A method, apparatus, equipment, and storage medium for risk early warning of power contractors.

Abstract

This invention discloses a method, apparatus, equipment, and storage medium for risk early warning of power contractors, belonging to the technical field of power contractor risk early warning. The invention includes four steps: Step 1: generating a risk profile of the power contractor; Step 2: quantitatively assessing the power contractor's risk resistance capability; Step 3: calculating the relative risk value of the power contractor enterprise; Step 4: based on pre-set thresholds as early warning conditions, issuing risk warnings to power contractors reaching high-risk and medium-risk levels, and outputting the relative risk value and indicator information for the warning; no warning is issued for low-risk contractors. This invention automates the entire process from data collection and classification of power contractor risk activities, generation of profile indicators, quantitative calculation and assessment, relative risk value calculation, and risk early warning. The entire process is based entirely on data-driven decision-making to achieve risk quantification and early warning, fully considering the relative numerical assessment of risk indicators and risk resistance capabilities, thus improving the accuracy of risk early warning.

Description

Technical Field

[0001] This invention relates to the field of risk warning technology for power contractors, and specifically to a method, apparatus, equipment, and storage medium for risk warning of power contractors. Background Technology

[0002] Currently, risk warnings for power contractors rely primarily on manual identification, and also utilize contractor information from contractor management systems or ERP systems for assessment. However, manual information analysis and risk diagnosis remain indispensable. Existing power contractor risk warning systems have the following drawbacks:

[0003] 1. The identification of contractor risks is greatly affected by the limitations of information and the subjectivity of manual diagnosis. Professional risk management personnel are needed to diagnose and analyze risk information, which cannot achieve the effect of automated early warning.

[0004] 2. Risk information is often collected, stored, and presented in different information systems or hardware devices, resulting in low timeliness of risk information processing. The dispersed storage of risk information leads to inconsistent and fragmented structures, resulting in slow, inaccurate, and difficult-to-observe overall risk information processing and early warning.

[0005] To address the aforementioned problems, this invention provides a method, apparatus, equipment, and storage medium for risk early warning of power contractors. Summary of the Invention

[0006] To address the aforementioned technical shortcomings, the present invention aims to provide a method and apparatus for risk early warning of power contractors. This method generates risk profiles of power contractors, quantitatively assesses their risk resistance capabilities, calculates their relative risk values, and issues risk warnings to power contractors reaching high-risk and medium-risk levels. It automates the entire process from data collection and classification of power contractor risk activities, generation of profile indicators, quantitative calculation and assessment, relative risk value calculation, and risk early warning. The entire process is based entirely on data-driven decision-making to achieve risk quantification and early warning, and fully considers the relative numerical assessment of risk indicators and risk resistance capabilities, thereby improving the accuracy of risk early warning. This invention solves the technical problems raised in the background section.

[0007] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a method for risk early warning of power contractors, comprising the following steps:

[0008] Step 1: Generate a risk profile of the power contractor: Collect relevant risk activity information data of the power contractor during the observation period, process the risk activity information data into risk indicators according to preset risk rules and elements, form a structured risk assessment system, and constitute the risk profile of the power contractor.

[0009] Step 2: Conduct a quantitative assessment of the power contractor's risk resistance capability, categorize the corresponding information types to generate relevant risk indicators, and obtain the power contractor's risk resistance capability level; wherein, the quantitative assessment of risk resistance capability includes the power contractor's business registration change information, judicial data, corporate credit data, operational fluctuation data, corporate public opinion data, and corporate qualification change data;

[0010] Step 3: Based on the risk profile obtained in Step 1 and the risk resistance level obtained in Step 2, the relative risk value of the power contractor is calculated using a risk index normalization and relative risk value calculation model. The calculation process for the relative risk value of the power contractor is as follows:

[0011] Risk indicator normalization: This involves mapping raw indicator values ​​of different dimensions to a risk score ranging from 0 to 100; for a specific indicator i, its risk score S... i The calculation is as follows:

[0012]

[0013] Among them, X i X represents the original observed value of this indicator. min and X max These are the industry's empirical minimum and maximum values ​​for this indicator;

[0014] Construct a relative risk value calculation model: Calculate the normalized risk value V i :

[0015] Among them, S i The indicator is the risk score, and R represents the risk resistance level.

