Method for monitoring credit risk of supplier by fusing bidding and tendering data and industry and commerce data

By collecting and integrating data from multiple data sources, building a credit risk assessment model and monitoring system, the problems of dispersion and isolation of supplier breach of trust are solved, and comprehensive and accurate assessment and real-time monitoring of supplier credit risks are achieved. Improved assessment efficiency and risk management level.

CN118941304APending Publication Date: 2024-11-12DADU RIVER HYDROPOWER DEV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410935289.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In supply chain management, the dispersion and isolation of supplier's breach of trust lead to data silos, information asymmetry, untimely updates, lack of comprehensive analysis and inefficiency, making it difficult to conduct accurate credit risk assessments.

Method used

By regularly collecting data from the entire network bidding platform, internal enterprise blacklists and industrial and commercial judicial data sources, pre-processing and integration, building a credit risk assessment and scoring model, and establishing a supplier's credit risk monitoring system to monitor and provide early warning in real time.

Benefits of technology

It realizes comprehensive and accurate assessment and real-time monitoring of supplier credit risks, improves assessment efficiency and objectivity, reduces risk management costs, and ensures timely measures.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941304A_ABST
    Figure CN118941304A_ABST
Patent Text Reader

Abstract

The invention discloses a method for monitoring the credit risk of a supplier by fusing bidding and tendering data and industry and commerce data, and relates to the technical field of credit risks, and the method comprises the following steps: S1, data collection; s2, data preprocessing; s3, data storage; s4, data integration; s5, constructing a credit risk assessment scoring model; s6, establishing a supplier credit risk monitoring system: realizing the supplier credit risk monitoring system, monitoring the credit risk condition of the supplier in real time, and providing early warning at the initial stage of risk occurrence; according to the technical scheme provided by the invention, the method can quickly and accurately obtain and update the dishonesty information of the supplier, constructs a comprehensive supplier credit risk database, covers various possible risk factors, monitors the credit risk condition of the supplier in real time, can provide early warning at the initial stage of risk occurrence, and improves the safety of the supplier. The enterprise is helped to better monitor and manage the supplier credit risk, and a beneficial technical reference can be provided for the whole industry.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of credit risk technology, and in particular to a method for integrating bidding and tendering with industrial and commercial data to monitor supplier credit risks. Background Art

[0002] When enterprises conduct supplier credit risk assessment in supply chain management, a key problem they face is the dispersion and isolation of supplier default data. Specific problems include the following:

[0003] Data island problem: Supplier default data is usually scattered across different platforms and systems, such as the public default enterprise information on the online bidding platform, internal corporate blacklist data, industrial and commercial judicial data, etc. There is a lack of effective connection and integration between these data sources.

[0004] Information asymmetry: Due to the dispersion of supplier default information, it is difficult for companies to obtain comprehensive credit records when evaluating suppliers, which may lead to biased evaluation results.

[0005] Untimely updates: The credit status of suppliers changes dynamically, but it is often difficult for companies to obtain the latest default information in real time, making it impossible for credit assessments to reflect the current situation in a timely manner.

[0006] Lack of comprehensive analysis: A single data source cannot provide a comprehensive credit risk assessment. It is necessary to conduct a comprehensive analysis of data from different sources to form a more accurate risk judgment.

[0007] Inefficiency: Due to data isolation, companies need to invest a lot of manpower and time in collecting and processing supplier credit information, which is inefficient. Summary of the invention

[0008] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide a method for integrating bidding and tendering with industrial and commercial data to monitor the credit risk of suppliers, so as to solve the problems in the prior art.

[0009] In view of this, the present invention provides a method for integrating bidding and industrial and commercial data to monitor supplier credit risk, comprising the following steps:

[0010] S1. Data collection: First, regularly collect relevant data from the bidding platform of the entire network, the internal blacklist of enterprises, and the data source of industrial and commercial judicial data of enterprises;

[0011] S2. Data preprocessing: After obtaining the original data, clean and organize the data to remove invalid data, duplicate data and inconsistent data;

[0012] S3, data storage: store the preprocessed data into a suitable database;

[0013] S4. Data integration: Integrate data from various data sources to form a complete supplier credit risk database;

[0014] S5. Construct a credit risk assessment and scoring model: process the data of bidding and tendering dishonesty records, tax violation records, dishonesty execution records, internal blacklist records, and industrial and commercial judicial records, and then train the data to construct a credit risk assessment and scoring model;

[0015] S6. Establish a supplier credit risk monitoring system: Implement a supplier credit risk monitoring system to monitor the supplier's credit risk status in real time and provide early warnings at the early stage of risk occurrence.

