CN116628206B - Enterprise credit analysis management system based on data analysis - Google Patents
Enterprise credit analysis management system based on data analysis Download PDFInfo
- Publication number
- CN116628206B CN116628206B CN202310673734.5A CN202310673734A CN116628206B CN 116628206 B CN116628206 B CN 116628206B CN 202310673734 A CN202310673734 A CN 202310673734A CN 116628206 B CN116628206 B CN 116628206B
- Authority
- CN
- China
- Prior art keywords
- credit
- enterprise
- social
- vocabulary
- preset
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 79
- 238000007405 data analysis Methods 0.000 title claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims description 36
- 230000007935 neutral effect Effects 0.000 claims description 33
- 238000011157 data evaluation Methods 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 16
- 230000007613 environmental effect Effects 0.000 claims description 10
- 230000008451 emotion Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012552 review Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000013481 data capture Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/268—Morphological analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses an enterprise credit analysis management system based on data analysis, which relates to the technical field of enterprise credit analysis and comprises a data grabbing module, an enterprise information database, a report output module, a self credit analysis module, a social credit analysis module, a comprehensive analysis module and a keyword characteristic database. The enterprise credit degree and the social credit degree are analyzed, so that the management level and the social responsibility of the enterprise are reflected, the enterprise credit awareness is further consolidated, the enterprise credit is comprehensively analyzed on the basis, the enterprise credit is more comprehensively estimated, the singleness of the traditional enterprise credit estimation is changed, the audience group of the enterprise credit estimation is wider, more comprehensive and accurate enterprise credit information can be provided for multiple roles of investors, suppliers, clients, job seekers and the like, and the public trust of the enterprise credit estimation is greatly improved.
Description
Technical Field
The invention relates to the technical field of enterprise credit analysis, in particular to an enterprise credit analysis management system based on data analysis.
Background
Credit is an inevitable product of social and economic development, and is an indispensable ring in the economic operation of modern markets. Maintaining and developing credit relationships is an important premise for protecting social economic order, and enterprise credit is not only focused by investors or borrowers in the financial market, but also by multiple parties in the general trading market, and with the development of economic contracts, enterprise credit becomes a prerequisite for cooperation and trading. Thus, enterprise credit system construction is a major concern for the construction of the entire social credit system.
At present, the phenomenon of enterprise credit deficiency is aggravated, the credit awareness is light, and the traditional enterprise credit assessment method mainly depends on assessing enterprise credit from two aspects of finance and law, so that the assessment result is one-sided due to excessive attention to asset guarantee, so that the enterprise credit assessment public trust is poor, service objects have limitations, further the audience group for enterprise credit assessment is small, and more comprehensive and accurate information is difficult to provide for multiple roles of investors, clients, job seekers and the like.
Disclosure of Invention
The invention aims to provide an enterprise credit analysis management system based on data analysis, so as to solve the problems set forth in the background technology.
The aim of the invention can be achieved by the following technical scheme: the enterprise credit analysis management system based on data analysis comprises a data capture module, an enterprise information database, a report output module, a self credit analysis module, a social credit analysis module, a comprehensive analysis module and a keyword characteristic database;
the data grabbing module is used for acquiring basic data of an enterprise and sending the basic data to the enterprise information database for storage;
the self credit analysis module is used for acquiring the business registration information, employee comments and labor dispute records of the enterprise, analyzing the self credit of the enterprise, generating a self credit good signal or a self credit warning signal according to the comparison between the self credit of the enterprise and a preset self credit threshold of the enterprise, and transmitting the self credit good signal or the self credit warning signal to the comprehensive analysis module;
the social credit analysis module is used for collecting social responsibility information and complaint records of enterprises, analyzing the social reliability of the enterprises, comparing the social reliability of the enterprises with a preset social reliability threshold corresponding to the enterprises to generate a social credit good signal or a social credit warning signal, and sending the social credit good signal or the social credit warning signal to the comprehensive analysis module;
the comprehensive analysis module is used for analyzing comprehensive credit of the enterprise, collecting financial and legal risk information of the enterprise, analyzing to obtain conventional credit of the enterprise, comparing the conventional credit of the enterprise with a preset conventional credit threshold of the enterprise, generating a conventional credit good signal or a conventional credit warning signal, receiving signals sent by the credit analysis module and the social credit analysis module to judge comprehensive credit of the enterprise, and sending a judging result to the report output module;
the report output module is used for receiving the judging result of the comprehensive analysis module, generating a prompting signal and prompting correspondingly when the comprehensive credit of the enterprise is general, and outputting an enterprise comprehensive credit analysis report based on the prompting signal when the comprehensive credit of the enterprise is excellent or good;
the enterprise information database is used for storing basic information of enterprises;
the keyword characteristic database is used for storing comment characteristic keywords and comprises a positive keyword list, a negative keyword list and a neutral keyword list, wherein the positive keyword list is used for storing keywords with vocabulary properties of positive, the negative keyword list is used for storing keywords with vocabulary properties of negative, and the neutral keyword list is used for storing keywords with vocabulary properties of neutral.
