will be understood that terms defined in commonly used dictionaries should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
FIG. 1 is a flow chart of an enterprise reputation evaluation method based on big data in accordance with a preferred embodiment of the present invention.
The invention provides an enterprise reputation evaluation method based on big data analysis. The invention uses the crawler technology to crawl the public information of enterprises, such as the establishment date, real-time capital, registered capital, tax payer qualification information of enterprises in the enterprise qualification, and the management abnormal information, administrative punishment information and serious illegal information in the national enterprise credit information public system; then collecting sales amount related in enterprise operation, and carrying out corresponding big data calculation scoring on the sales ranking interval and sales increase rate of the enterprises taking the commodities as dimensions by combining inter-enterprise cooperation; evaluating the position and stability of price indexes on the market by combining price factors of the enterprise commodity in sales and the premise of net distribution under multiple commodities and multiple enterprises, performing price factor algorithm distribution learning, and outputting analysis scores for single dimension of the enterprise under the commodity; the comprehensive customer satisfaction of customers on commodity qualification rate, logistics qualification rate, service attitude qualification rate and after-sales service qualification rate is utilized to establish product qualification rate distribution under product quality, and enterprise loyalty, large customer number ranking, customer location distribution and distribution of net growth data of customers are established; and finally, scoring the enterprise reputation by using the algorithm model section assignment to obtain an enterprise reputation evaluation model, and finally, evaluating the enterprise reputation when the multi-enterprise order is coordinated by using the model.
As shown in FIG. 1, the invention provides an enterprise reputation evaluation method based on big data, which comprises the following steps:
step 101: acquiring multi-dimensional characteristic data of each enterprise in a plurality of enterprises;
preferably, acquiring the multi-dimensional feature data of each enterprise of the plurality of enterprises includes:
established date, real-life capital, registered capital, taxpayer qualification, management anomaly information, administrative punishment information and serious illegal information.
The invention first obtains a dataset of an enterprise. The data adopted by the invention are all from enterprise public information collected by a crawler technology, and comprise established date, real-time payment capital, registered capital and tax payer qualification information, and the national enterprise credit information shows management abnormality information, administrative punishment information and serious illegal information in the system, so that a data basis is provided for the credit evaluation of the follow-up enterprises.
Step 102: cleaning the multidimensional characteristic data of each enterprise according to a consistency principle;
preferably, the cleaning of the multidimensional feature data of each enterprise according to the consistency principle comprises the following steps:
judging the rationality of the feature data, and removing or correcting unreasonable feature data;
consistency processing is carried out on the measurement units of the characteristic data;
and supplementing the missing key information in the characteristic data.
The invention cleans the collected enterprise data. Because the information disclosed by enterprises has inconsistency, the data disclosed by each enterprise has differences, and for certain information, some enterprises select to be not disclosed, while others select to be disclosed. Therefore, the information collected by the crawlers has the problems of default, unreasonable structure and the like, and the unreasonable data can influence the prediction result. To reduce errors in such data, it is desirable to clean such information to remove or correct unreasonable information, such as the importance of the value of real capital over registered capital. For the problem of inconsistent units in the collected amount data, such as ten thousand yuan, million yuan, hundred million yuan and the like, the invention adopts a measure of unified unit measurement. Such as monetary unit inconsistency in collected capital information, such as euro, dollar, yen, etc., the present invention employs conversion of exchange rates into a unified rennet measure. Meanwhile, for important missing information, the method searches the key information or fits the information through other ways.
Step 103: preprocessing the characteristic data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme;
preferably, preprocessing the feature data of each dimension in the multi-dimension after cleaning according to a preset data preprocessing scheme comprises the following steps:
the characteristic data of each dimension is given different weights;
assigning points to the time length of the enterprise duration in the characteristic data according to a preset assigning standard;
calculating sales growth rate in the feature data, comprising: (business current term invoice total/business upper term invoice total) -1;
calculating customer loyalty in the feature data, comprising: interval ratio (number of clients transacted/number of clients last year);
calculating a large customer ranking in the feature data, comprising: the number of clients with the transaction amount of the sales order being more than the expected amount accounts for the ranking interval of the whole industry;
calculating the product quality in the characteristic data comprises the following steps: (qualified lot/total lot) a value of 100%;
evaluating the price index in the characteristic data, comprising: (price of commodity/average price), and determining a price stability in a ranking interval in the industry after computing variance by price de-duplication of commodity in the past year;
and evaluating commodity acceptance rate, logistics acceptance rate, service attitude acceptance rate and after-sales service acceptance rate in the feature data.