[0016] Optionally, the information collected in S1 includes enterprise bidding information, dishonest enterprise information, blacklist data and industrial and commercial judicial data.

[0017] Optionally, the data collection in S1 includes determining the data source, writing a crawler program or using an API interface, data parsing and formatting, data cleaning and deduplication, data storage, and data association.

[0018] Optionally, the data preprocessing in S2 includes data integration, data cleaning, data conversion, data classification, and data association in sequence.

[0019] Optionally, the database in S3 is a relational database, a NoSQL database or a time series database.

[0020] Optionally, the data integration in S4 involves data merging, deduplication, and association.

[0021] Optionally, constructing the credit risk assessment scoring model in S5 includes data preparation, feature engineering, model training, model evaluation, and model tuning in sequence.

[0022] Optionally, the supplier credit risk monitoring system in S6 includes functions of data visualization, risk assessment, and early warning.

[0023] Optionally, establishing the supplier credit risk monitoring system in S6 sequentially includes system architecture design, data layer design, model layer design, interface layer design, testing and debugging, and online deployment.

[0024] Optionally, establishing the supplier credit risk monitoring system in S6 also includes tuning of the supplier credit risk assessment model, and the tuning of the supplier credit risk assessment model includes data enhancement, hyperparameter adjustment, model fusion, model fine-tuning, and model interpretation in sequence.

[0025] It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

[0026] The present invention provides a method for integrating bidding and industrial and commercial data to monitor supplier credit risk. By realizing the collection, processing and analysis of the information of dishonest enterprises disclosed on the bidding platform of the entire network, the internal blacklist data of enterprises, and the industrial and commercial judicial data, a supplier credit risk database is constructed in combination with these data to provide enterprises with a more comprehensive and accurate supplier credit risk assessment. At the same time, by designing and implementing a supplier credit risk monitoring system, it helps enterprises to monitor the credit risk status of suppliers in real time and provide early warnings to help enterprises take corresponding measures in a timely manner. It is ensured that the method can quickly and accurately obtain and update supplier dishonesty information, construct a comprehensive supplier credit risk database, cover various possible risk factors, monitor the credit risk status of suppliers in real time, provide early warnings at the early stage of risk occurrence, help enterprises better monitor and manage supplier credit risks, and provide a useful technical reference for the entire industry.

[0027] These features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0029] Figure 1 The present invention is a flow chart of a method for integrating bidding and industrial and commercial data to monitor supplier credit risk. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0032] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features limited to "first" and "second" may explicitly or implicitly include at least one of the features. In addition, if "and / or" or "and / or" appears in the full text, its meaning includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0033] A method for monitoring supplier credit risk by integrating bidding and tendering data with industrial and commercial data according to an embodiment of the present invention will be described in detail below with reference to the accompanying drawings.

[0034] Example

[0035] For easier understanding, see Figure 1 , an embodiment of a method for integrating bidding and industrial and commercial data to monitor supplier credit risk provided by the present invention includes the following steps:

[0036] S1. Data collection: First, regularly collect relevant data from the bidding platform of the entire network, the internal blacklist of enterprises, and the data source of industrial and commercial judicial data of enterprises;

[0037] Among them, data collection includes determining the data source, writing crawler programs or using API interfaces, data parsing and formatting, data cleaning and deduplication, data storage, and data association.

[0038] Determine the data source: including multiple data sources such as the entire network bidding platform, internal corporate blacklists, and corporate industrial and commercial judicial systems.

[0039] Write a crawler program or use an API interface: Write a corresponding crawler program or use an API interface to obtain data based on the data source. Use programming languages ​​such as Python, Java, Ruby, and toolkits such as Scrapy, Curl, and AspNet to crawl data.

[0040] Data parsing and formatting: Parse and format the acquired raw data according to the data format requirements. For example, if the data source is in JSON format, it needs to be converted into a Python object: If it is a CSV file, you can use libraries such as pandas to read and process it.

[0041] Data cleaning and deduplication: Clean and dedupe the acquired data, and delete invalid data such as duplicates, null values, and error values. Use Python's built-in data types such as collections and lists, as well as libraries such as pandas to clean and dedupe the data.

[0042] Data storage: Store the cleaned and formatted data in a database. Choose a relational database (such as MySQL, PostgreSQL), a NoSQL database (such as MongoDB, Redis), or a time series database (such as Prometheus, Grafana), etc.

[0043] Data association: Associating data from different data sources, such as matching and connecting through key fields such as ID and name.

[0044] S2. Data preprocessing: After obtaining the original data, clean and organize the data to remove invalid data, duplicate data and inconsistent data;

[0045] Among them, data preprocessing includes data integration, data cleaning, data conversion, data classification, and data association.