Preferably, the analysis of the enterprise's own credibility is performed as follows:
the method comprises the steps of researching real information of an enterprise in a staff questionnaire mode, wherein the real information of the enterprise comprises an actual office address, an actual staff number, an actual operation scale and an actual paramedic number, and acquiring the business registration information of the enterprise, wherein the business registration information comprises the office address, the staff number, the operation scale and the paramedic number;
comparing office addresses corresponding to business registration information of enterprises with actual office addresses, employee numbers corresponding to business registration information of the enterprises with actual employee numbers, enterprise operation scale with actual operation scale, and participants corresponding to business registration information of the enterprises with actual participants, generating real signals when the comparison is successful, generating false signals, counting the occurrence times of the real signals and the false signals, respectively marking the real signals and the false signals as fh and xj, and analyzing the occurrence times of the real signals and the false signals to obtain the authenticity ZS of the business registration information of the enterprises.
Collecting reviews of enterprise on-staff and off-staff, namely enterprise reviews, qualitatively judging the nature of the enterprise reviews through a keyword feature database, and counting the number of positive evaluations, negative evaluations and neutral evaluations, thereby analyzing the review coefficient PL of the enterprise;
acquiring labor dispute records in an enterprise, counting the occurrence times of the labor dispute records, and analyzing to obtain a labor specification coefficient LD corresponding to the enterprise;
the enterprise self-credit ME is obtained through the enterprise business registration information authenticity, the comment coefficient and the labor specification coefficient, the self-credit corresponding to the enterprise is compared with a preset self-credit threshold, when the self-credit corresponding to the enterprise is smaller than the preset self-credit threshold, a self-credit warning signal is generated, when the self-credit corresponding to the enterprise is larger than the preset self-credit threshold, a self-credit good signal is generated, and the self-credit warning signal or the self-credit good signal is sent to the comprehensive analysis module and is sent to the comprehensive analysis module.
Preferably, the enterprise comments are qualitatively determined through the keyword feature database, and the specific process is as follows:
obtaining enterprise comments as sample data, removing stop words in the sample data, simplifying the sample data, processing each simplified sample data by using a word segmentation tool, inputting each simplified sample data into the word segmentation tool to obtain vocabulary corresponding to each sample data, and forming a vocabulary list CH corresponding to each sample data by the vocabulary corresponding to each sample data r 'r represents the number of each sample data, r=1, 2, & gt, t, t is a positive integer, and the part of speech of the preset vocabulary is'Positive "," negative ", and" neutral ";
selecting the vocabulary in each vocabulary list, matching the vocabulary with the keywords stored in the keyword feature database, outputting the part of speech corresponding to the vocabulary if the vocabulary in each vocabulary list is successfully matched with the keywords stored in the keyword feature database, and counting the occurrence times of the parts of speech of positive, negative and neutral; if the matching of the vocabulary in each vocabulary list and the keywords stored in the keyword feature database is unsuccessful, invoking an emotion analysis interface to perform vocabulary emotion analysis on the vocabulary, if the vocabulary part is positive, increasing the occurrence frequency of the positive part of speech once, and sending the vocabulary to a positive keyword table in the keyword feature database for storage, if the vocabulary part is negative, increasing the occurrence frequency of the negative part of speech once, and sending the vocabulary to the positive keyword table in the keyword feature database for storage, if the vocabulary part is neutral, increasing the occurrence frequency of the neutral part of speech once, and sending the vocabulary to a neutral keyword table in the keyword feature database for storage, finally obtaining the occurrence frequency of each part of speech corresponding to each sample data, and recording the occurrence frequency as the occurrence frequency of each part of speech respectively
Obtaining an evaluation coefficient DX of each sample data by analysis r Marking the comment as a neutral comment when each sample data evaluation coefficient is equal to a preset sample data evaluation coefficient threshold value, marking the comment as a positive comment when each sample data evaluation coefficient is greater than the preset sample data evaluation coefficient threshold value, marking the comment as a negative comment when each sample data evaluation coefficient is less than the preset sample data evaluation coefficient threshold value, counting the times of positive, neutral and negative in enterprise comments, and marking the comments as Q respectively Frontal comments 、Q Negative comments 、Q Neutral comments 。
Preferably, the social credibility of the enterprise is analyzed, and the analysis process is as follows:
the method comprises the steps of obtaining social responsibility information of enterprises, wherein the social responsibility information comprises environment protection information and public welfare information, the environment protection information comprises total investment TZ, environment protection investment TZ', environment protection behavior records, the public welfare behavior records are extracted, records violating environment protection regulations in the environment protection behavior records are counted and recorded as WG, and the public welfare information comprises public welfare times G, total beneficiaries G and total duration T;
obtaining a first evaluation coefficient HB corresponding to the social credibility of the enterprise through analysis;
acquiring complaint records of an enterprise, extracting complaint time points and processing completion time points corresponding to the complaint records of the enterprise, and calculating the difference to obtain the corresponding acceptance time t of the complaint records B And also extracts the satisfaction score D corresponding to each complaint record of the enterprise B And complaint number ts;
obtaining a second evaluation coefficient TS corresponding to the enterprise through analysis;
and comparing the social reliability corresponding to the enterprise with a preset social reliability threshold value through analysis, generating a social credit warning signal when the social reliability corresponding to the enterprise is smaller than the preset social reliability threshold value, generating a social credit good signal when the social reliability corresponding to the enterprise is larger than the preset social reliability threshold value, and transmitting the social credit warning signal or the social credit good signal to the comprehensive analysis module.