The invention preprocesses the cleaned data. In order to evaluate the credit of the enterprise in multiple dimensions, the invention extracts different characteristic parameters according to the characteristics of different information and removes redundant information. The data preprocessing scheme used herein is as follows:
(1) The enterprise reputation score is the predicted key information, with higher scores representing higher enterprise reputation scores. The scoring data is determined by referring to information of multiple aspects, wherein the enterprise duration takes 5 years as a calculation standard, and the registered capital takes multiple amounts as a scoring segmentation section. The invention considers the authoritative negative information evaluation of the enterprise credit showing system, and the model calculation is endowed with a high weight calculation factor, and the comprehensive reputation evaluation ranking of the multidimensional factor is the enterprise reputation evaluation method under the big data algorithm learning;
(2) Calculating the time length of the enterprise duration, namely the current time-the establishment date of the enterprise, wherein the time is full of the factor in more than 5 years, and the score is obtained by dividing 60% of the enterprise duration by 5 in less than 5 years; the amount of registered capital and the qualification of general taxpayers are important factors for reflecting enterprise qualification;
(3) Calculating a ranking interval of order sales under enterprise operation analysis in the industry, and judging a sales increase rate in enterprise reputation evaluation (the total amount of the enterprise current sales invoice/the total amount of the enterprise upper sales invoice) -1;
(4) In the customer analysis, the section proportion occurring in 2 consecutive years (the number of customers in a transaction/the number of customers in the last year) is calculated, and is evaluation information reflecting customer loyalty. And calculating the ranking interval of the sales order, wherein the number of clients with the transaction amount of more than 1000 ten thousand (inclusive) accounts for the whole industry, so as to feed back the ranking evaluation information of the large number of clients. The net growth evaluation factor of the customer is judged by the value in the past 2 whole years (newly added customer number-lost customer number). The number of cities distributed by transaction clients is in a ranking interval in the whole industry, and a reputation evaluation client location distribution factor is fed back;
(5) In the product quality, calculating a value of 100% (qualified batch/total batch), and feeding back the influence of the product quality on enterprise reputation evaluation in a specific interval;
(6) In the price index, considering the ranking interval of (commodity price/average price) in the industry, reflecting the position of the commodity price of the enterprise in the market, and calculating the variance by combining the price de-duplication of the commodity in the past year, wherein the ranking interval in the industry is the price stability. And comprehensively analyzing to form a price index influence factor for enterprise reputation evaluation.
(7) Calculating the proportion of the commodity good score, the logistics good score, the service attitude good score and the after-sale service good score in the total score, and reflecting the reputation evaluation influence of the customer satisfaction;
step 104: taking the preprocessed characteristic data of each dimension as a training sample, training the established enterprise reputation evaluation model until the training error reaches a preset critical value, and stopping training the enterprise reputation evaluation model;
step 105: and evaluating the reputation of the target enterprise through the trained enterprise reputation evaluation model to obtain the reputation score of the target enterprise.
The invention generates an enterprise reputation evaluation model. According to the method, relevant data of all enterprises of the blockchain collaborative platform are crawled according to the steps, corresponding preprocessing is carried out, a training sample can be obtained, and big data scoring calculation is used as an enterprise reputation evaluation model. The invention uses big data scoring calculation is that enterprise operation data obtained through data preprocessing is subjected to parameterization treatment of 7 big class weights, the enterprise operation data is subdivided into 19 secondary weights, a grading assignment form is adopted for subdivision weight indexes, and a final output layer is a scoring digital layer. And training the reputation evaluation by using a training set, stopping training when the training error reaches a critical value, and storing the training model so as to obtain the enterprise reputation evaluation model. If the enterprise reputation comprehensive evaluation priority is required to be considered in the process of matching and trading the commodities sold by the enterprise, the enterprise reputation evaluation model is trained to obtain the enterprise reputation evaluation model to score the target enterprise reputation in the purchasing process, and then the enterprise reputation evaluation can be obtained.