[0046] Data integration: Merge and integrate data from different data sources to form a complete supplier credit risk database.

[0047] Data cleaning: Clean and transform the data, such as dealing with missing values, outliers, inconsistent date formats, etc.

[0048] Data conversion: converting data into a unified format and standard, such as converting text format into digital format, unifying units, etc.

[0049] Data classification: Classify and group data according to business needs, such as by region, industry, time period, etc.

[0050] Data association: Associating data from different data sources, such as matching and connecting through key fields such as ID and name.

[0051] S3, data storage: store the preprocessed data into a suitable database;

[0052] S4. Data integration: Integrate data from various data sources to form a complete supplier credit risk database;

[0053] S5. Construct a credit risk assessment and scoring model: process the data of bidding and tendering dishonesty records, tax violation records, dishonesty execution records, internal blacklist records, and industrial and commercial judicial records, and then train the data to construct a credit risk assessment and scoring model;

[0054] Among them, building a credit risk assessment scoring model includes data preparation, feature engineering, model training, model evaluation, and model tuning.

[0055] Data preparation: Preprocess the data to generate feature matrix and label matrix. The feature matrix contains input features, and the label matrix contains true labels.

[0056] Feature engineering: Perform feature selection, dimensionality reduction, encoding and other processing on the feature matrix to improve the performance of the model.

[0057] Model training: Train the model using machine learning algorithms such as logistic regression, decision trees, random forests, etc.

[0058] Model evaluation: Use cross-validation, grid search, etc. to evaluate the performance and generalization ability of the model.

[0059] Model tuning: Tune the model based on the evaluation results to improve prediction accuracy.

[0060] S6. Establish a supplier credit risk monitoring system: Implement a supplier credit risk monitoring system to monitor the supplier's credit risk status in real time and provide early warnings at the early stage of risk occurrence.

[0061] Establishing a supplier credit risk monitoring system includes system architecture design, data layer design, model layer design, interface layer design, testing and debugging, and online deployment.

[0062] System architecture design: Design the overall architecture of the system and determine the functions and responsibilities of each component.

[0063] Data layer design: Design data storage structure and query methods based on business needs and data characteristics.

[0064] Model layer design: Design model structure and parameters based on business requirements and data characteristics.

[0065] Interface layer design: Design the user interface and interaction process to ensure that users can use the system conveniently.

[0066] Testing and debugging: Perform unit testing, integration testing, end-to-end testing, etc. on the system to ensure system quality.

[0067] Online deployment: Deploy the system to the production environment and conduct continuous monitoring and optimization.

[0068] The implementation of the supplier credit risk monitoring system includes the following steps:

[0069] System architecture implementation: Choose to use programming languages ​​such as Python and Django, combined with web frameworks such as Flask or DjangoREST framework to implement API interfaces, and use technologies such as TensorFlow and XGBoost to build machine learning models. At the same time, you need to design the system architecture, such as using a microservice architecture to divide the system's functions into different services, such as data collection, data processing, model training, report generation, etc.

[0070] Data source access: Implement data source access, including the bidding platform of the entire network, internal blacklist of enterprises, and corporate industrial and commercial judicial data. Use Python's requests library to request data, or use some third-party libraries such as fetcher or scraper to crawl data.

[0071] Data preprocessing: Implement the data preprocessing module, including data collection, data cleaning, data conversion and other functions. Use Pandas' data reading and processing functions to read and process data, or use Scikit-learn's machine learning algorithms to perform data conversion and feature extraction.

[0072] Data storage: Implement the data storage module, including the design, storage and management of data tables, and use relational databases such as MySQL and PostgreSQL to store data. At the same time, consider issues such as data indexing and query optimization to ensure system performance and efficiency.

[0073] Model serving: Implement the model serving module, including functions such as model loading and reasoning, and use machine learning frameworks such as TensorFlow and XGBoost to build and train models.

[0074] Data report: implement the data report module, including data visualization, data analysis and other functions.

[0075] Model management: Implement the model management module, including model training, tuning, deployment and other functions.

[0076] User management: Implement the user management module, including user registration, login, permission control and other functions.

[0077] System integration: Realize system integration, including front-end and back-end integration, security integration and other functions.

[0078] Among them, establishing a supplier credit risk monitoring system also includes tuning the supplier credit risk assessment model, and the tuning of the supplier credit risk assessment model includes data enhancement, hyperparameter adjustment, model fusion, model fine-tuning, and model interpretation in sequence.

[0079] Data enhancement: Improve the performance of the model by enhancing the data, such as data synthesis, image thickening, audio voice changing, etc.

[0080] Hyperparameter adjustment: Improve the performance of the model by adjusting hyperparameters such as learning rate, number of iterations, network depth, etc.

[0081] Model fusion: Improve the performance of the model by fusing multiple models, such as voting, stacking, bagging, etc.

[0082] Model fine-tuning: After the model is deployed, the performance of the model can be improved by fine-tuning the model, such as adding regularization terms, dropout, L1 regularization, etc.

[0083] Model explanation: Explain the decision-making process of the model through visualization, interpretable analysis and other methods.

[0084] In summary, through the implementation of the project, we expect to achieve the following results:

[0085] ① Improve the company's risk management level: By monitoring the supplier's dishonest behavior, timely identify potential risks and take corresponding measures to reduce the company's risks.

[0086] ② Provide strong data support: By building a comprehensive supplier credit risk database, we provide enterprises with rich data resources to support decision-making.

[0087] ③ Improve the efficiency and objectivity of risk assessment: By using advanced credit risk assessment models, the assessment efficiency can be improved while ensuring the objectivity and fairness of the assessment results.

[0088] ④ Improve the real-time and practicality of the system: Through the design and implementation of the supplier credit risk monitoring system, the credit risk status of suppliers can be monitored in real time, and early warnings can be provided to help enterprises take timely response measures.

[0089] ⑤ Enhance user satisfaction: By providing high-quality products and services, collecting and valuing user feedback and suggestions, and continuously improving user satisfaction and loyalty.

[0090] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring supplier credit risk by integrating bidding and industrial and commercial data, characterized in that: The following steps are involved: S1. Data collection: First, regularly collect relevant data from the bidding platform of the entire network, the internal blacklist of enterprises, and the data source of industrial and commercial judicial data of enterprises; S2. Data preprocessing: After obtaining the original data, clean and organize the data to remove invalid data, duplicate data and inconsistent data; S3, data storage: store the preprocessed data into a suitable database; S4. Data integration: Integrate data from various data sources to form a complete supplier credit risk database; S5. Construct a credit risk assessment and scoring model: process the data of bidding and tendering dishonesty records, tax violation records, dishonesty execution records, internal blacklist records, and industrial and commercial judicial records, and then train the data to construct a credit risk assessment and scoring model; S6. Establish a supplier credit risk monitoring system: Implement a supplier credit risk monitoring system to monitor the supplier's credit risk status in real time and provide early warnings at the early stage of risk occurrence.

2. According to claim 1, a method for monitoring supplier credit risk by integrating bidding and industrial and commercial data is characterized in that: The information collected in S1 includes enterprise bidding information, dishonest enterprise information, blacklist data and industrial and commercial judicial data.

3. According to claim 1, a method for monitoring supplier credit risk by integrating bidding and industrial and commercial data is characterized in that: The data collection in S1 includes determining the data source, writing a crawler program or using an API interface, data parsing and formatting, data cleaning and deduplication, data storage, and data association.

4. According to claim 1, a method for monitoring supplier credit risk by integrating bidding and industrial and commercial data is characterized in that: The data preprocessing in S2 includes data integration, data cleaning, data conversion, data classification, and data association in sequence.

5. According to claim 1, a method for monitoring supplier credit risk by integrating bidding and industrial and commercial data is characterized in that: The database in S3 is a relational database, a NoSQL database or a time series database.

6. According to claim 1, a method for monitoring supplier credit risk by integrating bidding and industrial and commercial data is characterized in that: The data integration in S4 involves data merging, deduplication, and association.

7. According to claim 1, a method for monitoring supplier credit risk by integrating bidding and industrial and commercial data is characterized in that: The construction of the credit risk assessment scoring model in S5 includes data preparation, feature engineering, model training, model evaluation, and model tuning in sequence.

8. According to claim 1, a method for monitoring supplier credit risk by integrating bidding and industrial and commercial data is characterized in that: The supplier credit risk monitoring system in S6 includes functions of data visualization, risk assessment and early warning.

9. The method of monitoring supplier credit risk by integrating bidding and industrial and commercial data according to claim 1 is characterized in that: The establishment of the supplier credit risk monitoring system in S6 includes system architecture design, data layer design, model layer design, interface layer design, testing and debugging, and online deployment.

10. The method of monitoring supplier credit risk by integrating bidding and industrial and commercial data according to claim 1, characterized in that: The establishment of the supplier credit risk monitoring system in S6 also includes tuning of the supplier credit risk assessment model, and the tuning of the supplier credit risk assessment model includes data enhancement, hyperparameter adjustment, model fusion, model fine-tuning, and model interpretation in sequence.