Preferably, the comprehensive credibility of the enterprise is analyzed, and the specific analysis process is as follows:
collecting financial and legal risk information corresponding to an enterprise, counting the number CW of financial risk records and the number FW of legal risk records, obtaining conventional credit CT corresponding to the enterprise through analysis, comparing the conventional credit corresponding to the enterprise with a preset conventional credit threshold, generating a conventional credit warning signal when the conventional credit corresponding to the enterprise is smaller than the preset conventional credit threshold, and generating a conventional credit good signal when the conventional credit corresponding to the enterprise is larger than the preset conventional credit threshold;
acquiring self credit, social credit and conventional credit corresponding to an enterprise, analyzing to obtain comprehensive credit corresponding to the enterprise, comparing the comprehensive credit with a set comprehensive credit threshold, generating a primary credit signal if the comprehensive credit corresponding to the enterprise is greater than a preset comprehensive credit threshold, generating a secondary credit signal if the comprehensive credit corresponding to the enterprise is equal to the preset comprehensive credit threshold, and generating a tertiary credit signal if the comprehensive credit corresponding to the enterprise is less than the preset comprehensive credit threshold;
and when any one of the self credit warning signal, the social credit warning signal and the conventional credit warning signal and the primary credit signal or the secondary credit signal are identified, the comprehensive credit of the enterprise is judged to be good, and when any two or more of the self credit warning signal, the social credit warning signal and the conventional credit warning signal and any one of the secondary credit signal and the tertiary credit signal are identified, the comprehensive credit of the enterprise is judged to be general, and the judgment result is sent to the report output module.
The invention has the beneficial effects that:
1. by analyzing the credit rating and the social credit rating of the enterprise, the management level and the social responsibility of the enterprise are well reflected, and the credit awareness of the enterprise is further consolidated;
2. according to the enterprise credit evaluation method, the enterprise credit is comprehensively analyzed, the enterprise credit is more comprehensively evaluated, the singleness of the traditional enterprise credit evaluation is changed, the audience group of the enterprise credit evaluation is wider, more comprehensive and accurate enterprise credit information can be provided for multiple roles of investors, suppliers, clients, job seekers and the like, and the public trust of the enterprise credit evaluation is greatly improved.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a system block diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention discloses an enterprise credit analysis management system based on data analysis, which comprises a data capture module, an enterprise information database, a report output module, a self credit analysis module, a social credit analysis module, a comprehensive analysis module and a keyword characteristic database;
the data grabbing module is used for acquiring basic data of an enterprise and sending the basic data to the enterprise information database for storage.
The self credit analysis module is used for acquiring the business registration information, the employee comments and the labor dispute records of the enterprise, so that the self credit of the enterprise is analyzed, and the analysis steps are as follows:
the real information of the enterprise is researched in a staff questionnaire mode, the real information of the enterprise comprises an actual office address, an actual staff number, an actual operation scale and an actual participant number, and the staff registration information of the enterprise comprises the office address, the staff number, the operation scale and the participant number.
Comparing office addresses corresponding to business registration information of enterprises with actual office addresses, employee numbers corresponding to business registration information of enterprises with actual employee numbers, enterprise operation scale with actual operation scale, and participants corresponding to business registration information of enterprises with actual participants, generating real signals when the comparison is successful, otherwise generating false signals, counting the occurrence times of the real signals and the false signals, respectively recording as fh and xj, and according to the formulaAnd calculating to obtain the authenticity ZS of the business registration information of the enterprise.
The method comprises the steps of collecting comments of enterprise incumbent personnel and offstaff on the enterprise, namely enterprise comments, taking the enterprise comments as sample data, and removing stop words in each sample data, wherein the stop words comprise English characters, numbers, digital characters, punctuation marks and single Chinese characters with high use frequency, so that each sample data is simplified.
Processing each simplified sample data by using word segmentation tool, inputting each simplified sample data into word segmentation tool to obtain vocabulary corresponding to each sample data, and forming vocabulary list CH corresponding to each sample data by vocabulary corresponding to each sample data r ' r denotes the number of each sample data, r=1, 2,.., the s-th vocabulary corresponding to the r-th sample data is represented, s represents the number of each vocabulary, s=1, 2.