The invention provides a new enterprise reputation multi-factor comprehensive evaluation method by utilizing a crawler technology to crawl relevant information of an enterprise and extracting multi-dimensional characteristic data of the enterprise and taking the multi-dimensional characteristics of the enterprise as a basis, and provides a reference basis for matching the priority of the synthetic transaction in the cooperative transaction of the enterprise. In the data preprocessing stage, different assignment methods are adopted to preprocess the collected enterprise information according to different large-class weights referenced by enterprise reputation evaluation, redundant enterprise characteristics are removed, and enterprise reputation is evaluated from multiple dimensions.
The enterprise reputation evaluation method based on big data provided by the invention has the following advantages:
the enterprise reputation evaluation method provided by the invention evaluates the reputation of the enterprise by utilizing the information with different dimensionalities, and can predict enterprises with different types in different industries. Unlike traditional enterprise reputation evaluation method, the invention does not need to design fixed index to evaluate enterprise reputation, but solves the problem of real-time enterprise reputation evaluation by utilizing the characteristic of big data learning on the premise of data preprocessing. And as the data volume increases, the prediction model of the invention becomes more accurate. Meanwhile, along with the complexity of the economic environment, the invention can directly add the key information of related enterprises in the preprocessing stage without changing the model structure, and provides a relatively accurate reputation scoring reference basis for the supply and demand transaction activities of the enterprise transaction collaboration platform based on the supply chain technology.
Figure 2 is an overall flow of the present invention. (a) training procedure: firstly, crawling relevant public data of an enterprise through a crawler technology, preprocessing the data, then bringing the data into an enterprise reputation evaluation model for training, and storing the model when the model reaches a certain training frequency or the model prediction error is smaller than a specified threshold value; (b) use process: and preprocessing enterprises in commodity dimensions through enterprise priority related sequencing of supply-demand relations pre-generated by a transaction collaboration platform, and calculating preprocessing data by using a model to obtain an enterprise reputation evaluation result in the commodity dimensions.
FIG. 3 illustrates the structure of an enterprise reputation evaluation index model used in the present invention. The large class weight consists of 7 evaluation dimensions, the subdivision weight consists of 19 secondary indexes, and the subdivision weight reputation score value of each secondary index is calculated to represent enterprise reputation evaluation.
The invention provides a computer readable storage medium, which stores a computer program for executing an enterprise reputation evaluation method based on big data.
The present invention provides an electronic device, including: a processor and a memory; wherein,
a memory for storing processor-executable instructions;
and the processor is used for reading the executable instructions from the memory and executing the instructions to realize the enterprise reputation evaluation method based on the big data.
FIG. 4 is a block diagram of an enterprise reputation evaluation system based on big data in accordance with a preferred embodiment of the present invention.
As shown in FIG. 4, the present invention provides a big data based enterprise reputation evaluation system, the system comprising:
an initial unit 401, configured to acquire multidimensional feature data of each enterprise in the plurality of enterprises; preferably, acquiring the multi-dimensional feature data of each enterprise of the plurality of enterprises includes:
established date, real-life capital, registered capital, taxpayer qualification, management anomaly information, administrative punishment information and serious illegal information.
A processing unit 402, configured to clean the multidimensional feature data of each enterprise according to a consistency principle; preprocessing the characteristic data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme;
preferably, the processing unit 402 is configured to clean the multidimensional feature data of each enterprise according to a consistency principle, and includes:
judging the rationality of the feature data, and removing or correcting unreasonable feature data;
consistency processing is carried out on the measurement units of the characteristic data;
and supplementing the missing key information in the characteristic data.
Preferably, the processing unit 402 is configured to perform preprocessing on the feature data of each dimension in the cleaned multi-dimensions according to a preset data preprocessing scheme, where the preprocessing includes:
the characteristic data of each dimension is given different weights;
assigning points to the time length of the enterprise duration in the characteristic data according to a preset assigning standard;
calculating sales growth rate in the feature data, comprising: (business current term invoice total/business upper term invoice total) -1;
calculating customer loyalty in the feature data, comprising: interval ratio (number of clients transacted/number of clients last year);
calculating a large customer ranking in the feature data, comprising: the number of clients with the transaction amount of the sales order being more than the expected amount accounts for the ranking interval of the whole industry;
calculating the product quality in the characteristic data comprises the following steps: (qualified lot/total lot) a value of 100%;
evaluating the price index in the characteristic data, comprising: (price of commodity/average price), and determining a price stability in a ranking interval in the industry after computing variance by price de-duplication of commodity in the past year;
and evaluating commodity acceptance rate, logistics acceptance rate, service attitude acceptance rate and after-sales service acceptance rate in the feature data.