[0016] Step Four: Based on the relative risk value obtained in Step Three, and using pre-set thresholds as early warning conditions (thresholds include high risk, medium risk, and low risk), issue risk warnings to power contractors reaching high and medium risk levels, and output the relative risk value and indicator information for the warning. No warning is issued for low-risk contractors. These steps automate the entire process from data collection and classification of power contractor risk activities, generation of profiling indicators, quantitative calculation and evaluation, relative risk value calculation, and risk early warning. The entire process is based entirely on data-driven decision-making to achieve risk quantification and early warning, and fully considers the relative numerical assessment of risk indicators and risk resistance capabilities, improving the accuracy of risk early warning.

[0017] Preferably, the risk activity information data mentioned in step one includes the power contractor's business registration change information, judicial data, corporate credit data, operational fluctuation data, public opinion data, and qualification change data.

[0018] Preferably, in step one, the risk activity information data is processed into risk indicators based on preset risk rules and elements to form a structured risk assessment system, which constitutes the risk profile of the power contractor. This includes the following process:

[0019] Step 11: Based on the business registration change information provided by the power contractor, classify the types of business registration changes, such as changes in legal representative and changes in business address; generate corresponding risk indicators: major business registration changes, general business registration changes; generate risk indicators based on the frequency of changes: frequent changes, changes in the past 6 months;

[0020] Step 12: Based on the judicial data of the power contract, classify the information types of the judicial data, such as sales contract disputes, equity disputes, personnel disputes, and administrative penalties; generate corresponding risk indicators: serious violations, general violations, and too many economic disputes;

[0021] Step 13: Based on the enterprise credit data provided by the power contractor, classify the information types of the enterprise credit data, such as dishonest enterprises, consumption restriction orders, executors, credit ratings, etc.; generate corresponding risk indicators: the number of times currently registered dishonest persons subject to enforcement, and the total number of records of high consumption restrictions;

[0022] Step 14: Based on the operational fluctuation data provided by the power contractors, categorize the information types of the operational fluctuation data, such as bidding performance, personnel size, and annual revenue; generate corresponding risk indicators: stable operation, capacity warning, and business decline;

[0023] Step 15: Based on the corporate public opinion data provided by the power contractor, including business news, personnel changes, brand reputation, etc.; categorize the information types of the corporate public opinion data and generate corresponding risk indicators: brand exposure, negative public opinion ratio, and serious negative news;

[0024] Step 16: Classify the changes in the qualifications of the power contractor companies into information types such as mandatory national qualifications, professional qualifications, business qualifications, quality certificates, and honorary qualifications; generate corresponding risk indicators: expired or invalid mandatory qualifications, missing professional qualifications, and honorary evaluations.

[0025] Preferably, step two involves a quantitative assessment of the power contractor's risk resistance capability, including the following process:

[0026] Step 21: Different power contractors have different risk resistance capabilities. To quantify the risk tolerance of power contractors, we collect indicators representing their risk resistance capabilities, such as registered capital, paid-in capital, number of employees, annual revenue, annual profit, debt ratio, intellectual property rights, corporate qualifications, and honors and awards, for comprehensive evaluation.

[0027] Step 22: Name the indicators of the contractor's risk resistance capability as I1', I'2, ..., I' n Weight parameters w1, w2, ..., w n The weighting of different indicators is used to calculate the overall risk resistance score R.

[0028] R = w1·I1' + w2·I'2 + ... + w n ·I' n ;

[0029] The overall risk resistance score R is quantified into 1-5 levels, with the higher the level, the stronger the risk resistance.

[0030] Preferably, the score R level classification of the comprehensive risk resistance capability is based on a sample distribution percentile method; the percentile of the R values ​​of all contractor samples is calculated, and the level is mapped according to the percentiles shown in the level mapping relationship, which is as follows:

[0031] Risk resistance level - description - percentile range of comprehensive score R

[0032] Weak - Micro and small enterprises, with very low risk tolerance - R <P 20 ;

[0033] General-sized and medium-sized enterprises with basic stability - P 20 ≤R <P 40 ;

[0034] Medium-sized regional or industry-specific important enterprises - P 40 ≤R <P 70 ;

[0035] Good - Large enterprise with strong capital and technology - P 70 ≤R <P 90 ;

[0036] Strong - Industry leaders or large group enterprises - R≥P 90 ;

[0037] Among them, P x This represents the value of the xth percentile in the dataset.

[0038] A power contractor risk warning device, wherein the device performs the aforementioned power contractor risk warning method, comprising:

[0039] The judicial risk assessment module is used to classify the information types of judicial data and assess the corresponding risk indicators.

[0040] The enterprise credit risk assessment module is used to classify the information types of its credit data and assess the corresponding risk indicators.

[0041] The business risk assessment module is used to categorize the information types of its business data and assess the corresponding risk indicators.

[0042] The corporate public opinion risk assessment module is used to classify the types of public opinion information and assess the corresponding risk indicators.

[0043] The Enterprise Qualification Risk Assessment Module is used to categorize the types of information related to its qualifications and assess the corresponding risk indicators.

[0044] The enterprise risk resistance assessment module evaluates the corresponding risk resistance rating based on the enterprise's risk resistance index values.

[0045] The enterprise relative risk value calculation and risk level early warning module calculates the relative risk value and provides early warnings of the risk level based on the enterprise's various risk indicators and risk resistance capabilities.

[0046] Preferably, the enterprise risk resistance assessment module performs level mapping based on percentiles shown in the level mapping relationship, which is as follows:

[0047] Risk resistance level - description - percentile range of comprehensive score R

[0048] Weak - Micro and small enterprises, with very low risk tolerance - R <P 20 ;

[0049] General-sized and medium-sized enterprises with basic stability - P 20 ≤R <P 40 ;

[0050] Medium-sized regional or industry-specific important enterprises - P 40 ≤R <P 70 ;

[0051] Good - Large enterprise with strong capital and technology - P 70 ≤R <P 90 ;

[0052] Strong - Industry leaders or large group enterprises - R≥P 90 ;

[0053] Among them, P x This represents the value of the xth percentile in the dataset.

[0054] Preferably, the enterprise relative risk value calculation and risk level early warning module maps the original indicator values ​​of different dimensions to a risk score of 0-100 and calculates the normalized risk value.

[0055] A computer device includes a processor and a memory, the memory storing a computer program, wherein the processor executes the computer program to implement the steps of the aforementioned method.

[0056] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned method.

[0057] The beneficial effects of this invention are as follows:

[0058] This invention automates the entire process from data collection and classification of power contractor risk activities, generation of profile indicators, quantitative assessment of power contractors' risk resistance capabilities, calculation of relative risk values ​​for power contractor enterprises, and risk warning for power contractors that reach high-risk and medium-risk levels. The entire process is based entirely on data-driven decision-making to achieve risk quantification and early warning, and fully considers the relative numerical assessment of risk indicators and risk resistance capabilities, thereby improving the accuracy of risk warning. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 A flowchart illustrating a method for risk warning of power contractors provided in an embodiment of the present invention.

[0061] Figure 2 This is a flowchart illustrating the structured risk assessment system used in this invention.

[0062] Figure 3 This is a flowchart illustrating the quantitative assessment of the risk resistance capabilities of power contractors in this invention.