Selecting the vocabulary in each vocabulary list, matching the vocabulary with the keywords stored in the keyword feature database, outputting the part of speech corresponding to the vocabulary if the vocabulary in each vocabulary list is successfully matched with the keywords stored in the keyword feature database, and counting the occurrence times of the parts of speech of positive, negative and neutral; if the matching of the vocabulary in each vocabulary list and the keywords stored in the keyword feature database is unsuccessful, invoking an emotion analysis interface to perform vocabulary emotion analysis on the vocabulary, if the vocabulary part is positive, increasing the occurrence frequency of the positive part of speech once, and sending the vocabulary to the positive keyword list in the keyword feature database for storage, if the vocabulary part is negative, increasing the occurrence frequency of the negative part of speech once, and sending the vocabulary to the positive keyword list in the keyword feature database for storage, and if the vocabulary part is negative, sending the vocabulary to the positive keyword list in the keyword feature database for storageThe parts of speech is "neutral", the number of times of appearance of the "neutral" parts of speech is increased once, and the vocabulary is sent to a neutral keyword table in a keyword characteristic database for storage, finally the number of times of appearance of each part of speech corresponding to each sample data is obtained and respectively recorded as
According to the embodiment of the invention, the unsuccessfully matched vocabulary is subjected to vocabulary emotion analysis, and the unsuccessfully matched vocabulary is stored into different part-of-speech storage tables according to different parts-of-speech, so that a keyword feature library is continuously perfected, and more accurate judgment on the comment properties of enterprises is conveniently made.
Calculation by formula
Obtaining the data evaluation coefficient DX of each model r ，For the preset positive evaluation word weight factor, neutral evaluation word weight factor, negative evaluation word weight factor, ++>And marking the comment as a negative comment when each model data evaluation coefficient is smaller than a preset model data evaluation coefficient threshold value, marking the comment as a neutral comment when each model data evaluation coefficient is equal to the preset model data evaluation coefficient threshold value, and marking the comment as a positive comment when each model data evaluation coefficient is larger than the preset model data evaluation coefficient threshold value.
Obtaining comments of each comment corresponding to a target enterpriseProperties and counts the occurrence times of the products, which are respectively marked as Q Frontal comments 、Q Negative comments 、Q Neutral comments 。
By the formula
And calculating to obtain the comment coefficient PL of the enterprise.
Acquiring labor dispute records in enterprises, counting the occurrence times W of the labor dispute records, and passing through a formulaCalculating to obtain labor specification coefficients LD and R corresponding to enterprises Actual practice is that of Is the number of actual workers corresponding to the enterprise.
By the formula me=zs×β 1 +PL×β 2 +LD×β 3 Obtaining the self confidence of enterprises, beta 1 、β 2 、β 3 For a preset true degree weight factor, a comment coefficient weight factor and a labor specification coefficient weight factor, comparing the self-credit degree corresponding to the enterprise with a preset self-credit degree threshold, generating a self-credit warning signal when the self-credit degree corresponding to the enterprise is smaller than the preset self-credit degree threshold, generating a self-credit good signal when the self-credit degree corresponding to the enterprise is larger than the preset self-credit degree threshold, and transmitting the self-credit warning signal or the self-credit good signal to the comprehensive analysis module.
Further, the enterprise credit evaluation method and the enterprise credit evaluation system analyze the business registration information, the employee comments and the labor dispute records of the enterprise to obtain the self-credit of the enterprise, and the self-credit is used as one of the standards for evaluating the credit of the enterprise, so that the uniqueness of the credit evaluation of the traditional enterprise is changed.
The social credit analysis module is used for acquiring social responsibility information and complaint records of the enterprise, so that the social reliability of the enterprise is analyzed, and the analysis steps are as follows:
the method comprises the steps of obtaining social responsibility information of enterprises, wherein the social responsibility information comprises environment protection information and public welfare information, the environment protection information comprises total investment TZ, environment protection investment TZ', environment protection behavior records, the public welfare behavior records are extracted, records violating environment protection regulations in the environment protection behavior records are counted, the records are recorded as WG, and the public welfare information comprises public welfare times G, total beneficiaries G and total duration T.
According to the formulaObtaining a first evaluation coefficient HB, < ->Respectively a preset environmental protection investment weight factor, an environmental protection record weight factor and a public welfare weight factor.
According to the method and the device for the enterprise social credit assessment, the social responsibility information of the enterprise is obtained and analyzed and is used as a part of the enterprise social credit, so that the enterprise social credit can be more accurately reflected, the enterprise credit assessment range is wider, and the comprehensive performance is stronger.
Acquiring complaint records of an enterprise, extracting complaint time points and processing completion time points corresponding to the complaint records of the enterprise, and calculating the difference to obtain the corresponding acceptance time t of the complaint records B And also extracts the satisfaction score D corresponding to each complaint record of the enterprise B And the number of complaints ts.
According to the formula
Calculating to obtain a second evaluation coefficient TS, t ' corresponding to the enterprise is a preset processing time threshold, D ' is a preset satisfaction score threshold, TS ' is a preset complaint times threshold,the method comprises the steps of setting a preset acceptance duration influence factor, a satisfaction score influence factor and a complaint frequency influence factor.
Through the formula sh=hb×β 4 +TS×β 5 Obtaining social confidence level, beta, corresponding to the enterprise 4 And beta 5 And for the preset first evaluation coefficient weight factor and the second evaluation coefficient weight factor, when the social reliability corresponding to the enterprise is smaller than a preset social reliability threshold, generating a social credit warning signal, and when the social reliability corresponding to the enterprise is larger than the preset social reliability threshold, generating a social credit good signal, and transmitting the social credit warning signal or the social credit good signal to the comprehensive analysis module.
Further, the social reliability of the enterprise is analyzed, so that the social responsibility of the enterprise and the social image of the enterprise are comprehensively displayed, and the credit assessment public trust of the enterprise is increased.
The comprehensive analysis module is used for analyzing the comprehensive credibility of the enterprise, and the specific analysis steps are as follows:
collecting financial and legal risk information corresponding to enterprises, counting the number of financial risk records and legal risk records, respectively recording as CW and FW, and calculating through a formulaObtaining the conventional confidence level beta corresponding to the enterprise 6 And beta 7 And comparing the conventional credit corresponding to the enterprise with a preset conventional credit threshold for the preset financial risk influence factor and the legal risk influence factor, generating a conventional credit warning signal when the conventional credit corresponding to the enterprise is smaller than the preset conventional credit threshold, and generating a conventional credit good signal when the conventional credit corresponding to the enterprise is larger than the preset conventional credit threshold.
Acquiring self credit, social credit and conventional credit corresponding to an enterprise through a formulaObtaining the comprehensive credibility F, gamma corresponding to the enterprise 1 、γ 2 、γ 3 Respectively preset self-credit weighting factors, social credit weighting factors and conventional credit weighting factors, and integrating the comprehensive credit corresponding to enterprises with the set comprehensiveComparing the credit combination threshold, generating a first-level credit signal if the comprehensive credit corresponding to the enterprise is greater than a preset comprehensive credit threshold, generating a second-level credit signal if the comprehensive credit corresponding to the enterprise is equal to the preset comprehensive credit threshold, and generating a third-level credit signal if the comprehensive credit corresponding to the enterprise is less than the preset comprehensive credit threshold;
and when any one of the self credit warning signal, the social credit warning signal and the conventional credit warning signal and the primary credit signal or the secondary credit signal are identified, the comprehensive credit of the enterprise is judged to be good, and when any two or more of the self credit warning signal, the social credit warning signal and the conventional credit warning signal and any one of the secondary credit signal and the tertiary credit signal are identified, the comprehensive credit of the enterprise is judged to be general, and the judgment result is sent to the report output module.
The report output module is used for receiving the judging result of the comprehensive analysis module, generating a prompting signal and prompting correspondingly when the comprehensive credit of the enterprise is good or common, and outputting an enterprise comprehensive credit analysis report based on the prompting signal when the comprehensive credit of the enterprise is excellent.
The enterprise information database is used for storing basic information of enterprises.
The keyword feature database is used for storing comment feature keywords.
The foregoing is merely illustrative and explanatory of the invention, as it is apparent to those skilled in the art that various modifications and additions can be made to the specific embodiments described or in a similar manner without departing from the structure of the invention or beyond the scope of the invention as defined in the appended claims.
Claims (2)
1. The enterprise credit analysis management system based on data analysis comprises a data grabbing module, an enterprise information database and a report output module, and is characterized by also comprising a self credit analysis module, a social credit analysis module, a comprehensive analysis module and a keyword characteristic database;
the data grabbing module is used for acquiring basic data of an enterprise and sending the basic data to the enterprise information database for storage;
the self credit analysis module is used for analyzing the self credit degree of the enterprise to obtain the self credit degree of the enterprise, comparing the self credit degree of the enterprise with a preset self credit degree threshold value, generating a self credit signal according to a comparison result, wherein the self credit signal comprises a self credit good signal and a self credit warning signal, and transmitting the self credit signal of the enterprise to the comprehensive analysis module;
the social credit analysis module is used for analyzing the social credibility of the enterprise to obtain the social credibility of the enterprise, comparing the social credibility of the enterprise with a preset social credibility threshold value, generating a social credit signal according to a comparison result, wherein the social credit signal comprises a social credit good signal and a social credit warning signal, and transmitting the social credit signal of the enterprise to the comprehensive analysis module;
the comprehensive analysis module is used for analyzing the comprehensive credit of the enterprise, collecting financial and legal risk information of the enterprise, analyzing to obtain the conventional credit of the enterprise, receiving signals sent by the credit analysis module and the social credit analysis module, judging the comprehensive credit of the enterprise, and sending the judging result to the report output module;
the report output module is used for receiving the judging result of the comprehensive analysis module and outputting an enterprise comprehensive credit analysis report;
the enterprise information database is used for storing basic information of enterprises;
the keyword feature database is used for storing comment feature keywords;
the self credibility of the enterprise is analyzed, and the analysis process is as follows:
the method comprises the steps of researching the real information of enterprises in a staff questionnaire mode;
acquiring business registration information of an enterprise, comparing office addresses corresponding to the business registration information of the enterprise with actual office addresses, employee numbers corresponding to the business registration information of the enterprise with actual employee numbers, enterprise operation scale with actual operation scale, and insurers corresponding to the business registration information of the enterprise with actual insurers, generating a real signal when the comparison is successful, otherwise generating a false signal, counting the occurrence times of the real signal and the false signal, respectively marking the frequency as fh and xj, and according to a formulaCalculating to obtain the authenticity ZS of the business registration information of the enterprise;
collecting comments of enterprise on staff and off staff, namely enterprise comments, carrying out qualitative judgment on the enterprise comments through a keyword feature database, judging the properties of the enterprise comments, wherein the properties of the comments comprise positive evaluation, negative evaluation and neutral evaluation, counting the number of the positive evaluation, the negative evaluation and the neutral evaluation, acquiring the comment properties of each comment corresponding to a target enterprise, counting the occurrence frequency of each comment, and marking the comments as Q respectively Frontal comments 、Q Negative comments 、Q Neutral comments ；
By the formulaCalculating to obtain comment coefficients PL of enterprises;
acquiring labor dispute records in enterprises, counting the occurrence times W of the labor dispute records, and passing through a formulaCalculating to obtain labor specification coefficients LD and R corresponding to enterprises Actual practice is that of The number of actual staff corresponding to the enterprise;
by the formula me=zs×β 1 +PL×β 2 +LD×β 3 ObtainingThe self confidence of enterprises, beta 1 、β 2 、β 3 Comparing the self credit corresponding to the enterprise with a preset self credit threshold for a preset true degree weight factor, a comment coefficient weight factor and a labor specification coefficient weight factor, generating a self credit warning signal when the self credit corresponding to the enterprise is smaller than the preset self credit threshold, generating a self credit good signal when the self credit corresponding to the enterprise is larger than the preset self credit threshold, and transmitting the self credit warning signal or the self credit good signal to a comprehensive analysis module;
the enterprise comments are characterized by the keyword feature database, and the specific process is as follows:
the method comprises the steps of obtaining enterprise comments as sample data, simplifying and word segmentation processing is carried out on the sample data to obtain vocabularies corresponding to each sample data, forming a vocabulary list corresponding to each sample data by the vocabularies corresponding to each sample data, and presetting the parts of speech of the vocabularies as positive, negative and neutral;
selecting the vocabulary in each vocabulary list, matching the vocabulary with the keywords stored in the keyword feature database, and outputting the part of speech corresponding to the vocabulary if the vocabulary in each vocabulary list is successfully matched with the keywords stored in the keyword feature database; if the matching of the vocabulary in each vocabulary list and the keywords stored in the keyword feature database is unsuccessful, invoking an emotion analysis interface to perform vocabulary emotion analysis on the vocabulary, if the vocabulary part is positive, sending the vocabulary to a positive keyword table in the keyword feature database to store, if the vocabulary part is negative, sending the vocabulary to a negative keyword table in the keyword feature database to store, if the vocabulary part is neutral, sending the vocabulary to a neutral keyword table in the keyword feature database to store, counting the occurrence times of each part of speech in each vocabulary list, if the matching of the vocabulary in each vocabulary list and the keywords stored in the keyword feature database is unsuccessful, invoking an emotion analysis interface to perform vocabulary emotion analysis on the vocabulary, if the vocabulary part is positive, sending the vocabulary part of speech to the positive keyword feature database to count the number of times of each part of speech in each vocabulary listThe present times are increased once, the vocabulary is sent to a positive keyword list in a keyword characteristic database for storage, if the vocabulary part is negative, the number of times of occurrence of the negative part of speech is increased once, the vocabulary is sent to the positive keyword list in the keyword characteristic database for storage, if the vocabulary part of speech is neutral, the number of times of occurrence of the neutral part of speech is increased once, the vocabulary is sent to the neutral keyword list in the keyword characteristic database for storage, finally, the number of times of occurrence of each part of speech corresponding to each sample data is obtained and recorded as follows respectively
Calculation by formula
Obtaining the data evaluation coefficient DX of each model r ，For the preset positive evaluation word weight factor, neutral evaluation word weight factor, negative evaluation word weight factor, ++>For the reference appearance frequency of the neutral word, deltaC is the allowable difference of the preset appearance frequency of the neutral word, e is a natural constant, when each model data evaluation coefficient is smaller than a preset model data evaluation coefficient threshold value, the comment is marked as a negative comment, when each model data evaluation coefficient is equal to the preset model data evaluation coefficient threshold value, the comment is marked as a neutral comment, and when each model data evaluation coefficient is larger than the preset model data evaluation coefficient threshold valueMarking the comment as a positive comment; marking the comment as positive, and counting the occurrence times of positive evaluation, negative evaluation and neutral evaluation;
the social credibility of the enterprise is analyzed, and the analysis process is as follows:
acquiring social responsibility information of enterprises, including environmental protection information and public welfare information; the environmental protection information comprises total investment TZ, environmental protection investment TZ', environmental protection behavior records and public welfare behavior records, the records violating environmental protection regulations in the environmental protection behavior records are extracted and counted, the records are recorded as WG, and the public welfare information comprises public welfare times G, total beneficiaries G and total duration period T;
according to the formulaA first evaluation coefficient HB corresponding to the enterprise is obtained,respectively preset environmental protection investment weight factors, environmental protection record weight factors and public welfare weight factors;
acquiring complaint records of an enterprise, extracting complaint time points and processing completion time points corresponding to the complaint records of the enterprise, and calculating the difference to obtain the corresponding acceptance time t of the complaint records B And also extracts the satisfaction score D corresponding to each complaint record of the enterprise B And complaint number ts;
according to the formula
Calculating to obtain a second evaluation coefficient TS, t ' corresponding to the enterprise is a preset processing time threshold, D ' is a preset satisfaction score threshold, TS ' is a preset complaint times threshold,is a preset acceptance duration influence factor and is fullAn intention score influence factor, a complaint number influence factor;
through the formula sh=hb×β 4 +TS×β 5 Obtaining social confidence level, beta, corresponding to the enterprise 4 And beta 5 And comparing the social reliability corresponding to the enterprise with a preset social reliability threshold for the preset first evaluation coefficient weight factor and the second evaluation coefficient weight factor, generating a social reliability warning signal when the social reliability corresponding to the enterprise is smaller than the preset social reliability threshold, generating a social reliability good signal when the social reliability corresponding to the enterprise is larger than the preset social reliability threshold, and transmitting the social reliability warning signal or the social reliability good signal to the comprehensive analysis module.
2. The data analysis-based enterprise credit analysis management system of claim 1, wherein: the comprehensive credibility of the enterprise is analyzed, and the specific analysis process is as follows:
collecting financial and legal risk information corresponding to an enterprise, counting the number of financial risk records and legal risk records, obtaining conventional credit corresponding to the enterprise through analysis, comparing the conventional credit corresponding to the enterprise with a preset conventional credit threshold, generating a conventional credit warning signal when the conventional credit corresponding to the enterprise is smaller than the preset conventional credit threshold, and generating a conventional credit good signal when the conventional credit corresponding to the enterprise is larger than the preset conventional credit threshold;
acquiring self credit, social credit and conventional credit corresponding to an enterprise, analyzing to obtain comprehensive credit corresponding to the enterprise, comparing the comprehensive credit with a set comprehensive credit threshold to generate a grade signal, generating a primary credit signal if the comprehensive credit corresponding to the enterprise is greater than the preset comprehensive credit threshold, generating a secondary credit signal if the comprehensive credit corresponding to the enterprise is equal to the preset comprehensive credit threshold, and generating a tertiary credit signal if the comprehensive credit corresponding to the enterprise is less than the preset comprehensive credit threshold;
and receiving signals of the self credit analysis module and the social credit analysis module, extracting a first-level credit signal, a second-level credit signal and a third-level credit signal, identifying the signals, judging that the comprehensive credit of the enterprise is excellent when the first-level credit signal, the self credit good signal, the social credit good signal and the conventional credit good signal are simultaneously identified, judging that the comprehensive credit of the enterprise is good when any one of the self credit warning signal, the social credit warning signal and the conventional credit warning signal and the first-level credit signal or the second-level credit signal are identified, judging that the comprehensive credit of the enterprise is common when other conditions are identified, and sending a judging result to the report output module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310673734.5A CN116628206B (en) | 2023-06-08 | 2023-06-08 | Enterprise credit analysis management system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310673734.5A CN116628206B (en) | 2023-06-08 | 2023-06-08 | Enterprise credit analysis management system based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116628206A CN116628206A (en) | 2023-08-22 |
| CN116628206B true CN116628206B (en) | 2024-01-05 |
Family
ID=87613367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310673734.5A Active CN116628206B (en) | 2023-06-08 | 2023-06-08 | Enterprise credit analysis management system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116628206B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122432A (en) * | 2017-04-18 | 2017-09-01 | 广东数相智能科技有限公司 | CSR analysis method, device and system |
| CN108269023A (en) * | 2018-01-31 | 2018-07-10 | 合肥和钧正策信息技术有限公司 | One kind is based on big data goodwill comprehensive evaluating system |
| CN108629507A (en) * | 2018-05-03 | 2018-10-09 | 上海第二工业大学 | A kind of enterprise credit management system |
| CN108846547A (en) * | 2018-05-06 | 2018-11-20 | 成都信息工程大学 | A kind of Enterprise Credit Risk Evaluation method of dynamic adjustment |
| CN109766359A (en) * | 2018-12-26 | 2019-05-17 | 科大国创软件股份有限公司 | A kind of credit main body comprehensive analysis management system and method |
| KR102047859B1 (en) * | 2018-06-18 | 2019-11-22 | 주식회사 비즈부스터 | Corporate credit rating server based on deep learning and method for corporate credit rating using the same |
| CN113158669A (en) * | 2021-04-28 | 2021-07-23 | 河北冀联人力资源服务集团有限公司 | Method and system for identifying positive and negative comments of employment platform |
| CN113674075A (en) * | 2020-05-14 | 2021-11-19 | 瑞泽信用评级有限公司 | Method for credit rating of enterprise debt financing tool |
| CN113807625A (en) * | 2020-06-16 | 2021-12-17 | 朱泽华 | Method for grading credit of electronic commerce enterprise main body |
| CN113888278A (en) * | 2021-10-14 | 2022-01-04 | 黑龙江省范式智能技术有限公司 | Data analysis method and device based on enterprise credit line analysis model |
| CN116091196A (en) * | 2021-11-02 | 2023-05-09 | 河北省惠信大数据科技服务有限公司 | Method for controlling local financial risk through enterprise credit |
-
2023
