Block chain-based foreign enterprise portrait honesty-containing evaluation method and system, and storage medium

Abstract

The invention relates to a block chain-based foreign enterprise portrait integrity-containing evaluation method and system, and a storage medium. The method comprises the following steps of collecting cooperation record data of a Chinese marine operation unit and a foreign enterprise; key features related to enterprise integrity are extracted from the collected cooperation record data to form a data set; training a random forest model by using the data set to obtain an integrity evaluation model; and according to the collected cooperation record data and the evaluation result of the integrity evaluation model, generating and displaying a comprehensive portrait of the foreign enterprise. According to the method, the comprehensive and credible enterprise portrait platform is constructed by integrating the combined record data of the Chinese marine operation units and the foreign enterprises, so that the Chinese marine operation units can conveniently know the detailed information of the foreign enterprises in advance, more scientific and reasonable selection decisions can be made, and the overseas operation risk can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of blockchain, and particularly to a method, system and storage medium for overseas enterprise portraits including integrity evaluation based on blockchain. Background Art

[0002] With the increasing scale of Chinese enterprises' overseas operations, especially in fields such as construction projects, many large state-owned enterprises and central enterprises face numerous challenges when undertaking projects abroad. Due to factors such as foreign policies, tariffs, and trade protection, when selecting subcontractors (such as for engineering construction) and suppliers (such as for material supply) locally, due to the lack of background data query platforms similar to Qichacha and Tianyancha in China and unfamiliarity with the local situation, they can only make passive selections. This has led to problems such as insufficient experience or lack of strength among some subcontractors and suppliers, resulting in obstacles to project progress and bringing many risks and losses to Chinese overseas enterprises. Therefore, there is an urgent need to provide a new solution to solve the above problems. Summary of the Invention

[0003] The purpose of the present invention is to overcome the defects of the prior art and provide a method, system and storage medium for overseas enterprise portraits including integrity evaluation based on blockchain, so as to solve the problems in the prior art such as the inability to query the enterprise integrity of overseas subcontractors and suppliers, resulting in obstacles to project progress and bringing many risks and losses to overseas enterprises.

[0004] The technical solution for achieving the above purpose is as follows:

[0005] The present invention provides a method for overseas enterprise portraits including integrity evaluation based on blockchain, comprising the following steps:

[0006] Collect cooperation record data of Chinese overseas operating units and foreign enterprises;

[0007] Extract key features related to enterprise integrity from the collected cooperation record data to form a data set;

[0008] Use the data set to train a random forest model to obtain an integrity evaluation model;

[0009] Generate and display a comprehensive portrait of foreign enterprises based on the collected cooperation record data and the evaluation results of the integrity evaluation model.

[0010] A further improvement of the method for overseas enterprise portraits including integrity evaluation based on blockchain of the present invention is that the key features related to enterprise integrity extracted from the collected cooperation record data include the proportion feature of payment delay days, the deviation rate feature of the average project completion cycle, and the proportion feature of the number of contract defaults.

[0011] A further improvement of the method for depicting foreign enterprises including credit evaluation based on blockchain of the present invention lies in that when training the random forest model using the data set, the data set is divided into a training set and a test set according to a certain ratio;

[0012] The training set is used to train the random forest model to obtain a credit evaluation model;

[0013] The test set is used to test the obtained credit evaluation model.

[0014] A further improvement of the method for depicting foreign enterprises including credit evaluation based on blockchain of the present invention lies in that it further includes: regularly performing incremental training on the credit evaluation model using newly collected data.

[0015] A further improvement of the method for depicting foreign enterprises including credit evaluation based on blockchain of the present invention lies in that it further includes: using the encryption technology of blockchain to encrypt the collected cooperation record data.

[0016] The present invention also provides a storage medium, on which a program of the method for depicting foreign enterprises including credit evaluation based on blockchain is stored,

[0017] When the program of the method for depicting foreign enterprises including credit evaluation based on blockchain is executed by a processor, the steps of the method for depicting foreign enterprises including credit evaluation based on blockchain are implemented.

[0018] The present invention further provides a system for depicting foreign enterprises including credit evaluation based on blockchain, including:

[0019] A data acquisition unit, configured to acquire cooperation record data of Chinese overseas business entities and foreign enterprises;

[0020] A feature extraction unit, connected to the data acquisition unit, configured to extract key features related to enterprise credit from the acquired cooperation record data to form a data set;

[0021] A model construction unit, connected to the feature extraction unit, configured to train the random forest model using the data set to obtain a credit evaluation model;

[0022] An enterprise portrait generation unit, connected to the data acquisition unit and the model construction unit, configured to generate a comprehensive portrait of a foreign enterprise based on the acquired cooperation record data and the evaluation result of the credit evaluation model and display it.

[0023] A further improvement of the system for depicting foreign enterprises including credit evaluation based on blockchain of the present invention lies in that the key features extracted by the feature extraction unit include the ratio feature of payment delay days, the deviation rate feature of the average project completion cycle, and the ratio feature of the number of contract defaults.

[0024] A further improvement of the system for overseas enterprise portraits with integrity evaluation based on blockchain of the present invention lies in that the model construction unit is further configured to divide the data set into a training set and a test set according to a certain ratio;

[0025] Furthermore, the training set is used to train the random forest model to obtain an integrity evaluation model;

[0026] The obtained integrity evaluation model is tested using the test set.

[0027] A further improvement of the system for overseas enterprise portraits with integrity evaluation based on blockchain of the present invention lies in that the model construction unit is further configured to locate and perform incremental training on the integrity evaluation model using newly collected data.

[0028] The beneficial effects of the method, system and storage medium for overseas enterprise portraits with integrity evaluation based on blockchain of the present invention are as follows:

[0029] By integrating the cooperation record data of Chinese overseas business entities and overseas enterprises, the present invention constructs a comprehensive and trustworthy enterprise portrait platform, which facilitates Chinese overseas entities to understand the detailed information of overseas enterprises in advance, so as to make more scientific and reasonable selection decisions and reduce overseas business risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a system diagram of the system for overseas enterprise portraits with integrity evaluation based on blockchain of the present invention.

[0031] Figure 2 It is a flowchart of the method for overseas enterprise portraits with integrity evaluation based on blockchain of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0033] Refer to Figure 1 , the present invention provides a method, system and storage medium for overseas enterprise portraits with integrity evaluation based on blockchain. By integrating the cooperation data of Chinese overseas business entities and overseas subcontractors and suppliers (i.e., overseas enterprises), including cooperation records, payment records, credit evaluations, etc., a comprehensive and trustworthy enterprise portrait platform is constructed, which facilitates Chinese overseas entities to understand the detailed information of subcontractors and suppliers in advance, so as to make more scientific and reasonable selection decisions and reduce overseas business risks. The method, system and storage medium for overseas enterprise portraits with integrity evaluation based on blockchain of the present invention will be described below with reference to the accompanying drawings.

[0034] Refer to Figure 1, shows the system diagram of the system of the present invention for the portrait of foreign enterprises including integrity evaluation based on blockchain. The following combines Figure 1 , to explain the system of the present invention for the portrait of foreign enterprises including integrity evaluation based on blockchain.

[0035] As Figure 1 shown, the system of the present invention for the portrait of foreign enterprises including integrity evaluation based on blockchain includes a data collection unit 21, a feature extraction unit 22, a model construction unit 23, and an enterprise portrait generation unit 24, wherein the data collection unit 21 is connected to the feature extraction unit 22, the feature extraction unit 22 is connected to the model construction unit 23, and the enterprise portrait generation unit 24 is connected to the data collection unit 21 and the model construction unit 23. The data collection unit 21 is used to collect the cooperation record data of Chinese overseas business entities and foreign enterprises; the feature extraction unit 22 is used to extract key features related to enterprise integrity from the collected cooperation record data to form a data set; the model construction unit 23 is used to train a random forest model with the data set to obtain an integrity evaluation model; the enterprise portrait generation unit 24 is used to generate and display a comprehensive portrait of foreign enterprises according to the collected cooperation record data and the evaluation results of the integrity evaluation model.

[0036] In a specific embodiment of the present invention, the data collection unit 21 of the system of the present invention is docked with the business system of Chinese overseas business entities, and the data collection unit 21 collects the basic data in the business system of Chinese overseas business entities, including the cooperation records, payment details, engineering quality feedback, etc. of Chinese overseas business entities and foreign subcontractors and suppliers (i.e., foreign enterprises). Specifically, communication and cooperation agreements can be signed with Chinese overseas business entities to determine the scope, frequency, and format requirements of data collection, and corresponding industry agreement contracts can also be used to collect the cooperation record data of Chinese overseas business entities. Preferably, a special data collection interface and adaptation program can be developed to dock with the business system of Chinese overseas business entities to collect data such as cooperation record data and payment records.

[0037] Furthermore, the data collection unit 21 is also used to obtain enterprise basic information data through a specific data interface, and the enterprise basic information data includes enterprise registration information, business scope, etc., and the enterprise registration information includes information such as enterprise name, address, and registered capital. Preferably, the data collection unit 21 uses web crawler technology to obtain the basic information of foreign enterprises from public business databases, government enterprise registration information databases, etc.

[0038] In a specific embodiment of the present invention, the system of the present invention further includes a data encryption unit, which is connected to the data acquisition unit 21 and is used to encrypt the collected data by using the encryption technology of the blockchain to ensure the security and immutability of the data. After encrypting the data, the data encryption unit uploads the encrypted data to each node in the blockchain network for storage.

[0039] Further, the system of the present invention builds a blockchain network based on a consortium blockchain, and invites Chinese overseas business operation units, relevant industry associations, etc. to join the network as nodes. Configure the hardware and software environment of the blockchain nodes, including installing the blockchain underlying platform software, setting the encryption algorithm and key management mechanism, etc. Encrypt the collected data according to the data format requirements of the blockchain, and then upload the data to the blockchain network through the consensus mechanism of the nodes to ensure that each node stores the same and immutable data copy.

[0040] In a specific embodiment of the present invention, the system of the present invention further includes a data preprocessing unit, which is connected to the data acquisition unit 21 and is used to clean multi-dimensional data such as cooperation records, payment timeliness, and project quality feedback collected, and remove noise data, outliers, and duplicate data, etc. For example, correct or delete incorrect payment amounts or records that obviously do not conform to business logic in the payment records.

[0041] Further, the key features extracted by the feature extraction unit include the proportion feature of the number of days of payment delay, the deviation rate feature of the average project completion cycle, and the proportion feature of the number of contract defaults.

[0042] Among them, the proportion feature of the number of days of payment delay = the total number of days of delayed payment / the total number of days of payable, the deviation rate feature of the average project completion cycle = (the actual project completion cycle - the planned project completion cycle) / the average value of the planned project completion cycle, and the proportion feature of the number of contract defaults = the number of default contracts / the total number of contracts.

[0043] Furthermore, the model construction unit constructs an integrity evaluation model by using the random forest algorithm. The model construction unit is also used to divide the data set into a training set and a test set according to a certain proportion; for example, 70% is the training set and 30% is the test set.

[0044] Then use the training set to train the random forest model to obtain the integrity evaluation model;

[0045] Use the test set to test the obtained integrity evaluation model.

[0046] The number of decision trees in the random forest can be determined according to the scale of the dataset and the number of features, and is generally set to 100 - 500. During the training process, the model performance is optimized by adjusting parameters such as the depth of the tree and the number of features considered when splitting nodes. For example, the depth of the tree can be adjusted between 3 and 10, and the number of features considered when splitting nodes can be set to the square root of the total number of features. The trained model is evaluated using a test set, and metrics such as accuracy, recall, and F1-score are used to measure the model's performance. If the model performance does not meet the expectations, the parameters are adjusted and retrained until the model performance meets the requirements. For example, starting from the initial settings of a tree depth of 5 and a split feature number of the square root of the total number of features, different combinations are gradually tried until the evaluation metrics of the model on the test set reach a better level.

[0047] Furthermore, the model construction unit is also used to locate and incrementally train the integrity evaluation model using newly collected data to achieve model update.

[0048] As new data continuously flows in, the model is incrementally trained with new data regularly (such as monthly or quarterly) to ensure that the model can adapt to the dynamic changes of the enterprise's business.

[0049] In a specific embodiment of the present invention, the foreign enterprise portrait generation unit 24 integrates and generates a comprehensive portrait of foreign enterprises based on the data collection results and integrity evaluation results, including various aspects such as enterprise basic information, business capabilities, and integrity levels, and displays it to Chinese overseas units through a visual interface. For example, the integrity level can be divided into five levels: excellent (90 - 100 points), good (75 - 89 points), medium (60 - 74 points), poor (45 - 59 points), and very poor (0 - 44 points) according to the integrity score.