[0063] Figure 4 This is a schematic diagram of the structure of a risk warning device for power contractors according to the present invention. Detailed Implementation

[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] Example:

[0066] like Figure 1 As shown, the present invention provides a method for risk warning of power contractors, including the following steps:

[0067] Step 1: Generate a risk profile of the power contractor: Collect relevant risk activity information data of the power contractor during the observation period, process the risk activity information data into risk indicators according to preset risk rules and elements, form a structured risk assessment system, and constitute the risk profile of the power contractor.

[0068] Step 2: Conduct a quantitative assessment of the power contractor's risk resistance capability, categorize the corresponding information types to generate relevant risk indicators, and obtain the power contractor's risk resistance capability level; wherein, the quantitative assessment of risk resistance capability includes the power contractor's business registration change information, judicial data, corporate credit data, operational fluctuation data, corporate public opinion data, and corporate qualification change data;

[0069] Step 3: Based on the risk profile obtained in Step 1 and the risk resistance level obtained in Step 2, the relative risk value of the power contractor is calculated using a risk index normalization and relative risk value calculation model. The calculation process for the relative risk value of the power contractor is as follows:

[0070] Risk indicator normalization: This involves mapping raw indicator values ​​of different dimensions to a risk score ranging from 0 to 100; for a specific indicator i, its risk score S... i The calculation is as follows:

[0071]

[0072] Among them, X i X represents the original observed value of this indicator. min and X max These are the industry's empirical minimum and maximum values ​​for this indicator;

[0073] Construct a relative risk value calculation model: Calculate the normalized risk value V i :

[0074] Among them, S i The indicator is the risk score, and R represents the risk resistance level.

[0075] Step 4: Based on the relative risk value obtained in Step 3, and using pre-set thresholds as early warning conditions, the thresholds include high risk, medium risk, and low risk; issue risk warnings to power contractors that reach the high risk and medium risk levels, and output the relative risk value and indicator information for the warning; do not issue warnings for low risk.

[0076] In this embodiment, by generating risk profiles of power contractors, quantitatively assessing their risk resistance capabilities, calculating their relative risk values, and issuing risk warnings to power contractors that reach high-risk and medium-risk levels, the entire process of collecting and classifying risk activity data of power contractors, generating profile indicators, quantitatively calculating and assessing them, calculating relative risk values, and issuing risk warnings is fully automated. The entire process is based entirely on data-driven decision-making to achieve risk quantification and warnings, and fully considers the relative numerical assessment of risk indicators and risk resistance capabilities, thereby improving the accuracy of risk warnings.

[0077] Furthermore, the risk activity information data mentioned in step one includes the power contractor's business registration changes, judicial data, corporate credit data, operational fluctuation data, public opinion data, qualification change data, etc.

[0078] Furthermore, such as Figure 2 As shown, in step one, based on preset risk rules and elements, the risk activity information data is processed into risk indicators to form a structured risk assessment system, which constitutes the risk profile of the power contractor. This includes the following process:

[0079] Step 11: Based on the business registration change information provided by the power contractor, classify the types of business registration changes, such as changes in legal representative and changes in business address; generate corresponding risk indicators: major business registration changes, general business registration changes; generate risk indicators based on the frequency of changes: frequent changes, changes in the past 6 months, etc.

[0080] Step 12: Based on the judicial data of the power contract, classify the information types of the judicial data, such as sales contract disputes, equity disputes, personnel disputes, administrative penalties, etc.; generate corresponding risk indicators: serious violations, general violations, too many economic disputes, etc.

[0081] Step 13: Based on the enterprise credit data provided by the power contractor, classify the information types of the enterprise credit data, such as dishonest enterprises, consumption restriction orders, executors, credit ratings, etc.; generate corresponding risk indicators: the number of times currently registered dishonest persons subject to enforcement, the total number of records of high consumption restrictions, etc.

[0082] Step 14: Based on the operational fluctuation data provided by the power contractors, categorize the information types of the operational fluctuation data, such as bidding performance, personnel size, and annual revenue; generate corresponding risk indicators: stable operation, capacity warning, business decline, etc.

[0083] Step 15: Based on the corporate public opinion data provided by the power contractor, including business news, personnel changes, brand reputation, etc.; categorize the information types of the corporate public opinion data and generate corresponding risk indicators: brand exposure, proportion of negative public opinion, serious negative news, etc.

[0084] Step 16: Classify the changes in the qualifications of the power contractor companies into information types such as mandatory national qualifications, professional qualifications, business qualifications, quality certificates, and honorary qualifications; generate corresponding risk indicators such as expired or invalid mandatory qualifications, missing professional qualifications, and honorary evaluations.

[0085] Furthermore, such as Figure 3 As shown, step two involves a quantitative assessment of the power contractor's risk resistance capabilities, including the following process:

[0086] Step 21: Different power contractors have different risk resistance capabilities. To quantify the risk tolerance of power contractors, we collect indicators representing their risk resistance capabilities, such as registered capital, paid-in capital, number of employees, annual revenue, annual profit, debt ratio, intellectual property rights, corporate qualifications, and honors and awards, for comprehensive evaluation.

[0087] Step 22: Name the indicators of the contractor's risk resistance capability as I1', I'2, ..., I' n Weight parameters w1, w2, ..., w n The weighting of different indicators is used to calculate the overall risk resistance score R.

[0088] R = w1·I1' + w2·I'2 + ... + w n ·I' n ;

[0089] The overall risk resistance score R is quantified into 1-5 levels, with the higher the level, the stronger the risk resistance.

[0090] Furthermore, the overall risk resistance capability score R-level classification adopts a method based on sample distribution percentiles; the percentiles of the R-values ​​for all contractor samples are calculated, and the level mapping is performed according to the percentiles shown in the level mapping relationship, which is as follows:

[0091] Risk resistance level - description - percentile range of comprehensive score R

[0092] Weak - Micro and small enterprises, with very low risk tolerance - R <P 20 ;

[0093] General-sized and medium-sized enterprises with basic stability - P 20 ≤R <P 40 ;

[0094] Medium-sized regional or industry-specific important enterprises - P 40 ≤R <P 70 ;

[0095] Good - Large enterprise with strong capital and technology - P 70 ≤R <P 90 ;

[0096] Strong - Industry leaders or large group enterprises - R≥P 90 ;

[0097] The mapping relationship can be displayed in a mapping table as follows:

[0098]

[0099] Among them, P x This represents the value of the xth percentile in the dataset.

[0100] Please see Figure 4 As shown, a power contractor risk early warning device, wherein the power contractor risk early warning method described above includes:

[0101] The system comprises several modules: Judicial Risk Assessment, Enterprise Credit Risk Assessment, Enterprise Operational Risk Assessment, Enterprise Public Opinion Risk Assessment, Enterprise Qualification Risk Assessment, Enterprise Risk Resistance Assessment, and Enterprise Resilience Assessment. The Judicial Risk Assessment module categorizes judicial data information types and assesses corresponding risk indicators. The Enterprise Resilience Risk Assessment module categorizes public opinion information types and assesses corresponding risk indicators. The Enterprise Qualification Risk Assessment module categorizes qualification information types and assesses corresponding risk indicators. The Enterprise Risk Resistance Assessment module assesses the corresponding risk resistance rating based on the enterprise's risk resistance indicator values. Finally, the Enterprise Relative Risk Value Calculation and Risk Level Early Warning module calculates relative risk values ​​and provides risk level early warnings based on the enterprise's various risk indicator values ​​and risk resistance capabilities.

[0102] Furthermore, the enterprise risk resistance assessment module performs level mapping based on the percentiles shown in the level mapping relationship, which is as follows:

[0103] Risk resistance level - description - percentile range of comprehensive score R

[0104] Weak - Micro and small enterprises, with very low risk tolerance - R <P 20 ;

[0105] General-sized and medium-sized enterprises with basic stability - P 20 ≤R <P 40 ;

[0106] Medium-sized regional or industry-specific important enterprises - P 40 ≤R <P 70 ;

[0107] Good - Large enterprise with strong capital and technology - P 70 ≤R <P 90 ;

[0108] Strong - Industry leaders or large group enterprises - R≥P 90 ;

[0109] Among them, P x This represents the value of the xth percentile in the dataset.

[0110] Furthermore, the enterprise relative risk value calculation and risk level early warning module uniformly maps the original indicator values ​​of different dimensions to a risk score of 0-100 and calculates the normalized risk value.

[0111] A computer device includes a processor and a memory, the memory storing a computer program, wherein the processor executes the computer program to implement the steps of the aforementioned method.

[0112] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned method.

[0113] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for risk early warning of power contractors, characterized in that, Includes the following steps: Step 1: Generate a risk profile of the power contractor: Collect relevant risk activity information data of the power contractor during the observation period, process the risk activity information data into risk indicators according to preset risk rules and elements, form a structured risk assessment system, and constitute the risk profile of the power contractor. Step 2: Conduct a quantitative assessment of the power contractor's risk resistance capability, categorize the corresponding information types to generate relevant risk indicators, and obtain the power contractor's risk resistance capability level; wherein, the quantitative assessment of risk resistance capability includes the power contractor's business registration change information, judicial data, corporate credit data, operational fluctuation data, corporate public opinion data, and corporate qualification change data; Step 3: Based on the risk profile obtained in Step 1 and the risk resistance level obtained in Step 2, the relative risk value of the power contractor is calculated using a risk index normalization and relative risk value calculation model. The calculation process for the relative risk value of the power contractor is as follows: Risk indicator normalization: This involves mapping raw indicator values ​​of different dimensions to a risk score ranging from 0 to 100; for a specific indicator i, its risk score S... i The calculation is as follows: Among them, X i X represents the original observed value of this indicator. min and X max These are the industry's empirical minimum and maximum values ​​for this indicator; Construct a relative risk value calculation model: Calculate the normalized risk value V i : Among them, S i The indicator is the risk score, and R represents the risk resistance level. Step 4: Based on the relative risk value obtained in Step 3, and using pre-set thresholds as early warning conditions, issue risk warnings to power contractors that reach high-risk and medium-risk levels.

2. The method for risk early warning of power contractors as described in claim 1, characterized in that, The risk activity information data mentioned in Step 1 includes the power contractor's business registration changes, judicial data, corporate credit data, operational fluctuation data, public opinion data, and qualification change data.

3. The method for risk early warning of power contractors as described in claim 1, characterized in that, Step one involves processing the risk activity information data into risk indicators based on preset risk rules and elements, forming a structured risk assessment system, and creating a risk profile of the power contractor. This process includes the following steps: Step 11: Based on the business registration change information provided by the power contractor, classify the types of business registration changes and generate corresponding risk indicators: major business registration changes and general business registration changes; Risk indicators are generated based on the frequency of change: frequent changes, changes in the past 6 months; Step 12: Based on the judicial data of the power contract, classify the information types of the judicial data and generate corresponding risk indicators: serious violations, general violations, and too many economic disputes; Step 13: Based on the credit data of the power contractor, classify the information types of the credit data and generate corresponding risk indicators: the number of times the current registered dishonest persons are subject to enforcement and the total number of records of restrictions on high consumption; Step 14: Based on the operational fluctuation data provided by the power contractors, classify the information types of the operational fluctuation data and generate corresponding risk indicators: stable operation, capacity warning, and business decline; Step 15: Based on the corporate public opinion data provided by the power contractor, classify the information types of the corporate public opinion data and generate corresponding risk indicators: brand exposure, negative public opinion ratio, and serious negative news; Step 16: Classify the changes in the qualifications of the power contractor companies into information types and generate corresponding risk indicators: expired or invalid qualifications, missing professional qualifications, and honorary evaluations.

4. The method for risk early warning of power contractors as described in claim 1, characterized in that, Step two involves a quantitative assessment of the power contractor's risk resistance capabilities, including the following process: Step 21: Collect and comprehensively evaluate the risk resistance capabilities of power contractors by collecting indicators such as registered capital, paid-in capital, number of employees, annual revenue, annual profit, debt ratio, intellectual property rights, enterprise qualifications, and honors and awards. Step 22: Name the indicators of the contractor's risk resistance capability as I1', I'2, ..., I' n Weight parameters w1, w2, ..., w n The weighting of different indicators is used to calculate the overall risk resistance score R. R=w1·I1'+w2·I'2+...+w n ·I' n ; The overall risk resistance score R is quantified into 1-5 levels, with the higher the level, the stronger the risk resistance.

5. The method for risk early warning of power contractors as described in claim 4, characterized in that, The overall risk resistance capability score R-level classification adopts a method based on sample distribution percentiles; the percentiles of R-values ​​for all contractor samples are calculated, and the level mapping is performed according to the percentiles shown in the level mapping relationship, which is as follows: Risk resistance level - description - percentile range of comprehensive score R Weak - Micro and small enterprises, with very low risk tolerance - R <P 20 ; General-sized and medium-sized enterprises with basic stability - P 20 ≤R <P 40 ; Medium-sized regional or industry-specific important enterprises - P 40 ≤R <P 70 ; Good - Large enterprise with strong capital and technology - P 70 ≤R <P 90 ; Strong - Industry leaders or large group enterprises - R≥P 90 ; Among them, P x This represents the value of the xth percentile in the dataset.

6. A power contractor risk early warning device, the device performing the power contractor risk early warning method as described in any one of claims 1-7, characterized in that, include: The judicial risk assessment module is used to classify the information types of judicial data and assess the corresponding risk indicators. The enterprise credit risk assessment module is used to classify the information types of its credit data and assess the corresponding risk indicators. The business risk assessment module is used to categorize the information types of its business data and assess the corresponding risk indicators. The corporate public opinion risk assessment module is used to classify the types of public opinion information and assess the corresponding risk indicators. The Enterprise Qualification Risk Assessment Module is used to categorize the types of information related to its qualifications and assess the corresponding risk indicators. The enterprise risk resistance assessment module evaluates the corresponding risk resistance rating based on the enterprise's risk resistance index values. The enterprise relative risk value calculation and risk level early warning module calculates the relative risk value and provides early warnings of the risk level based on the enterprise's various risk indicators and risk resistance capabilities.

7. The power contractor risk early warning device as described in claim 6, characterized in that, The enterprise risk resistance assessment module performs level mapping based on percentiles shown in the level mapping relationship, which is as follows: Risk resistance level - description - percentile range of comprehensive score R Weak - Micro and small enterprises, with very low risk tolerance - R <P 20 ; General-sized and medium-sized enterprises with basic stability - P 20 ≤R <P 40 ; Medium-sized regional or industry-specific important enterprises - P 40 ≤R <P 70 ; Good - Large enterprise with strong capital and technology - P 70 ≤R <P 90 ; Strong - Industry leaders or large group enterprises - R≥P 90 ; Among them, P x This represents the value of the xth percentile in the dataset.

8. The power contractor risk early warning device as described in claim 6, characterized in that, The enterprise relative risk value calculation and risk level early warning module maps the original indicator values ​​of different dimensions to a risk score of 0-100 and calculates the normalized risk value.

9. A computer device comprising a processor and a memory, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of any one of the methods described in 1 to 5 above.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of any one of the methods described in 1 to 5 above.

Images