- 2023-06-08 CN CN202310673734.5A patent/CN116628206B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122432A (en) * | 2017-04-18 | 2017-09-01 | 广东数相智能科技有限公司 | CSR analysis method, device and system |
| CN108269023A (en) * | 2018-01-31 | 2018-07-10 | 合肥和钧正策信息技术有限公司 | One kind is based on big data goodwill comprehensive evaluating system |
| CN108629507A (en) * | 2018-05-03 | 2018-10-09 | 上海第二工业大学 | A kind of enterprise credit management system |
| CN108846547A (en) * | 2018-05-06 | 2018-11-20 | 成都信息工程大学 | A kind of Enterprise Credit Risk Evaluation method of dynamic adjustment |
| KR102047859B1 (en) * | 2018-06-18 | 2019-11-22 | 주식회사 비즈부스터 | Corporate credit rating server based on deep learning and method for corporate credit rating using the same |
| CN109766359A (en) * | 2018-12-26 | 2019-05-17 | 科大国创软件股份有限公司 | A kind of credit main body comprehensive analysis management system and method |
| CN113674075A (en) * | 2020-05-14 | 2021-11-19 | 瑞泽信用评级有限公司 | Method for credit rating of enterprise debt financing tool |
| CN113807625A (en) * | 2020-06-16 | 2021-12-17 | 朱泽华 | Method for grading credit of electronic commerce enterprise main body |
| CN113158669A (en) * | 2021-04-28 | 2021-07-23 | 河北冀联人力资源服务集团有限公司 | Method and system for identifying positive and negative comments of employment platform |
| CN113888278A (en) * | 2021-10-14 | 2022-01-04 | 黑龙江省范式智能技术有限公司 | Data analysis method and device based on enterprise credit line analysis model |
| CN116091196A (en) * | 2021-11-02 | 2023-05-09 | 河北省惠信大数据科技服务有限公司 | Method for controlling local financial risk through enterprise credit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116628206A (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8438089B1 (en) | Method and apparatus for transaction verification | |
| CN107608958B (en) | Contract text risk information mining method and system based on unified modeling of clauses | |
| Peng et al. | Detecting Spam Review through Sentiment Analysis. | |
| Morimoto et al. | Corporate social responsibility audit: From theory to practice | |
| Zhaokai et al. | Contract analytics in auditing | |
| US9477750B2 (en) | System and method for real-time dynamic measurement of best-estimate quality levels while reviewing classified or enriched data | |
| KR101125417B1 (en) | Method and system for assessing data quality | |
| Adiloğlu et al. | A multicriterion decision support methodology for audit opinions: the case of audit reports of distressed firms in Turkey | |
| US20130024467A1 (en) | Distributed online collaboration platform incorporating unstructured and structured data | |
| Kleinman et al. | Why do auditors fail to identify fraud? An exploration | |
| CN116628206B (en) | Enterprise credit analysis management system based on data analysis | |
| CN116151840B (en) | User service data intelligent management system and method based on big data | |
| Janvrin et al. | SOX 404 (b) audits: Evidence from auditing the financial close process of the accounting system | |
| CN114611515A (en) | Method and system for identifying actual control person of enterprise based on enterprise public opinion information | |
| CN110766091B (en) | Method and system for identifying trepanning loan group partner | |
| TW201837824A (en) | Conversational financial management robot system and method including a communication module and a portfolio investment artificial intelligence server | |
| TWI676953B (en) | Beneficial owner auditing device | |
| US20140344172A1 (en) | Data analytics platform using social network and web data to identify a pattern or anomaly among relevant events and entities | |
| CN112949963A (en) | Employee service quality evaluation method and device, storage medium and intelligent equipment | |
| CN116308134B (en) | Audit data online auditing method and system based on data processing | |
| Diane Janvrin PhD | Textual analysis for accountants | |
| Deaconu et al. | Measuring the convergence degree between accounting and valuation standards: Case study on intangible assets | |
| CN116757807B (en) | Intelligent auxiliary label evaluation method based on optical character recognition | |
| CN114240405B (en) | Intelligent customs management system based on data analysis | |
| Wang et al. | Examining the Usability of the Annual Comprehensive Financial Report’s MD&A using Textual Analytics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231214 Address after: 830054 Room 1001-10, 10th Floor, Block E, Innovation Plaza, No. 2288 Siping Road, High tech Zone (Xinshi District), Urumqi City, Xinjiang Uygur Autonomous Region Applicant after: Urumqi Huizhi Industrial Information Technology Co.,Ltd. Address before: 1018, 10th Floor, Main Building, Cultural and Creative Building, No. 60 Fenghuang East Road, Hailing District, Taizhou City, Jiangsu Province, 225300 Applicant before: Jiangsu Wanhe Information Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |