Credit evaluation method, device, equipment and computer-readable storage medium

Abstract

The embodiments of the present invention provide a credit evaluation method, device, equipment and computer-readable storage medium. The credit evaluation method includes obtaining the target credit score of the second user associated with the first user in the industrial chain, obtaining the transaction flow data of the first user and the second user in the industrial chain, determining the first impact factor of the second user on the first user based on the first preset rule, the flow direction of the transaction flow data and the proportion of the transaction flow data in all the transaction flow data of the first user, determining the associated credit of the second user to the first user based on the first impact factor and the target credit score of the second user; determining the target credit score of the first user based on the associated credit and the credit score of the first user; the credit score of the first user includes a credit score determined based on a credit evaluation model. According to the embodiments of the present application, the current credit evaluation of the user can be accurate.

Description

Technical Field

[0001] The present invention belongs to the field, and in particular to a credit evaluation method, device, equipment and computer-readable storage medium. Background Art

[0002] As society becomes more transparent and standardized, user credit is becoming more and more important. Currently, the user's credit is mainly evaluated using the user's own data. In this credit evaluation process, the connection between the user and society is ignored, so the evaluation data is single in the user credit evaluation process, resulting in inaccurate credit evaluation of the user. Summary of the invention

[0003] The embodiments of the present invention provide a credit evaluation method, apparatus, device and computer-readable storage medium, which can make the current credit evaluation of a user accurate.

[0004] In a first aspect, an embodiment of the present invention provides a credit evaluation method, the method comprising:

[0005] Obtaining a target credit score of a second user associated with the first user in the industrial chain;

[0006] Obtaining transaction flow data between the first user and the second user in the industrial chain;

[0007] Determine a first influence factor of the second user on the first user based on a first preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data in all transaction flow data of the first user;

[0008] determining the associated credit of the second user to the first user based on the first impact factor and the target credit score of the second user;

[0009] Based on the associated credit and the credit score of the first user, a target credit score of the first user is determined; the credit score of the first user includes a credit score determined based on a credit evaluation model.

[0010] In some implementations, the second users include industry chain core users and industry chain non-core users;

[0011] In the case where the second user includes a core user of the industrial chain, obtaining a target credit score of the second user associated with the first user in the industrial chain specifically includes:

[0012] Determining the credit score of the second user determined by the credit evaluation model as a target credit score for the second user;

[0013] In the case where the second user includes a non-core user of the industrial chain, obtaining a target credit score of the second user associated with the first user in the industrial chain specifically includes:

[0014] Determine a target credit score of a third user associated with the second user based on the target credit score of the core user of the industry chain;

[0015] Determining the associated credit of the third user to the second user based on the second influencing factor and the target credit score of the third user; the second influencing factor is determined according to the first preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data of the second user and the third user in all the transaction flow data of the second user;

[0016] Based on the associated credit and the credit score of the second user, a target credit score of the second user is determined; the credit score of the second user includes a credit score determined based on a credit evaluation model.

[0017] In some embodiments, the transaction flow data includes at least one of logistics, capital flow, or information flow data;

[0018] Obtain transaction flow data between the first user and the second user in the industrial chain, including:

[0019] Based on the knowledge graph corresponding to the preset industrial chain, at least one of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain is determined.

[0020] In some embodiments, before determining at least one of logistics, capital flow, or information flow data of the first user and the second user in the industrial chain based on the knowledge graph corresponding to the preset industrial chain, the method further includes:

[0021] Build a knowledge graph based on the logistics, capital flow or information flow data of the industrial chain stored on the blockchain.

[0022] In some implementations, determining a first influence factor of the second user on the first user based on the first preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data in all transaction flow data of the first user specifically includes:

[0023] Determine the flow direction of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain and the proportion of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain to the total logistics, capital flow or information flow data of the first user based on graph theory technology;

[0024] The first influence factor of the second user on the first user is determined based on the first preset rule, the flow direction and proportion of logistics, capital flow or information flow data in the industrial chain.

[0025] In some implementations, the credit score determined based on the credit evaluation model specifically includes:

[0026] The investment data of users outside the industrial chain and the first user, the government affairs data of the first user, public opinion data and the credit evaluation score of financial institutions are input into the credit evaluation model to obtain the credit score of the first user.

[0027] In some implementations, the credit evaluation method further includes:

[0028] Obtaining a target risk score for the second user;

[0029] Determine a third influence factor of the second user on the first user based on a second preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data in all transaction flow data of the first user;

[0030] Determining an association risk of the second user to the first user based on the third impact factor and the target risk score of the second user;

[0031] Based on the associated risk and the risk score of the first user, a target risk score for the first user is determined; the risk score of the first user includes a risk score determined based on a risk assessment model.

[0032] In some implementations, the credit evaluation method further includes: when the second user includes a core user of the industrial chain, obtaining a target risk score of the second user associated with the first user in the industrial chain, specifically including:

[0033] Determining the risk score of the second user determined by the credit evaluation model as a target risk score of the second user;

[0034] In the case where the second user includes a non-core user of the industrial chain, obtaining a target credit score of the second user associated with the first user in the industrial chain specifically includes:

[0035] Determine the target risk score of the third user associated with the second user based on the target risk score of the core user of the industrial chain;

[0036] determining the associated credit of the third user to the second user based on the fourth influencing factor and the target credit score of the third user; the second influencing factor comprises determining according to the second preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user;

[0037] Based on the associated risk and the risk score of the second user, a target risk score for the second user is determined; the risk score of the second user includes a risk score determined based on a credit evaluation model.

[0038] In some embodiments, the risk score determined based on the risk assessment model specifically includes:

[0039] The first user's government affairs data, public opinion data, asset data, contract performance data, operation data and financial institution risk assessment score are input into the risk assessment model to obtain the first user's risk score.

[0040] In some implementations, the credit evaluation method further includes:

[0041] Determining a credit reference value of the first user based on a third preset rule and a target credit score of the first user;

[0042] When the association risk between the second user and the first user is greater than or equal to the credit reference value, a risk warning is issued to the first user.

[0043] In a second aspect, an embodiment of the present invention provides a credit evaluation device, the credit evaluation device comprising:

[0044] A first acquisition module, used to acquire a target credit score of a second user associated with the first user in the industrial chain;

[0045] A second acquisition module is used to acquire transaction flow data between the first user and the second user in the industrial chain;

[0046] A first determination module, configured to determine a first influence factor of the second user on the first user based on a first preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data in all transaction flow data of the first user;

[0047] A second determination module, configured to determine the associated credit of the second user to the first user based on the first impact factor and the target credit score of the second user;

[0048] The third determination module is used to determine the target credit score of the first user based on the associated credit and the credit score of the first user; the credit score of the first user includes a credit score determined based on a credit evaluation model.

[0049] In some implementations, the second users include industry chain core users and industry chain non-core users;

[0050] A first acquisition module, when the second user includes a core user of the industrial chain, is used to determine the credit score of the second user determined by the credit evaluation model as the target credit score of the second user;

[0051] The first acquisition module, when the second user includes a non-core user of the industrial chain, includes:

[0052] A first determining unit, configured to determine a target credit score of a third user associated with the second user based on a target credit score of a core user of the industry chain;

[0053] A second determining unit is used to determine the associated credit of the third user to the second user based on the second influencing factor and the target credit score of the third user; the second influencing factor is determined according to the first preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user;

[0054] The third determining unit is used to determine a target credit score of the second user based on the associated credit and the credit score of the second user; the credit score of the second user includes a credit score determined based on a credit evaluation model.

[0055] In some embodiments, the transaction flow data includes at least one of logistics, capital flow, or information flow data;

[0056] The second acquisition module is used to determine at least one of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain based on the knowledge graph corresponding to the preset industrial chain.

[0057] In some embodiments, the credit evaluation device also includes: a construction module for constructing a knowledge graph based on the logistics, capital flow or information flow data on the industrial chain stored on the blockchain before determining at least one of the logistics, capital flow or information flow data of the first user and the second user on the industrial chain based on the knowledge graph corresponding to the preset industrial chain.

[0058] In some implementations, the first determining module specifically includes:

[0059] A fourth determination unit is used to determine the flow direction of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain and the proportion of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain in all the logistics, capital flow or information flow data of the first user based on graph theory technology;

[0060] The fifth determining unit is used to determine the first influence factor of the second user on the first user based on the first preset rule, the flow direction and proportion of logistics, capital flow or information flow data in the industrial chain.

[0061] In some implementations, the third determination module specifically includes:

[0062] The sixth determination unit is used to input the investment data of users outside the industrial chain and the first user, the government affairs data of the first user, the public opinion data and the credit evaluation score of the financial institution into the credit evaluation model to obtain the credit score of the first user.

[0063] In some implementations, the credit evaluation device further includes:

[0064] A third acquisition module is used to obtain a target risk score of the second user;

[0065] A fourth determination module, configured to determine a third influence factor of the second user on the first user based on the second preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data in all transaction flow data of the first user;

[0066] A fifth determination module, configured to determine the association risk of the second user to the first user based on the third impact factor and the target risk score of the second user;

[0067] The sixth determination module is used to determine a target risk score for the first user based on the associated risk and the risk score of the first user; the risk score of the first user includes a risk score determined based on a risk assessment model.

[0068] In some embodiments,

[0069] A third acquisition module is used to determine the risk score of the second user determined by the credit evaluation model as the target risk score of the second user when the second user includes a core user of the industrial chain;

[0070] The third acquisition module, when the second user includes a non-core user of the industrial chain, specifically includes:

[0071] A seventh determination unit, configured to determine a target risk score of a third user associated with the second user based on the target risk score of the core user of the industrial chain;

[0072] An eighth determination unit is used to determine the associated credit of the third user to the second user based on the fourth impact factor and the target credit score of the third user; the second impact factor includes the second preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user.

[0073] The ninth determination unit is used to determine a target risk score for the second user based on the associated risk and the risk score of the second user; the risk score of the second user includes a risk score determined based on a credit evaluation model.

[0074] In some implementations, the sixth determination module specifically includes:

[0075] The tenth determination unit is used to input the first user's government data, public opinion data, asset data, contract performance data, operation data and financial institution risk assessment score into the risk assessment model to obtain the risk score of the first user.

[0076] In some implementations, the credit evaluation device further includes:

[0077] A seventh determination module, configured to determine a credit reference value of the first user based on a third preset rule and a target credit score of the first user;

[0078] The warning module is used to issue a risk warning to the first user when the association risk between the second user and the first user is greater than or equal to the credit reference value.

[0079] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;

[0080] When the processor executes the computer program instructions, the steps of the credit evaluation method in any one of the embodiments of the first aspect are implemented.

[0081] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the steps of the credit evaluation method in any one of the embodiments of the first aspect are implemented.

[0082] In a fifth aspect, an embodiment of the present invention provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device can execute a credit evaluation method as described in any one of the embodiments of the first aspect.

[0083] The credit evaluation method, device, equipment and computer-readable storage medium of the embodiment of the present invention, after obtaining the target credit score of the second user associated with the first user in the industrial chain, determine the first influence factor of the second user on the first user based on the transaction flow data of the first user and the second user in the industrial chain, the first preset rule and the proportion of the transaction flow data of the first user and the second user in the industrial chain in all the transaction flow data of the first user. Then, the associated credit of the second user to the first user is determined based on the acquired influence factor and the target credit score of the second user, and then the target credit score of the first user is determined based on the credit evaluation score and the associated credit determined by the first user through the credit evaluation model. Therefore, since the target credit score of the first user is finally determined based on the associated credit of the second user associated with the first user in the industrial chain and the credit score determined by the credit evaluation model, the reference data is more comprehensive when determining the target credit score of the first user, and further, the determined target credit score of the first user can be made more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the following is a brief introduction to the drawings required for use in the embodiment of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0085] Figure 1 This is a schematic diagram of the structure of the industrial chain provided by an example of this application;

[0086] Figure 2 It is a flowchart of a credit evaluation method provided by an embodiment of the present application;

[0087] Figure 3 is a schematic diagram of a knowledge graph provided by an embodiment of the present application;

[0088] Figure 4 is a flow chart of a credit evaluation method provided by another embodiment of the present application;

[0089] Figure 5 This is a schematic diagram of the structure of a credit evaluation device provided by an embodiment of the present application.

[0090] Figure 6 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0091] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present invention, rather than to limit the present invention. For those skilled in the art, the present invention can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present invention by illustrating examples of the present invention.

[0092] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0093] In order to introduce the credit evaluation method provided in the embodiment of the present application in more detail, the embodiment of the present application first introduces the industrial chain. Figure 1 A schematic diagram of the structure of the industrial chain provided by an example of this application is shown. Figure 1As shown, the industrial chain can include core enterprises, upstream enterprises and downstream enterprises related to the core enterprises, as well as logistics, capital flow and information flow between the above-mentioned core enterprises and upstream enterprises and downstream enterprises.

[0094] In the current credit evaluation process, enterprises at the core of the industrial chain can often obtain higher credit ratings by relying on their larger size and core position in the industrial chain. However, enterprises upstream and downstream of the industrial chain can often only obtain credit ratings based on existing credit evaluation methods and their own credit evaluation data, resulting in inaccurate corresponding credit evaluation results for upstream and downstream enterprises.

[0095] In order to solve the problems in the prior art, embodiments of the present invention provide a credit evaluation method, apparatus, device and computer-readable storage medium.

[0096] The following first introduces the credit evaluation method provided by the embodiment of the present invention.

[0097] Figure 2 FIG. 1 is a flow chart of a credit evaluation method provided by an embodiment of the present invention. Figure 2 As shown, the method may include the following steps:

[0098] S210, obtaining a target credit score of a second user associated with the first user in the industrial chain;

[0099] S220, obtaining transaction flow data between the first user and the second user in the industrial chain;

[0100] S230, determining a first influence factor of the second user on the first user based on a first preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data in all transaction flow data of the first user;

[0101] S240, determining the associated credit of the second user to the first user based on the first impact factor and the target credit score of the second user;

[0102] S250: Determine a target credit score for the first user based on the associated credit and the credit score of the first user; the credit score of the first user includes a credit score determined based on a credit evaluation model.

[0103] Thus, after obtaining the target credit score of the second user associated with the first user in the industrial chain, the first influence factor of the second user on the first user is determined based on the transaction flow data of the first user and the second user in the industrial chain, the first preset rule, and the proportion of the transaction flow data of the first user and the second user in the industrial chain in all the transaction flow data of the first user. Then, the associated credit of the second user to the first user is determined based on the acquired influence factor and the target credit score of the second user, and then the target credit score of the first user is determined based on the credit evaluation score and the associated credit determined by the first user through the credit evaluation model. Thus, since the target credit score of the first user is finally determined based on the associated credit of the second user associated with the first user in the industrial chain and the credit score determined through the credit evaluation model, the reference data is more comprehensive when determining the target credit score of the first user, and further, the determined target credit score of the first user can be made more accurate.

[0104] In some implementations, in S210, the first user and the second user are both users in the industrial chain, wherein the second user may include a core user of the industrial chain or a non-core user of the industrial chain, and the first user may include a user adjacent to the second user in the industrial chain.

[0105] In some embodiments, when the second user includes a core user of the industrial chain, S210 may specifically include:

[0106] The credit score of the second user determined by the credit evaluation model is determined as the target credit score of the second user.

[0107] In some implementations, determining the credit score of the second user based on the credit evaluation model specifically includes:

[0108] At least one of the investment data of the user outside the industrial chain and the second user, the government affairs data of the second user, public opinion data and the credit evaluation score of the financial institution is input into the credit evaluation model to obtain the credit score of the second user.

[0109] In some implementations, in actual production and life, in addition to having an association relationship with enterprises in the industrial chain, users usually also have an investment relationship with users outside the industrial chain. The government data of the second user, such as tax payment, policy support funds, and policy exemption funds, is also closely related to the credit evaluation of the second user.

[0110] In some embodiments, before inputting at least one of the investment data of the user outside the industrial chain and the second user, the government affairs data of the second user, the public opinion data, and the credit evaluation score of the financial institution into the credit evaluation model to obtain the credit score of the second user, the credit evaluation method may further include:

[0111] The credit evaluation model is trained based on multiple sets of training samples to obtain a trained credit evaluation model, wherein each set of training samples may include historical investment data, historical government data, historical public opinion data, and historical financial institution credit evaluation scores and historical credit scores.

[0112] In some specific examples, it is possible to obtain investment data of users and second users outside the industrial chain, second user government affairs data, public opinion data and credit rating scores of financial institutions through artificial intelligence, blockchain, cloud computing, big data, mobile Internet, Internet of Things, and multi-network integration technologies.

[0113] In some implementations, training a credit evaluation model based on multiple sets of training samples may include:

[0114] For each set of training samples, perform the following steps:

[0115] Each set of training samples is input into the credit evaluation model to obtain the predicted credit scores corresponding to the historical investment data, historical government data, historical public opinion data and historical financial institution credit evaluation scores. Then, the loss function value corresponding to the credit evaluation model is determined based on the historical credit score and the predicted credit score. If the loss function value does not meet the training stop condition, the model parameters of the credit evaluation model are adjusted, and the training samples are used to train the credit evaluation model with adjusted parameters until the training stop condition is met, thereby obtaining the trained credit evaluation model.

[0116] Here, the training stop condition may include a condition set by a user. Exemplarily, the training stop condition may include a loss function value being less than a certain threshold or the number of training iterations reaching a certain specific value.

[0117] Therefore, by pre-training the credit evaluation model, the trained credit evaluation model can make the credit score predicted by the subsequent credit score prediction more accurate.

[0118] In some embodiments, when the second user includes a non-core user of the industrial chain, obtaining the target credit score of the second user associated with the first user in the industrial chain specifically includes:

[0119] Determining the credit score of the second user determined by the credit evaluation model as a target credit score for the second user;

[0120] In the case where the second user includes a non-core user of the industrial chain, obtaining a target credit score of the second user associated with the first user in the industrial chain specifically includes:

[0121] Determine a target credit score of a third user associated with the second user based on the target credit score of the core user of the industry chain;

[0122] Determining the associated credit of the third user to the second user based on the second influencing factor and the target credit score of the third user; the second influencing factor is determined according to the first preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data of the second user and the third user in all the transaction flow data of the second user;

[0123] Based on the associated credit and the credit score of the second user, a target credit score of the second user is determined; the credit score of the second user includes a credit score determined based on a credit evaluation model.

[0124] In some implementations, when the second user includes a non-core user of the industry chain, the method for determining the target credit score of the second user is the same as the method for determining the target credit score of the first user, and will not be repeated here.

[0125] Thus, after obtaining the target credit score of the third user associated with the second user in the industrial chain, the second impact factor of the third user on the second user is determined based on the transaction flow data between the second user and the third user in the industrial chain, the second preset rule, and the proportion of the transaction flow data between the second user and the third user in the industrial chain in all the transaction flow data of the second user. Then, the associated credit of the third user to the second user is determined based on the acquired impact factor and the target credit score of the third user, and then the target credit score of the second user is determined based on the credit evaluation score and the associated credit determined by the second user through the credit evaluation model. Thus, since the target credit score of the second user is finally determined based on the associated credit of the third user associated with the second user in the industrial chain and the credit score determined through the credit evaluation model, the reference data is more comprehensive when determining the target credit score of the second user, and further, the determined target credit score of the second user can be made more accurate.

[0126] In some embodiments, in S220, the transaction flow data includes at least one of logistics, capital flow, or information flow data.

[0127] Here, the logistics, capital flow or information flow data includes the logistics, capital flow or information flow data in the industrial chain.

[0128] In some embodiments, S220 may specifically include:

[0129] Based on the knowledge graph corresponding to the preset industrial chain, at least one of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain is determined.

[0130] In some embodiments, before determining at least one of the logistics, capital flow, or information flow data of the first user and the second user in the industrial chain based on the knowledge graph corresponding to the preset industrial chain, the credit evaluation method may further include:

[0131] Build a knowledge graph based on the logistics, capital flow or information flow data of the industrial chain stored on the blockchain.

[0132] In some implementations, the logistics, capital flow, or data flow in the industrial chain can be stored in advance based on blockchain technology.

[0133] In some specific examples, logistics data and warehouse receipt data can be marked with RFID electronic tags, and then combined with electronic maps to monitor the authenticity of the entire process of logistics. Blockchain technology can be used to specify smart contracts in multiple user transactions in the supply chain, and data asset certificates between users are transferred and exchanged through the smart contract platform. Once the data asset transfer is completed, the core enterprise creditor's rights relationship corresponding to the supply chain financial assets is transferred, and the receivables due funds are automatically transferred and exchanged according to the transaction number certificate holdings, which can be traced in both directions.

[0134] In some specific examples, users' logistics, capital flow or data flow data can also be obtained through artificial intelligence, blockchain, cloud computing, big data, mobile Internet, Internet of Things, and multi-network integration technologies.

[0135] Therefore, by introducing blockchain technology to store the logistics, capital flow or data flow in the industrial chain, when the logistics, capital flow or data flow in the industrial chain changes, the changed information can be changed in time, further ensuring the accuracy of the data used to construct the knowledge graph.

[0136] In some implementations, in S230, the first preset rule may include determining the influence factor between the second user and the first user according to the proportion of the transaction flow data of the first user and the second user in all the transaction flow data of the first user. The first user may be associated with multiple users.

[0137] In some embodiments, S230 may specifically include:

[0138] Determine the flow direction of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain and the proportion of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain to the total logistics, capital flow or information flow data of the first user based on graph theory technology;

[0139] The first influence factor of the second user on the first user is determined based on the first preset rule, the flow direction and proportion of logistics, capital flow or information flow data in the industrial chain.

[0140] In some embodiments, the flow direction of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain and the proportion of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain in the first user's total logistics, capital flow or information flow data can be determined in the acquired knowledge graph based on graph theory technology. In some specific examples, the relevant data of the user can be obtained in the data storage node of the corresponding blockchain based on natural language processing technology (Natural Language Processing, NLP), the corresponding sentence or corresponding data can be obtained using embedding vector, and then the knowledge graph corresponding to the user can be constructed.

[0141] In some specific examples, after obtaining the relevant data of users, we can also use machine learning model methods to learn and identify transaction classes, association relationship classes and graph features between users, and then generalize and identify users through community discovery algorithms.

[0142] In order to give a detailed introduction to knowledge graph and graph theory technology, Figure 3 A schematic diagram of a knowledge graph provided by an example of this application is shown, Figure 3 As shown, the direction of logistics, capital flow or information flow data on the industrial chain in the knowledge graph and the proportion of logistics, capital flow or information flow data between different users can be marked based on graph theory technology.

[0143] After annotating the knowledge graph based on graph theory technology, we can intuitively obtain the flow direction of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain, as well as the proportion of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain in the total logistics, capital flow or information flow data of the first user.

[0144] Therefore, by marking the direction of the logistics, capital flow or information flow data on the industrial chain in the knowledge graph and the proportion of the logistics, capital flow or information flow data between different users based on graph theory technology, it is possible to intuitively obtain the direction of the logistics, capital flow or information flow data and the proportion of the logistics, capital flow or information flow data between different users. Furthermore, it can be more intuitive and convenient to determine the influencing factor between the first user and the second user.

[0145] In some specific examples, external events that occur to users, such as users defaulting on interest, can lead to debts, which are then transmitted through the associated relationships in the industry chain, transforming the associated users’ actual debts, aggravating the associated users’ debt burden and financial pressure, and even dragging down the associated users. The associated users then transmit the risks to new associated users.

[0146] In some embodiments, in order to conduct risk analysis on users in the industrial chain and avoid associated risks. This application embodiment also provides a credit evaluation method. Figure 4 FIG. 1 is a flow chart of a credit evaluation method provided by an embodiment of the present invention. Figure 4 As shown, the method may include:

[0147] S410, obtaining a target risk score of the second user;

[0148] S420, determining a third influence factor of the second user on the first user based on a second preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data in all transaction flow data of the first user;

[0149] S430, determining the association risk of the second user to the first user based on the third impact factor and the target risk score of the second user;

[0150] S440: Determine a target risk score for the first user based on the associated risk and the risk score of the first user; the risk score of the first user includes a risk score determined based on a risk assessment model.

[0151] Therefore, after obtaining the target risk score of the second user, the associated risk of the second user to the first user is determined based on the second preset rule, the flow direction of the transaction flow data and the proportion of the transaction flow data in all the transaction flow data of the first user, and then the target risk score of the first user is determined based on the associated risk and the risk score of the first user. Since the target risk score of the first user is determined by the associated risk of the second user and the risk score of the first user, the reference data is more comprehensive when determining the target risk score of the first user, and further, the determined target risk score of the first user can be made more accurate.

[0152] In some embodiments, when the second user includes a core user of the industrial chain, S410 specifically includes:

[0153] The risk score of the second user determined by the risk assessment model is determined as the target risk score of the second user.

[0154] In some implementations, determining a target risk score for the second user based on the risk assessment model specifically includes:

[0155] The second user's government affairs data, public opinion data, asset data, performance data, operation data and financial institution risk assessment score are input into the risk assessment model to obtain the risk score of the first user.

[0156] In some embodiments, in actual production and life, users are usually associated with financial institutions in addition to being associated with users in the industrial chain. In addition to the asset data and performance data of the relevant financial institutions, the user's risks are also related to social public opinion data, government data, and their own operating data.

[0157] In some specific examples, obtaining user public opinion data may include: using the NLP public opinion attention model to conduct public opinion analysis based on the user list, and conducting operational monitoring and management based on the preset threshold. Pay timely attention to the risk users in key areas such as de-capacity, de-stocking, deleveraging, and guarantee circles that are continuously released by the outside world. Timely discover various types of risky users in daily off-site monitoring; pay attention to public market defaults, negative information in the bond market, external rating downgrades, etc. Major media report negative public opinion. Pay attention to various external "blacklists", safety and environmental protection penalties, and shutdown list companies, as well as large-amount risk users, large-amount non-performing users, and users who have defaulted for more than 30 days that are regularly released by the China Insurance Regulatory Commission.

[0158] In some specific examples, obtaining user operating data may include: paying attention to the non-performing rate, overdue rate, newly exposed non-performing loan rate, and loan-like ratio readiness rate, loan-like migration readiness rate, credit cost readiness rate, pure newly issued non-performing loans and other operating indicators of financial products, while combining the user's normal indicators for real-time monitoring.

[0159] In some specific examples, user risks may include risks transmitted through the industrial chain and risks transmitted through non-industrial chains. Non-industrial chain transmission risks may include risks transmitted through users not associated with the industrial chain and risks incurred by users on the industrial chain due to their own reasons. Both risks will be transmitted to the industrial chain through users on the industrial chain.

[0160] In some specific examples, RPA robots can be used to analyze legal texts and government texts to obtain government data.

[0161] In some embodiments, before inputting the second user's government affairs data, public opinion data, asset data, contract performance data, operation data, and financial institution risk assessment score into the risk assessment model to obtain the risk score of the first user, the credit assessment method further includes:

[0162] The risk assessment model is trained based on multiple sets of training samples to obtain a trained risk assessment model, wherein each set of training samples may include historical government data, historical public opinion data, historical asset data, historical performance data, historical operation data, historical financial institution risk assessment scores, and historical risk scores.

[0163] In some embodiments, training a risk assessment model based on multiple sets of training samples may include:

[0164] For each set of training samples, perform the following steps:

[0165] Each set of training samples is input into the risk assessment model to obtain the predicted risk scores corresponding to the historical government data, historical public opinion data, historical asset data, historical performance data, historical operation data and historical financial institution risk assessment scores. Then, the loss function value of the risk assessment model is determined based on the predicted risk score and the historical risk score. If the loss function value does not meet the training stop condition, the model parameters of the risk assessment model are adjusted, and the risk assessment model with adjusted parameters is trained using the training samples until the training stop condition is met to obtain the trained risk assessment model.

[0166] Here, the training stop condition may include a condition set by a user. Exemplarily, the training stop condition may include a loss function value being less than a certain threshold or the number of training iterations reaching a certain specific value.

[0167] Therefore, by pre-training the risk assessment model, the risk score predicted by the trained risk assessment model in the subsequent prediction of the risk score can be more accurate.

[0168] In some specific examples, core users may accumulate or incur debts that exceed their own upper limit due to business expansion and other factors, causing the overall credit of the supply chain to deteriorate. When the core user's industry status undergoes major changes and develops in a bad direction, it may conceal or privately change various transaction information, organize upstream and downstream to obtain excess credit, and use it for extracorporeal circulation without regulatory control. In response to this situation, you can pay attention to the core user's account status and behavior status, pay attention to the status, behavior, and change trends, and introduce full-process financing management. Carry out full-process tracking of the relevant account status while paying attention to operating indicators such as the non-performing rate of financing products, overdue rate, newly exposed non-performing loan rate, readiness of the proportion of loans of concern, readiness of migration of loans of concern, credit cost readiness, and pure new non-performing loans. Pay attention to the derivative risks of public opinion risks and related risks, so as to dynamically monitor the risks of core users.

[0169] In some specific examples, non-core users are affected by the scale of operation, poor operational transparency, poor information disclosure, lack of credibility of financial characteristics, weak compliance constraints, etc. There are not many targeted measures, resulting in multi-dimensional risks for non-core users. Non-core users are affected by their own operational risk factors and are also susceptible to the transmission of supply chain risks. In view of this situation, full-process financing management can be introduced. Full-process tracking of relevant account conditions is carried out, and attention is paid to operating indicators such as the non-performing rate of financing products, overdue rate, newly exposed non-performing loan rate, the proportion of loans under special attention, the migration readiness rate of loans under special attention, the readiness of credit costs, and the purely newly issued non-performing loans. At the same time, attention is paid to the derivative risks of public opinion risks and related risks, so as to conduct dynamic full-process monitoring and early warning of supply chain risks.

[0170] In the case where the second user includes a non-core user of the industrial chain, obtaining a target credit score of the second user associated with the first user in the industrial chain specifically includes:

[0171] Determine the target risk score of the third user associated with the second user based on the target risk score of the core user of the industrial chain;

[0172] determining the associated credit of the third user to the second user based on the fourth influencing factor and the target credit score of the third user; the second influencing factor comprises determining according to the second preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user;

[0173] Based on the associated risk and the risk score of the second user, a target risk score for the second user is determined; the risk score of the second user includes a risk score determined based on a risk assessment model.

[0174] In some implementations, when the second user includes a non-core user of the industrial chain, the method for determining the target risk score of the second user is the same as the method for determining the risk score of the first user, and is not described in detail here.

[0175] In some specific examples, the target risk score can be divided into three levels, namely, prompt level, warning level and alarm level.

[0176] At the prompt level, it can include warning-true association reminders, real-alarm association reminders, prompt-type rules, and whitelist dimensionality reduction for users corresponding to the prompt level.

[0177] At the early warning level, it can include monitoring account behavior of users corresponding to the early warning level, predicting contract performance risks, collecting credit information of users, and collecting financial status of users.

[0178] At the alarm level, it can include credit compliance, HRS monitoring, risk preference implementation, and industry limit implementation for users corresponding to the alarm level.

[0179] Thus, after obtaining the target risk score of the third user associated with the second user in the industrial chain, the second impact factor of the third user on the second user is determined based on the transaction flow data between the second user and the third user in the industrial chain, the second preset rule, and the proportion of the transaction flow data between the second user and the third user in the industrial chain in all the transaction flow data of the second user. Then, the associated risk of the third user to the second user is determined based on the acquired impact factor and the target risk score of the third user, and then the target risk score of the second user is determined based on the risk assessment score and the associated risk determined by the risk assessment model of the second user. Thus, since the target risk score of the second user is finally determined based on the associated risk of the third user associated with the second user in the industrial chain and the risk score determined by the risk assessment model, the reference data is more comprehensive when determining the target risk score of the second user, and further, the determined target risk score of the second user can be made more accurate.

[0180] In some embodiments, in S420, the second preset rule may be the same as the first preset rule, and may include determining the final impact factor based on the flow direction of the transaction flow data and the proportion of the transaction flow data in all transaction flow data of the first user in a user-defined manner. The above proportion value may be positively correlated with the impact factor value.

[0181] In some implementations, the third impact factor may be the same as the first impact factor, which will not be described in detail herein.

[0182] In some implementations, the product of the third impact factor and the target risk score of the second user may be used as the associated risk of the second user and the first user.

[0183] In some implementations, the method of determining the target risk score of the first user in S440 may include: determining the risk score based on a risk assessment model. The method of determining the risk score of the first user based on the risk assessment model is the same as the method of determining the risk score of the second user based on the risk assessment model, and will not be repeated here.

[0184] In some embodiments, after obtaining the target credit score and associated risk of the first user, in order to prevent the risk from being transmitted in the industrial chain to cause greater risk, the credit evaluation method may also include:

[0185] Determining a credit reference value of the first user based on a third preset rule and a target credit score of the first user;

[0186] When the association risk between the second user and the first user is greater than or equal to the credit reference value, a risk warning is issued to the first user.

[0187] In some implementations, the third preset rule may include a rule determined by the user based on actual conditions. The credit reference value of the first user may be determined based on the target credit score of the first user in a preset ratio.

[0188] In some implementations, issuing a risk warning to the first user may include sending a credit risk value to a smart device of the first user.

[0189] When the credit evaluation device determines that the second user has incurred risk but the associated risk between the second user and the first user is greater than or equal to the credit reference value, risk warning information can be sent to the relevant smart device of the first user via network transmission.

[0190] In some specific examples, users can also be stress tested, using three dimensions of neutrality, optimism, and pessimism, introducing four types of financing products: large and medium-sized, small and micro, individuals, and cardholders, and conducting overall stress tests on indicators such as non-performing, non-performing at the beginning of the year, overdue, overdue compared to the beginning of the year, and overdue non-performing scissors, and forming analysis models for related indicators. Focus on quantitative analysis of areas with large indicator fluctuations. At the same time, combine supply chain credit and supply chain knowledge graphs to conduct overall stress tests on the supply chain. Combine the supply chain user ecosystem and conduct an overall stress test on the supply chain user ecosystem. Determine the user's risk tolerance through stress testing.

[0191] Therefore, by comparing the associated risk between the second user and the first user with the credit reference value of the first user, and issuing an alarm to the first user when the associated risk is greater than or equal to the credit reference value, the first user can take early prevention of the associated risk and prevent the risk from being transmitted in the industrial chain to cause greater risk.

[0192] It should be noted that the application scenarios described in the above-mentioned disclosed embodiments are intended to more clearly illustrate the technical solutions of the disclosed embodiments, and do not constitute a limitation of the technical solutions provided by the disclosed embodiments. A person of ordinary skill in the art can appreciate that with the emergence of new application scenarios, the technical solutions provided by the disclosed embodiments are also applicable to similar technical problems.

[0193] Based on the same inventive concept, the present application embodiment also provides a credit evaluation device. Figure 5 The credit evaluation device provided in the embodiment of the present application is described in detail:

[0194] Figure 5 FIG. 1 is a schematic diagram showing a structure of an embodiment of a credit evaluation device provided by the present application. Figure 5 As shown, the credit evaluation device may include:

[0195] A first acquisition module 501 is used to acquire a target credit score of a second user associated with the first user in the industrial chain;

[0196] The second acquisition module 502 is used to acquire transaction flow data between the first user and the second user in the industrial chain;

[0197] A first determination module 503, configured to determine a first influence factor of the second user on the first user based on a first preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data in all transaction flow data of the first user;

[0198] A second determination module 504, configured to determine the associated credit of the second user to the first user based on the first impact factor and the target credit score of the second user;

[0199] The third determination module 505 is used to determine the target credit score of the first user based on the associated credit and the credit score of the first user; the credit score of the first user includes a credit score determined based on a credit evaluation model.

[0200] Thus, after obtaining the target credit score of the second user associated with the first user in the industrial chain, the first influence factor of the second user on the first user is determined based on the transaction flow data of the first user and the second user in the industrial chain, the first preset rule, and the proportion of the transaction flow data of the first user and the second user in the industrial chain in all the transaction flow data of the first user. Then, the associated credit of the second user to the first user is determined based on the acquired influence factor and the target credit score of the second user, and then the target credit score of the first user is determined based on the credit evaluation score and the associated credit determined by the first user through the credit evaluation model. Thus, since the target credit score of the first user is finally determined based on the associated credit of the second user associated with the first user in the industrial chain and the credit score determined through the credit evaluation model, the reference data is more comprehensive when determining the target credit score of the first user, and further, the determined target credit score of the first user can be made more accurate.

[0201] In some implementations, in order to make the target credit score of the second user more accurate, the second user includes a core user of the industry chain and a non-core user of the industry chain;

[0202] The first acquisition module 501, when the second user includes a core user of the industrial chain, can be used to determine the credit score of the second user determined by the credit evaluation model as the target credit score of the second user;

[0203] The first acquisition module 501, when the second user includes a non-core user of the industrial chain, includes:

[0204] The first determining unit may be configured to determine a target credit score of a third user associated with the second user based on a target credit score of a core user of the industry chain;

[0205] The second determination unit may be used to determine the associated credit of the third user to the second user based on the second influencing factor and the target credit score of the third user; the second influencing factor includes the first preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user.

[0206] The third determining unit may be configured to determine a target credit score of the second user based on the associated credit and the credit score of the second user; the credit score of the second user includes a credit score determined based on a credit evaluation model.

[0207] Thus, after obtaining the target credit score of the third user associated with the second user in the industrial chain, the second impact factor of the third user on the second user is determined based on the transaction flow data between the second user and the third user in the industrial chain, the second preset rule, and the proportion of the transaction flow data between the second user and the third user in the industrial chain in all the transaction flow data of the second user. Then, the associated credit of the third user to the second user is determined based on the acquired impact factor and the target credit score of the third user, and then the target credit score of the second user is determined based on the credit evaluation score and the associated credit determined by the second user through the credit evaluation model. Thus, since the target credit score of the second user is finally determined based on the associated credit of the third user associated with the second user in the industrial chain and the credit score determined through the credit evaluation model, the reference data is more comprehensive when determining the target credit score of the second user, and further, the determined target credit score of the second user can be made more accurate.

[0208] In some embodiments, in order to make the acquired knowledge graph more accurate, the transaction flow data includes at least one of logistics, capital flow or information flow data;

[0209] The second acquisition module 502 can be used to determine at least one of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain based on the knowledge graph corresponding to the preset industrial chain.

[0210] In some embodiments, the credit evaluation device also includes: a construction module, which can be used to construct a knowledge graph based on the logistics, capital flow or information flow data on the industrial chain stored on the blockchain before determining at least one of the logistics, capital flow or information flow data of the first user and the second user on the industrial chain based on the knowledge graph corresponding to the preset industrial chain.

[0211] Therefore, by introducing blockchain technology to store the logistics, capital flow or data flow in the industrial chain, when the logistics, capital flow or data flow in the industrial chain changes, the changed information can be changed in time, further ensuring the accuracy of the data used to construct the knowledge graph.

[0212] In some implementations, in order to make the determination of the influence factor between the first user and the second user more intuitive and convenient, the first determination module 503 may specifically include:

[0213] The fourth determination unit may be used to determine the flow direction of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain and the proportion of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain in the total logistics, capital flow or information flow data of the first user based on graph theory technology;

[0214] The fifth determination unit may be configured to determine a first influence factor of the second user on the first user based on the first preset rule, the flow direction and proportion of logistics, capital flow or information flow data in the industrial chain.

[0215] Therefore, by marking the direction of the logistics, capital flow or information flow data on the industrial chain in the knowledge graph and the proportion of the logistics, capital flow or information flow data between different users based on graph theory technology, it is possible to intuitively obtain the direction of the logistics, capital flow or information flow data and the proportion of the logistics, capital flow or information flow data between different users. Furthermore, it can be more intuitive and convenient to determine the influencing factor between the first user and the second user.

[0216] In some implementations, the third determining module 505 may specifically include:

[0217] The sixth determination unit can be used to input the investment data of users outside the industrial chain and the first user, the government affairs data of the first user, public opinion data and the credit evaluation score of financial institutions into the credit evaluation model to obtain the credit score of the first user.

[0218] In some implementations, the credit evaluation device may further include:

[0219] A third acquisition module may be used to acquire a target risk score of a second user;

[0220] A fourth determination module may be used to determine a third influence factor of the second user on the first user based on the second preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data in all transaction flow data of the first user;

[0221] A fifth determination module may be used to determine the association risk of the second user to the first user based on the third impact factor and the target risk score of the second user;

[0222] The sixth determination module may be used to determine a target risk score for the first user based on the associated risk and the risk score of the first user; the risk score of the first user includes a risk score determined based on a risk assessment model.

[0223] Therefore, after obtaining the target risk score of the second user, the associated risk of the second user to the first user is determined based on the second preset rule, the flow direction of the transaction flow data and the proportion of the transaction flow data in all the transaction flow data of the first user, and then the target risk score of the first user is determined based on the associated risk and the risk score of the first user. Since the target risk score of the first user is determined by the associated risk of the second user and the risk score of the first user, the reference data is more comprehensive when determining the target risk score of the first user, and further, the determined target risk score of the first user can be made more accurate.

[0224] In some implementations, in order to make the determined target risk score of the second user more accurate, the third acquisition module may be used to determine the risk score of the second user determined by the credit evaluation model as the target risk score of the second user when the second user includes a core user of the industrial chain;

[0225] The third acquisition module, when the second user includes a non-core user of the industrial chain, may specifically include:

[0226] A seventh determination unit may be used to determine a target risk score of a third user associated with the second user based on the target risk score of the core user of the industrial chain;

[0227] An eighth determination unit may be used to determine the associated credit of the third user to the second user based on the fourth impact factor and the target credit score of the third user; the second impact factor comprises a factor determined according to a second preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user;

[0228] The ninth determination unit may be configured to determine a target risk score for the second user based on the associated risk and the risk score of the second user; the risk score of the second user includes a risk score determined based on a credit evaluation model.

[0229] Thus, after obtaining the target risk score of the third user associated with the second user in the industrial chain, the second impact factor of the third user on the second user is determined based on the transaction flow data between the second user and the third user in the industrial chain, the second preset rule, and the proportion of the transaction flow data between the second user and the third user in the industrial chain in all the transaction flow data of the second user. Then, the associated risk of the third user to the second user is determined based on the acquired impact factor and the target risk score of the third user, and then the target risk score of the second user is determined based on the risk assessment score and the associated risk determined by the risk assessment model of the second user. Thus, since the target risk score of the second user is finally determined based on the associated risk of the third user associated with the second user in the industrial chain and the risk score determined by the risk assessment model, the reference data is more comprehensive when determining the target risk score of the second user, and further, the determined target risk score of the second user can be made more accurate.

[0230] In some implementations, the sixth determining module may specifically include:

[0231] The tenth determination unit can be used to input the first user's government data, public opinion data, asset data, performance data, operation data and financial institution risk assessment score into the risk assessment model to obtain the first user's risk score.

[0232] In some implementations, in order to prevent the risk from being transmitted in the industrial chain to cause greater risk, the credit evaluation device may further include:

[0233] A seventh determination module may be used to determine a credit reference value of the first user based on a third preset rule and a target credit score of the first user;

[0234] The warning module can be used to issue a risk warning to the first user when the association risk between the second user and the first user is greater than or equal to the credit reference value.

[0235] Therefore, by comparing the associated risk between the second user and the first user with the credit reference value of the first user, and issuing an alarm to the first user when the associated risk is greater than or equal to the credit reference value, the first user can take early prevention of the associated risk and prevent the risk from being transmitted in the industrial chain to cause greater risk.

[0236] Figure 6 A hardware structure diagram of an embodiment of the electronic device provided by the present application is shown.

[0237] The electronic device 600 may include a processor 601 and a memory 602 storing computer program instructions.

[0238] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0239] The memory 602 may include a large capacity memory that can be used for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0240] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present application.

[0241] The processor 601 implements any one of the credit evaluation methods in the above embodiments by reading and executing computer program instructions stored in the memory 602 .

[0242] In some examples, the electronic device 600 may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.

[0243] The communication interface 603 can be mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0244] Bus 610 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus 610 may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0245] For example, as a payment terminal, the electronic device 600 may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. As a code scanning terminal, the electronic device 600 may be a POS (Point of sales terminal, POS), a code scanner, etc.

[0246] The electronic device can execute the credit evaluation method in the embodiment of the present application, thereby realizing the combination Figures 1 to 5 Described is a credit evaluation method and apparatus.

[0247] In addition, in combination with the credit evaluation method in the above embodiment, the embodiment of the present application may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the credit evaluation methods in the above embodiment is implemented. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as portable disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, etc.

[0248] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0249] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that can be used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0250] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0251] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0252] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A credit evaluation method, characterized in that: The method comprises: Obtaining a target credit score of a second user associated with the first user in the industrial chain; Acquire transaction flow data between the first user and the second user in the industrial chain; Determine a first influence factor of the second user on the first user based on a first preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data in all transaction flow data of the first user; Determining the associated credit of the second user to the first user based on the first impact factor and the target credit score of the second user; determining a target credit score of the first user based on the associated credit and the credit score of the first user; the credit score of the first user comprising a credit score determined based on a credit evaluation model; The second users include core users of the industry chain and non-core users of the industry chain; In the case where the second user includes a core user of the industrial chain, the step of obtaining a target credit score of the second user associated with the first user in the industrial chain specifically includes: determining the credit score of the second user determined by the credit evaluation model as a target credit score of the second user; In the case where the second user includes a non-core user of the industrial chain, the step of obtaining a target credit score of the second user associated with the first user in the industrial chain specifically includes: Determining a target credit score of a third user associated with the second user based on the target credit score of the core user of the industry chain; Determining the associated credit of the third user to the second user based on the second influencing factor and the target credit score of the third user; the second influencing factor is determined according to the first preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user; Based on the associated credit and the credit score of the second user, a target credit score of the second user is determined; the credit score of the second user includes a credit score determined based on a credit evaluation model.

2. The method according to claim 1, characterized in that: The transaction flow data includes at least one of logistics, capital flow or information flow data; The obtaining of the transaction flow data between the first user and the second user in the industrial chain specifically includes: Based on the knowledge graph corresponding to the preset industrial chain, at least one of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain is determined.

3. The method according to claim 2, characterized in that Before determining at least one of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain based on the knowledge graph corresponding to the preset industrial chain, the method further includes: The knowledge graph is constructed based on the logistics, capital flow or information flow data on the industrial chain stored on the blockchain.

4. The method according to claim 1 or 2, characterized in that: The determining the first influence factor of the second user on the first user based on the first preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data in all transaction flow data of the first user specifically includes: Determine the flow direction of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain and the proportion of the logistics, capital flow or information flow data of the first user and the second user in the industrial chain in all the logistics, capital flow or information flow data of the first user based on graph theory technology; A first influence factor of the second user on the first user is determined based on a first preset rule, the flow direction of logistics, capital flow or information flow data on the industrial chain, and the proportion.

5. The method according to claim 1, characterized in that The credit score determined based on the credit evaluation model specifically includes: At least one of the investment data of users outside the industrial chain and the first user, the government affairs data of the first user, public opinion data, and the credit evaluation score of a financial institution is input into the credit evaluation model to obtain the credit score of the first user.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining a target risk score for the second user; Determine a third influence factor of the second user on the first user based on a second preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data in all transaction flow data of the first user; Determining an associated risk of the second user to the first user based on the third impact factor and the target risk score of the second user; Based on the associated risk and the risk score of the first user, a target risk score of the first user is determined; the risk score of the first user includes a risk score determined based on a risk assessment model.

7. The method according to claim 6, characterized in that The method further includes: in the case where the second user includes a core user of the industrial chain, obtaining a target risk score of the second user associated with the first user in the industrial chain specifically includes: determining the risk score of the second user determined by the risk assessment model as a target risk score of the second user; In the case where the second user includes a non-core user of the industrial chain, the step of obtaining a target credit score of the second user associated with the first user in the industrial chain specifically includes: Determine the target risk score of the third user associated with the second user based on the target risk score of the core user of the industrial chain; determining the associated credit of the third user to the second user based on the fourth influencing factor and the target credit score of the third user; the second influencing factor is determined according to the second preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user; Based on the associated risk and the risk score of the second user, a target risk score of the second user is determined; the risk score of the second user includes a risk score determined based on a risk assessment model.

8. The method according to claim 6, characterized in that The risk score determined based on the risk assessment model specifically includes: The first user's government affairs data, public opinion data, asset data, performance data, operation data and financial institution risk assessment score are input into the risk assessment model to obtain the risk score of the first user.

9. The method according to claim 1 or 6, characterized in that: The method further comprises: Determining a credit reference value of the first user based on a third preset rule and a target credit score of the first user; When the association risk between the second user and the first user is greater than or equal to the credit reference value, a risk warning is issued to the first user.

10. A credit evaluation device, characterized in that: The device comprises: A first acquisition module, used to acquire a target credit score of a second user associated with the first user in the industrial chain; A second acquisition module is used to acquire transaction flow data between the first user and the second user in the industrial chain; A first determining module, configured to determine a first influence factor of the second user on the first user based on a first preset rule, a flow direction of the transaction flow data, and a proportion of the transaction flow data in all transaction flow data of the first user; A second determination module, configured to determine the associated credit of the second user to the first user based on the first impact factor and the target credit score of the second user; A third determination module, configured to determine a target credit score of the first user based on the associated credit and the credit score of the first user; the credit score of the first user includes a credit score determined based on a credit evaluation model; The second users include core users of the industry chain and non-core users of the industry chain; The first acquisition module, when the second user includes a core user of the industrial chain, can be used to determine the credit score of the second user determined by the credit evaluation model as the target credit score of the second user; The first acquisition module, when the second user includes a non-core user of the industrial chain, includes: The first determining unit may be configured to determine a target credit score of a third user associated with the second user based on a target credit score of a core user of the industry chain; The second determination unit may be used to determine the associated credit of the third user to the second user based on the second influencing factor and the target credit score of the third user; the second influencing factor includes the first preset rule, the flow direction of the transaction flow data, and the proportion of the transaction flow data between the second user and the third user in all the transaction flow data of the second user. The third determining unit may be configured to determine a target credit score of the second user based on the associated credit and the credit score of the second user; the credit score of the second user includes a credit score determined based on a credit evaluation model.

11. An electronic device, characterized in that: The device comprises: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the credit evaluation method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the credit evaluation method according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the credit evaluation method as described in any one of claims 1 to 9.

Images