[0050] The foreign enterprise portrait generation unit 24 is used to integrate various types of data to generate the final portrait of foreign enterprises and convert it into a format suitable for display and interaction. Specifically, the front-end interface of the development platform is used to intuitively and friendly display the enterprise portrait information to Chinese overseas unit users.

[0051] In a specific embodiment of the present invention, the system of the present invention further includes an interaction and sharing unit, which is used to implement the data sharing and interaction functions and process data requests and permission verifications between different users.

[0052] In a blockchain network, it is allowed to share part of the data among different Chinese companies going global (under the compliance with privacy and permission rules), which promotes information exchange and cooperation experience sharing among enterprises. At the same time, it also facilitates new enterprises entering overseas markets to quickly obtain valuable information. Data sharing and permission management are achieved by designing blockchain-based smart contracts. For example, when an overseas-going unit requests to view the subcontractor data shared by another unit, the smart contract will verify the identity and permission of the requester. Only when specific conditions are met (such as the two parties having a cooperation relationship or belonging to the same industry association), data access is allowed, and the access log is recorded.

[0053] The system of the present invention establishes user management, permission management, and data sharing management mechanisms for the platform to ensure the secure and stable operation of the platform and the legal and compliant use of data. During the operation of the platform, user feedback is continuously collected, and the platform is upgraded and optimized according to new data and business requirements.

[0054] The system of the present invention can run on high-performance computing devices such as server clusters, including hardware components such as processors, memories, and network interfaces. The processor is used to execute various data processing and logical operation tasks in the platform building method; the memory is used to store data, program codes, and blockchain-related data structures; the network interface is used to achieve communication connections with external systems and other nodes to ensure data transmission and interaction.

[0055] The present invention also provides a method for depicting foreign enterprises based on blockchain including integrity evaluation. The method will be described below.

[0056] As Figure 2 shown, the method of the present invention includes the following steps:

[0057] Execute step S11 to collect cooperation record data of Chinese overseas business units and foreign enterprises; then execute step S12;

[0058] Execute step S12 to extract key features related to enterprise integrity from the collected cooperation record data to form a data set; then execute step S13;

[0059] Execute step S13 to train a random forest model using the data set to obtain an integrity evaluation model; then execute step S14;

[0060] Execute step S14 to generate a comprehensive portrait of foreign enterprises based on the collected cooperation record data and the evaluation results of the integrity evaluation model and display it.

[0061] Furthermore, in the data collection step, the sources of the collected data also include obtaining basic information of foreign enterprises from public commercial databases and government enterprise registration information databases through web crawler technology.

[0062] In a specific embodiment of the present invention, the key features related to enterprise integrity extracted from the collected cooperation record data include the proportion feature of the number of days of payment delay, the deviation rate feature of the average project completion cycle, and the proportion feature of the number of contract defaults.

[0063] Among them, the proportion feature of the number of days of payment delay = the total number of days of late payment / the total number of days of payable; the deviation rate feature of the average project completion cycle = (the actual project completion cycle - the planned project completion cycle) / the average value of the planned project completion cycle; the proportion feature of the number of contract defaults = the number of default contracts / the total number of contracts.

[0064] Before extracting the key features related to enterprise integrity, it also includes cleaning multi-dimensional data such as the collected cooperation records, payment timeliness, and project quality feedback, removing noise data, outliers, and duplicate data, etc. For example, correcting or deleting incorrect payment amounts or records that obviously do not conform to business logic in the payment records.

[0065] In a specific embodiment of the present invention, when training a random forest model using a data set, the data set is divided into a training set and a test set according to a certain proportion;

[0066] Using the training set to train the random forest model to obtain an integrity evaluation model;

[0067] Using the test set to test the obtained integrity evaluation model.

[0068] Specifically, a random forest algorithm is used to construct an integrity evaluation model. The processed data set is divided into a training set and a test set according to a certain proportion, for example, 70% is the training set and 30% is the test set. Using the training set to train the random forest model, where the number of decision trees in the random forest can be determined according to the scale of the data set and the number of features, and is generally set to 100 - 500 trees. During the training process, the model performance is optimized by adjusting parameters such as the depth of the tree and the number of features considered when splitting nodes. For example, the depth of the tree can be adjusted between 3 - 10, and the number of features considered when splitting nodes can be set to the square root of the total number of features. Using the test set to evaluate the trained model, and using indicators such as accuracy, recall rate, and F1 value to measure the model effect. If the model effect does not meet the expectations, adjust the parameters and retrain until the model performance meets the requirements.

[0069] Furthermore, it also includes: regularly using newly collected data to perform incremental training on the integrity evaluation model.

[0070] As new data continuously flows in, regularly (such as monthly or quarterly) using the new data to perform incremental training on the model to ensure that the model can adapt to the dynamic changes of enterprise business.

[0071] In a specific embodiment of the present invention, it further includes: encrypting the collected cooperation record data by using the encryption technology of the blockchain.

[0072] The present invention also provides a storage medium, on which a program of the method for depicting foreign enterprises including integrity evaluation based on the blockchain is stored.

[0073] The steps of the method for depicting foreign enterprises including integrity evaluation based on the blockchain, which are implemented when the program of the method for depicting foreign enterprises including integrity evaluation based on the blockchain is executed by a processor.

[0074] The present invention has been described in detail above in combination with the embodiments with the accompanying drawings. Those of ordinary skill in the art can make various variations of the present invention according to the above description. Therefore, certain details in the embodiments should not constitute a limitation to the present invention, and the present invention will take the scope defined by the appended claims as the protection scope of the present invention.

Claims

1. A method for evaluating the integrity of foreign enterprise portraits based on blockchain, characterized in that: The steps include: Collect data on cooperation records between Chinese overseas business units and foreign companies; Extract key features related to corporate integrity from the collected cooperation record data to form a data set; Using the data set to train a random forest model to obtain a credit evaluation model; Based on the collected cooperation record data and the evaluation results of the integrity evaluation model, a comprehensive portrait of foreign companies is generated and displayed.

2. The method for evaluating the integrity of foreign enterprise portraits based on blockchain as claimed in claim 1 is characterized in that: The key features related to corporate integrity extracted from the collected cooperation record data include the proportion of payment delay days, the average project completion cycle deviation rate, and the proportion of contract breach times.

3. The method for evaluating the integrity of foreign enterprise portraits based on blockchain as claimed in claim 1 is characterized in that: When using the data set to train the random forest model, the data set is divided into a training set and a test set according to a certain ratio; Using the training set to train the random forest model to obtain a credit evaluation model; The obtained integrity evaluation model is tested using the test set.

4. The method for evaluating the integrity of foreign enterprise portraits based on blockchain as claimed in claim 1, characterized in that: Also includes: Regularly use newly collected data to perform incremental training on the integrity evaluation model.

5. The method for evaluating the integrity of foreign enterprise portraits based on blockchain as claimed in claim 1 is characterized in that: Also includes: The collected cooperation record data is encrypted using blockchain encryption technology.

6. A storage medium, characterized in that: The storage medium stores a program of a method for evaluating the integrity of foreign enterprise portraits based on blockchain. When the program of the method for generating a portrait of a foreign enterprise including integrity evaluation based on blockchain is executed by a processor, the steps of the method for generating a portrait of a foreign enterprise including integrity evaluation based on blockchain as described in any one of claims 1 to 5 are implemented.

7. A blockchain-based foreign enterprise portrait system with integrity evaluation, characterized by: include: Data collection unit, used to collect cooperation record data between Chinese overseas business units and foreign enterprises; A feature extraction unit, connected to the data collection unit, for extracting key features related to corporate integrity from the collected cooperation record data to form a data set; A model building unit, connected to the feature extraction unit, for training a random forest model using the data set to obtain a credit evaluation model; The enterprise portrait generation unit is connected to the data collection unit and the model building unit, and is used to generate and display a comprehensive portrait of the foreign enterprise based on the collected cooperation record data and the evaluation results of the integrity evaluation model.

8. The blockchain-based foreign enterprise portrait system with integrity evaluation as claimed in claim 7 is characterized in that: The key features extracted by the feature extraction unit include a payment delay days ratio feature, a project average completion cycle deviation rate feature, and a contract breach times ratio feature.

9. The blockchain-based foreign enterprise portrait system with integrity evaluation as claimed in claim 7, characterized in that: The model building unit is also used to divide the data set into a training set and a test set according to a certain ratio; Then, the random forest model is trained using the training set to obtain a credit evaluation model; The obtained integrity evaluation model is tested using the test set.

10. The blockchain-based foreign enterprise portrait system with integrity evaluation as claimed in claim 7, characterized in that: The model building unit is also used to locate and use newly collected data to perform incremental training on the integrity evaluation model.

Images