The training unit 403 is configured to train the established enterprise reputation evaluation model by using the preprocessed feature data of each dimension as a training sample until the training error reaches a preset critical value, and stop training the enterprise reputation evaluation model;
and a result unit 404, configured to evaluate the reputation of the target enterprise through the trained enterprise reputation evaluation model, and obtain a reputation score of the target enterprise.
The enterprise reputation evaluation system based on big data in the preferred embodiment of the present invention corresponds to the enterprise reputation evaluation method based on big data in the preferred embodiment of the present invention, and will not be described here again.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the invention can be realized by adopting various computer languages, such as object-oriented programming language Java, an transliteration script language JavaScript and the like.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
The invention has been described with reference to a few embodiments. However, as is well known to those skilled in the art, other embodiments than the above disclosed invention are equally possible within the scope of the invention, as defined by the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise therein. All references to "a/an/the [ means, component, etc. ]" are to be interpreted openly as referring to at least one instance of said means, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
Claims (10)
1. An enterprise reputation evaluation method based on big data, the method comprising:
acquiring multi-dimensional characteristic data of each enterprise in a plurality of enterprises;
cleaning the multidimensional characteristic data of each enterprise according to a consistency principle;
preprocessing the characteristic data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme;
taking the preprocessed characteristic data of each dimension as a training sample, training the established enterprise reputation evaluation model, and stopping training the enterprise reputation evaluation model until the training error reaches a preset critical value;
and evaluating the reputation of the target enterprise through the trained enterprise reputation evaluation model to obtain the reputation score of the target enterprise.
2. The method of claim 1, the obtaining multi-dimensional feature data for each of a plurality of businesses, comprising:
established date, real-life capital, registered capital, taxpayer qualification, management anomaly information, administrative punishment information and serious illegal information.
3. The method of claim 1, wherein the cleaning the multidimensional feature data of each enterprise according to a consistency principle comprises:
judging the rationality of the characteristic data, and removing or correcting unreasonable characteristic data;
carrying out consistency processing on the measurement units of the characteristic data;
and supplementing the missing key information in the characteristic data.
4. The method of claim 1, wherein the preprocessing of the feature data for each of the plurality of dimensions after cleaning according to a preset data preprocessing scheme comprises:
the characteristic data of each dimension is given different weights;
assigning points to the time length of the enterprise duration in the characteristic data according to a preset assigning standard;
calculating sales growth rate in the feature data, comprising: (business current term invoice total/business upper term invoice total) -1;
calculating customer loyalty in the feature data, comprising: interval ratio (number of clients transacted/number of clients last year);
calculating a large customer ranking in the feature data, comprising: the number of clients with the transaction amount of the sales order being more than the expected amount accounts for the ranking interval of the whole industry;
calculating the product quality in the characteristic data comprises the following steps: (qualified lot/total lot) a value of 100%;
evaluating the price index in the characteristic data, comprising: (price of commodity/average price), and determining a price stability in a ranking interval in the industry after computing variance by price de-duplication of commodity in the past year;
and evaluating commodity acceptance rate, logistics acceptance rate, service attitude acceptance rate and after-sales service acceptance rate in the feature data.
5. An enterprise reputation evaluation system based on big data, the system comprising:
the initial unit is used for acquiring multidimensional characteristic data of each enterprise in the plurality of enterprises;
the processing unit is used for cleaning the multidimensional characteristic data of each enterprise according to a consistency principle; preprocessing the characteristic data of each dimension in the cleaned multi-dimension according to a preset data preprocessing scheme;
the training unit is used for training the established enterprise reputation evaluation model by taking the preprocessed feature data of each dimension as a training sample until the training error reaches a preset critical value, and stopping training the enterprise reputation evaluation model;
and the result unit is used for evaluating the reputation of the target enterprise through the trained enterprise reputation evaluation model to acquire the reputation score of the target enterprise.
6. The system of claim 5, the acquiring multi-dimensional feature data for each of a plurality of businesses, comprising:
established date, real-life capital, registered capital, taxpayer qualification, management anomaly information, administrative punishment information and serious illegal information.
7. The system of claim 5, the processing unit configured to clean the multidimensional feature data for each enterprise on a consistency basis, comprising:
judging the rationality of the characteristic data, and removing or correcting unreasonable characteristic data;
carrying out consistency processing on the measurement units of the characteristic data;
and supplementing the missing key information in the characteristic data.
8. The system according to claim 5, wherein the processing unit is configured to perform preprocessing according to a preset data preprocessing scheme on the feature data of each dimension in the multi-dimensions after cleaning, and includes:
the characteristic data of each dimension is given different weights;
assigning points to the time length of the enterprise duration in the characteristic data according to a preset assigning standard;
calculating sales growth rate in the feature data, comprising: (business current term invoice total/business upper term invoice total) -1;
calculating customer loyalty in the feature data, comprising: interval ratio (number of clients transacted/number of clients last year);
calculating a large customer ranking in the feature data, comprising: the number of clients with the transaction amount of the sales order being more than the expected amount accounts for the ranking interval of the whole industry;
calculating the product quality in the characteristic data comprises the following steps: (qualified lot/total lot) a value of 100%;
evaluating the price index in the characteristic data, comprising: (price of commodity/average price), and determining a price stability in a ranking interval in the industry after computing variance by price de-duplication of commodity in the past year;
and evaluating commodity acceptance rate, logistics acceptance rate, service attitude acceptance rate and after-sales service acceptance rate in the feature data.
9. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for executing the method of any one of claims 1-4.
10. An electronic device, the electronic device comprising: a processor and a memory;
wherein,
the memory is used for storing the processor executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311772021.0A CN117893063A (en) | 2023-12-21 | 2023-12-21 | Enterprise reputation evaluation method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311772021.0A CN117893063A (en) | 2023-12-21 | 2023-12-21 | Enterprise reputation evaluation method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117893063A true CN117893063A (en) | 2024-04-16 |
Family
ID=90638756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311772021.0A Pending CN117893063A (en) | 2023-12-21 | 2023-12-21 | Enterprise reputation evaluation method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117893063A (en) |
-
2023
- 2023-12-21 CN CN202311772021.0A patent/CN117893063A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
| CN107103548A (en) | The monitoring method and system and risk monitoring and control method and system of network behavior data | |
| JP7017149B2 (en) | Information processing equipment, information processing method and information processing program using deep learning | |
| Fort | Breaking up is hard to do: Why firms fragment production across locations | |
| CN113919886A (en) | Data characteristic combination pricing method and system based on summer pril value and electronic equipment | |
| CN110378546B (en) | Method and apparatus for generating information | |
| CN111695979A (en) | Method, device and equipment for analyzing relation between raw material and finished product | |
| CN114723492B (en) | Enterprise portrait generation method and equipment | |
| CN112836964A (en) | Enterprise abnormity assessment system and assessment method | |
| CN116468273A (en) | Customer risk identification method and device | |
| CN115953021A (en) | Supplier risk analysis method and device based on machine learning | |
| CN116934160A (en) | Method and system for evaluating asset value of data element | |
| CN115147144A (en) | Data processing method and electronic equipment | |
| Dai et al. | Audit analytics: A field study of credit card after-sale service problem detection at a major bank | |
| CN117114812A (en) | Financial product recommendation method and device for enterprises | |
| KR101536536B1 (en) | Method for evaluating technology by adjusted reproduction cost approaching | |
| CN116629998A (en) | Automatic information counting method and device, electronic equipment and readable storage medium | |
| CN117422321A (en) | Patent value evaluation method, device, electronic equipment and storage medium | |
| CN116228403A (en) | Personal bad asset valuation method and system based on machine learning algorithm | |
| CN117893063A (en) | Enterprise reputation evaluation method and system based on big data | |
| CN114693428A (en) | Data determination method and device, computer readable storage medium and electronic equipment | |
| CN117751362A (en) | AI-enhanced audit platform including techniques for applying combinable assurance integrity frameworks | |
| CN113870007A (en) | Product recommendation method, device, equipment and medium | |
| CN113269412A (en) | Risk assessment method and related device | |
| Saygili | Taking advantage of computer assisted audit tools and techniques during testing phase in financial audits: An empirical study in a food processing company in Turkey |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |