Supply chain checking-based investor and financing party matching method and equipment, and medium

Abstract

The invention relates to the technical field of investment matching, and relates to an investor and financing party matching method and device based on supply chain check, and a medium, and the method comprises the steps: obtaining a financing party data set and an investor data set, carrying out the supply structure analysis of the financing party data set, and obtaining a financing supply chain network set; performing multi-dimensional financing feature extraction and demand risk assessment on the financing party data set to obtain a primary financing risk portrait set; performing topology stability analysis on the financing supply chain network set to obtain a secondary financing risk portrait set, and generating a financing risk portrait set according to the primary financing risk portrait set and the secondary financing risk portrait set; performing investment return analysis on the investor data set to obtain an investment willingness portrait set; and performing dimension association disassembly and portrait matching operation on the financing risk portrait set and the investment willingness portrait set to obtain a capital matching result. According to the invention, the accuracy and efficiency of investment and financing party matching can be improved.

Description

Technical Field

[0001] The present invention relates to the field of investment matching technology, and in particular to a method, device and medium for matching investors and financiers based on supply chain verification. Background Art

[0002] There are a large number of investment and financing needs in the market. The financiers hope to find stable and suitable investors, while the investors hope to find stable and reliable financiers. Therefore, how to accurately match the market investment and financing needs has become an urgent problem to be solved.

[0003] Existing methods for matching investors and financiers are mostly based on traditional rule-based or experience-based matching algorithms, which achieve matching through a single feature clustering method. They are unable to perform personalized matching based on the actual situation of the financier and the investor, and do not take into account the investment preferences of the investor and the risks of the financier, which may lead to low accuracy and efficiency in matching investors and financiers. Summary of the invention

[0004] The present invention provides a method, device and medium for matching investors and financiers based on supply chain verification, the main purpose of which is to solve the problem of low accuracy and efficiency when matching investors and financiers.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for matching investors and financiers based on supply chain verification, comprising:

[0006] Obtaining a financing party data set and an investment party data set, performing supply structure analysis on the financing party data set, and obtaining a financing supply chain network set;

[0007] Extracting multi-dimensional financing features and conducting demand risk assessment on the financing party data set to obtain a primary financing risk portrait set;

[0008] Performing a topological stability analysis on the financing supply chain network set to obtain a secondary financing risk portrait set, and generating a financing risk portrait set based on the primary financing risk portrait set and the secondary financing risk portrait set;

[0009] Performing investment return analysis on the investor data set to obtain an investment intention portrait set;

[0010] The financing risk portrait set and the investment intention portrait set are subjected to dimension association decomposition and portrait matching operations to obtain a capital matching result.

[0011] Optionally, performing supply structure analysis on the financing party data set to obtain a financing supply chain network set includes:

[0012] Selecting the financing party data in the financing party data set one by one as the target financing party data, extracting supply data from the target financing party data, and obtaining target supply data;

[0013] Performing entity detection on the target supply data to obtain a financing entity group;

[0014] Performing association detection on the financing entity group according to the target supply data to obtain supply association information;

[0015] Performing network association on the financing entity group according to the supply association information to obtain a target supply chain network;

[0016] The target supply chain networks of all target financing party data in the financing party data set are aggregated into a financing supply chain network set.

[0017] Optionally, performing network association on the financing entity group according to the supply association information to obtain a target supply chain network includes:

[0018] Performing network node mapping on the financing entity group to obtain an entity node group;

[0019] Using the supply association information, performing an edge association operation on the entity node group to obtain a primary supply chain network;

[0020] Simplifying the primary supply chain network to obtain a standard supply chain network;

[0021] The supply association information is used to perform supply feature mapping on the standard supply chain network to obtain a target supply chain network.

[0022] Optionally, the multi-dimensional financing feature extraction and demand risk assessment are performed on the financing party data set to obtain a primary financing risk portrait set, including:

[0023] Extracting financial features from the financing party data set to obtain a financing financial feature set;

[0024] Extracting transaction features from the financing party data set to obtain a financing transaction feature set;

[0025] Extracting background features from the financing party data set to obtain a financing background feature set;

[0026] Extracting business characteristics from the financing party data set to obtain a financing business characteristic set;

[0027] Performing financing feature fusion on the financing financial feature set, the financing operation feature set, the financing transaction feature set, and the financing background feature set to obtain a financing feature set;

[0028] A risk assessment is performed on the financing feature set to obtain a primary financing risk portrait set.

[0029] Optionally, performing risk assessment on the financing feature set to obtain a primary financing risk portrait set includes:

[0030] Selecting financing features in the financing feature set one by one as target financing features, performing root node feature matching on the target financing features, and obtaining feature gains;

[0031] Perform iterative branch decision on the target financing feature according to the feature gain to obtain a risk leaf node;

[0032] Perform risk labeling on the target financing characteristics according to the risk leaf nodes to obtain a primary risk profile;

[0033] The primary risk profiles of all target financing characteristics in the financing characteristic set are collected into a primary financing risk profile set.

[0034] Optionally, performing a topological stability analysis on the financing supply chain network set to obtain a secondary financing risk portrait set includes:

[0035] Selecting financing supply chain networks in the financing supply chain network set one by one as target supply chain networks, performing topological key node analysis on the target supply chain networks, and obtaining a target network node group;

[0036] Performing path identification on the target supply chain network according to the target network node group to obtain a target network path;

[0037] Performing risk factor analysis on the target network path to obtain target risk factors;

[0038] Conduct stability analysis on the target risk factors to obtain a secondary risk profile;

[0039] The secondary risk profiles of all target supply chain networks in the financing supply chain network set are collected into a secondary financing risk profile set.

[0040] Optionally, performing topological key node analysis on the target supply chain network to obtain a target network node group includes:

[0041] Extracting nodes from the target supply network to obtain a physical node group;

[0042] Performing in-and-out degree statistics on the entity node group according to the target supply network to obtain a network node degree group;

[0043] Perform path overlap statistics on the entity node group according to the target supply network to obtain a node betweenness group;

[0044] Performing path length statistics on the entity node group according to the target supply network to obtain a node distance group;

[0045] The node criticality group corresponding to the entity node group is calculated according to the network node degree group, the node betweenness group and the node distance group using the following criticality analysis algorithm:

[0046]

[0047] Among them, E i is the i-th node criticality in the node criticality group, D i is the i-th network node degree in the network node degree group, C i is the betweenness of the ith node in the node betweenness array, γ is the preset adversarial coefficient, J i is the i-th node distance in the node distance group;

[0048] The entity node group is threshold screened according to the node criticality group to obtain a target network node group.

[0049] Optionally, performing investment return analysis on the investor data set to obtain an investment intention portrait set includes:

[0050] Extracting returns from the investor data set to obtain an expected return feature set;

[0051] Performing investment structure analysis on the investor data set to obtain an investment structure feature set;

[0052] A preference evaluation is performed on the expected return feature set and the investment structure feature set to obtain an investment intention portrait set.

[0053] Optionally, performing dimension association decomposition and portrait matching operations on the financing risk portrait set and the investment intention portrait set to obtain a capital matching result includes:

[0054] Performing feature standardization on the financing risk portrait set to obtain a standard financing feature set, and performing feature standardization on the investment intention portrait set to obtain a standard investment feature set;

[0055] The standard financing feature set and the standard investment feature set are combined into a standard financing and investment feature set, and covariance calculation is performed on the standard financing and investment feature set to obtain a standard covariance feature matrix;

[0056] Performing eigenvalue decomposition on the standard covariance characteristic matrix to obtain standard eigenvalues;

[0057] Performing principal component screening on the standard financing and investment feature set according to the standard feature values ​​to obtain a disassembled financing feature set and a disassembled investment feature set;

[0058] The matching degree between the disassembly financing feature set and the disassembly investment feature set is calculated using the following correlation matching formula:

[0059]

[0060] Among them, R xj,yk is the matching degree between the jth disassembly financing feature in the disassembly financing feature set and the kth disassembly investment feature in the disassembly investment feature set, con() is the covariance symbol, x j refers to the jth dismantling financing feature in the dismantling financing feature set, y k refers to the kth dismantling investment feature in the dismantling investment feature set, t is the feature sequence number, M is the number of features in the dismantling financing feature set, N is the number of features in the dismantling investment feature set, x t refers to the t-th dismantling financing feature in the dismantling financing feature set, y t refers to the t-th dismantling investment feature in the dismantling investment feature set, It refers to the mean feature of the disassembled financing feature set. It refers to the mean characteristic of the disassembled investment characteristic set;

[0061] According to all the matching degrees, the financing risk portrait set and the investment intention portrait set are matched to obtain the capital matching result.

[0062] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein:

[0063] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned method for matching investors and financiers based on supply chain verification.

[0064] In order to solve the above problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method for matching investors and financiers based on supply chain verification.

[0065] The embodiment of the present invention obtains a financing supply chain network set by performing supply structure analysis on the financing party data set, and can extract the supply chain structure of each financing party from the financing party data set, which can assist in judging the risks faced by each financing party, thereby improving the accuracy of subsequent risk portraits. By performing multi-dimensional financing feature extraction and demand risk assessment on the financing party data set, a primary financing risk portrait set is obtained, and a multi-level risk assessment of the financing party can be performed based on the financing party's finance, transaction, market environment, and business trends, thereby improving the accuracy of subsequent matching between investors and financiers. By performing topological stability analysis on the financing supply chain network set, a risk analysis of the supply chain stability of each financing party can be achieved, thereby improving the comprehensiveness of the risk assessment of the financing risk portrait set.

[0066] By performing investment return analysis on the investor data set, the investment intention portrait set can be obtained to analyze the preferences and risk tolerance of each investor for different types of investment, thereby improving the accuracy of subsequent matching. By performing dimensional association decomposition and portrait matching operations on the financing risk portrait set and the investment intention portrait set, multi-dimensional matching verification of the financing party and the investor portrait can be achieved to improve the matching accuracy. Therefore, the investment and financing party matching method, equipment and medium based on supply chain verification proposed in the present invention can solve the problem of low accuracy and efficiency in matching investment and financing parties. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A schematic diagram of a flow chart of a method for matching investors and financiers based on supply chain verification provided by an embodiment of the present invention;

[0068] Figure 2 A schematic diagram of a process for generating a target supply chain network provided by an embodiment of the present invention;

[0069] Figure 3 A schematic diagram of a process for generating a primary financing risk profile set provided by an embodiment of the present invention;

[0070] Figure 4 A functional module diagram of an investment and financing party matching system based on supply chain verification provided by an embodiment of the present invention;

[0071] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0072] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0073] The embodiment of the present application provides a method for matching investors and financiers based on supply chain verification. The execution subject of the method for matching investors and financiers based on supply chain verification includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for matching investors and financiers based on supply chain verification can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0074] Reference Figure 1 FIG. 1 is a flow chart of a method for matching investors and financiers based on supply chain verification according to an embodiment of the present invention. In this embodiment, the method for matching investors and financiers based on supply chain verification includes:

[0075] S1. Obtain a financing party data set and an investment party data set, perform supply structure analysis on the financing party data set, and obtain a financing supply chain network set.

[0076] In an embodiment of the present invention, each financing party data in the financing party data set corresponds to data such as supply chain data, financial data, business data, and historical transaction data of a financing party, and each investor data in the investor data set corresponds to data such as investment structure, risk preference, return expectation, and capital flow of an investor. The financing party data set and the investor data set can be obtained through the database provided by the financing party and the investor.

[0077] In detail, the supply structure analysis is performed on the financing party data set to obtain a financing supply chain network set, including:

[0078] Selecting the financing party data in the financing party data set one by one as the target financing party data, extracting supply data from the target financing party data, and obtaining target supply data;

[0079] Performing entity detection on the target supply data to obtain a financing entity group;

[0080] Performing association detection on the financing entity group according to the target supply data to obtain supply association information;

[0081] Performing network association on the financing entity group according to the supply association information to obtain a target supply chain network;

[0082] The target supply chain networks of all target financing party data in the financing party data set are aggregated into a financing supply chain network set.

[0083] Specifically, the target supply data refers to the data related to the supply chain in the target financing party data, including supplier information, partner information, product information, logistics information, etc. The supply data can be extracted using a keyword matching method.

[0084] In detail, the entity detection refers to extracting the supply entity organizations in the target supply data, and the entity detection can be performed using keyword matching or attribute matching methods. Each financing entity in the financing entity group represents an entity organization that has a supply relationship with the financing party corresponding to the target supply data. The association detection refers to extracting the association information between each financing entity in the financing entity group in the target data, and the association detection can be performed using text mining or data item matching methods.

[0085] Specifically, refer to Figure 2 As shown, the network association of the financing entity group is performed according to the supply association information to obtain a target supply chain network, including:

[0086] S21, performing network node mapping on the financing entity group to obtain an entity node group;

[0087] S22, performing an edge association operation on the entity node group using the supply association information to obtain a primary supply chain network;

[0088] S23, simplifying the primary supply chain network to obtain a standard supply chain network;

[0089] S24. Use the supply association information to perform supply feature mapping on the standard supply chain network to obtain a target supply chain network.

[0090] In detail, the network node mapping refers to taking the financing party in the financing entity group as the network center node, and the remaining financing entities in the financing entity group as the nodes of the network, and the edge association is to select the association information in the supply association information one by one as the target association information, and select the two entity nodes corresponding to the target association information from the entity node group as the target entity node pair, and add a node edge between the target entity node pair.

[0091] Specifically, the network simplification refers to generating the minimum network of the primary supply chain network using a topological algorithm, and the supply feature mapping refers to extracting the supply features of each associated information from the supply associated information, and mapping the supply features to the corresponding edges of the standard supply chain network, wherein the supply features include transaction frequency, transaction amount, transaction duration and other features.

[0092] In an embodiment of the present invention, by performing supply structure analysis on the financing party data set to obtain a financing supply chain network set, the supply chain structure of each financing party can be extracted from the financing party data set, which can assist in determining the risks faced by each financing party, thereby improving the accuracy of subsequent risk profiling.

[0093] S2. Extract multi-dimensional financing features and conduct demand risk assessment on the financing party data set to obtain a primary financing risk portrait set.

[0094] In an embodiment of the present invention, each primary risk profile in the primary financing risk portrait set is used to describe the characteristic description semantics of the financing risk and financing demand of each financing party data in the financing party data set, including whether there is risk in the financing financial characteristics, financing operation characteristics, financing transaction characteristics and financing background characteristics in the financing characteristics, the reason for the existence of risk and the level of risk.

[0095] In detail, the multi-dimensional financing feature extraction and demand risk assessment are performed on the financing party data set to obtain a primary financing risk portrait set, including:

[0096] Extracting financial features from the financing party data set to obtain a financing financial feature set;

[0097] Extracting transaction features from the financing party data set to obtain a financing transaction feature set;

[0098] Extracting background features from the financing party data set to obtain a financing background feature set;

[0099] Extracting business characteristics from the financing party data set to obtain a financing business characteristic set;

[0100] Performing financing feature fusion on the financing financial feature set, the financing operation feature set, the financing transaction feature set, and the financing background feature set to obtain a financing feature set;

[0101] A risk assessment is performed on the financing feature set to obtain a primary financing risk portrait set.

[0102] Specifically, the keyword matching method can be used to extract financial features, transaction features, background features and operating features. The transaction feature extraction refers to extracting features such as transaction frequency and transaction amount from the transaction data of each financing party. The background feature extraction refers to extracting features such as market competition and industry development trends from the background data of each financing party. The financial feature extraction refers to extracting features such as total assets, liabilities, net assets and cash flow from the financial data of each financing party. The financing and operation feature extraction refers to extracting features such as historical credit reports, credit scores, operating income, profits and market share related to operations in each financing data.

[0103] Specifically, refer to Figure 3 As shown, the risk assessment is performed on the financing feature set to obtain a primary financing risk portrait set, including:

[0104] S31, selecting financing features in the financing feature set one by one as target financing features, performing root node feature matching on the target financing features, and obtaining feature gains;

[0105] S32, performing iterative branch decision on the target financing feature according to the feature gain to obtain a risk leaf node;

[0106] S33, performing risk labeling on the target financing characteristics according to the risk leaf nodes to obtain a primary risk profile;

[0107] S34. The primary risk profiles of all target financing characteristics in the financing characteristic set are assembled into a primary financing risk profile set.

[0108] In detail, the financing feature fusion method can be a feature splicing and merging method or an attention weighted fusion algorithm, and a pre-trained decision tree or decision forest model can be used to perform root node feature matching and iterative branch decision on the financing feature set.

[0109] In an embodiment of the present invention, by performing multi-dimensional financing feature extraction and demand risk assessment on the financing party data set, a primary financing risk portrait set is obtained, and a multi-level risk assessment of the financing party can be performed based on the financing party's finances, transactions, market environment, and operating trends, thereby improving the accuracy of subsequent matching between investors and financiers.

[0110] S3. Perform a topological stability analysis on the financing supply chain network set to obtain a secondary financing risk portrait set, and generate a financing risk portrait set based on the primary financing risk portrait set and the secondary financing risk portrait set.

[0111] In detail, each secondary risk profile in the secondary financing risk profile set corresponds to the stability characteristic description semantics of each financing supply chain network in the financing supply chain network set.

[0112] In the embodiment of the present invention, the topological stability analysis of the financing supply chain network set is performed to obtain a secondary financing risk portrait set, including:

[0113] Selecting financing supply chain networks in the financing supply chain network set one by one as target supply chain networks, performing topological key node analysis on the target supply chain networks, and obtaining a target network node group;

[0114] Performing path identification on the target supply chain network according to the target network node group to obtain a target network path;

[0115] Performing risk factor analysis on the target network path to obtain target risk factors;

[0116] Conduct stability analysis on the target risk factors to obtain a secondary risk profile;

[0117] The secondary risk profiles of all target supply chain networks in the financing supply chain network set are collected into a secondary financing risk profile set.

[0118] Specifically, the topological key node analysis of the target supply chain network is performed to obtain a target network node group, including:

[0119] Extracting nodes from the target supply network to obtain a physical node group;

[0120] Performing in-and-out degree statistics on the entity node group according to the target supply network to obtain a network node degree group;

[0121] Perform path overlap statistics on the entity node group according to the target supply network to obtain a node betweenness group;

[0122] Performing path length statistics on the entity node group according to the target supply network to obtain a node distance group;

[0123] The node criticality group corresponding to the entity node group is calculated according to the network node degree group, the node betweenness group and the node distance group using the following criticality analysis algorithm:

[0124]

[0125] Among them, E i is the i-th node criticality in the node criticality group, D i is the i-th network node degree in the network node degree group, C iis the betweenness of the ith node in the node betweenness array, γ is the preset adversarial coefficient, J i is the i-th node distance in the node distance group;

[0126] The entity node group is threshold screened according to the node criticality group to obtain a target network node group.

[0127] In detail, the in-degree statistics refer to counting the out-degree and in-degree of each entity node in the entity node group of the target supply network, and aggregating the sum of the out-degree and in-degree as the network node degree into a network node degree group; the path coincidence statistics refer to counting the number of shortest paths of each entity node in the entity node group, and aggregating the number as the node betweenness into a node betweenness group; the path length statistics refer to counting the average shortest path length from each entity node in the entity node group to the remaining nodes, and aggregating the average shortest path length as the node distance into a node distance group.

[0128] In detail, the criticality analysis algorithm can determine the key nodes according to the link degree, propagation importance and closeness of each entity node, thereby improving the accuracy of key node extraction.

[0129] Specifically, generating a financing risk portrait set based on the primary financing risk portrait set and the secondary financing risk portrait set means merging the corresponding primary risk portraits and secondary risk portraits in the primary financing risk portrait set and the secondary financing risk portrait set into a financing risk portrait, and compiling all the financing risk portraits into a financing risk portrait set.

[0130] In the embodiment of the present invention, by performing a topological stability analysis on the financing supply chain network set, risk analysis on the supply chain stability of each financing party can be achieved, thereby improving the comprehensiveness of the risk assessment of the financing risk portrait set.

[0131] S4. Perform investment return analysis on the investor data set to obtain an investment intention portrait set.

[0132] In detail, each investment intention portrait in the investment intention portrait set is used to describe the characteristic description semantics of the investment preference, risk preference, return expectation, etc. of each investor data in the investor data set.

[0133] In the embodiment of the present invention, the investment return analysis is performed on the investor data set to obtain the investment intention portrait set, including:

[0134] Extracting returns from the investor data set to obtain an expected return feature set;

[0135] Performing investment structure analysis on the investor data set to obtain an investment structure feature set;

[0136] A preference evaluation is performed on the expected return feature set and the investment structure feature set to obtain an investment intention portrait set.

[0137] Specifically, each expected return feature in the expected return feature set corresponds to the historical asset yield, risk level, expected growth rate and other features of each investor data in the investor data set; each investment structure feature in the investment structure feature set corresponds to the investment type proportion, investment distribution and other features of each investor data in the investor data set; the preference assessment refers to calculating the degree of preference of each investor data for different asset categories, tolerance for different risk levels, and expectations for expected returns, etc., using methods such as cluster analysis.

[0138] In the embodiment of the present invention, by performing investment return analysis on the investor data set to obtain an investment intention portrait set, the preference and risk tolerance of each investor for different types of investment types can be analyzed, thereby improving the accuracy of subsequent matching.

[0139] S5. Perform dimension association decomposition and portrait matching operations on the financing risk portrait set and the investment intention portrait set to obtain the capital matching result.

[0140] In the embodiment of the present invention, the financing party matching result includes the matching results between each financing party corresponding to the financing risk portrait set and each investment party in the investment intention portrait set.

[0141] In detail, the dimension association decomposition and portrait matching operations are performed on the financing risk portrait set and the investment intention portrait set to obtain the capital matching result, including:

[0142] Performing feature standardization on the financing risk portrait set to obtain a standard financing feature set, and performing feature standardization on the investment intention portrait set to obtain a standard investment feature set;

[0143] The standard financing feature set and the standard investment feature set are combined into a standard financing and investment feature set, and covariance calculation is performed on the standard financing and investment feature set to obtain a standard covariance feature matrix;

[0144] Performing eigenvalue decomposition on the standard covariance characteristic matrix to obtain standard eigenvalues;

[0145] Performing principal component screening on the standard financing and investment feature set according to the standard feature values ​​to obtain a disassembled financing feature set and a disassembled investment feature set;

[0146] The matching degree between the disassembly financing feature set and the disassembly investment feature set is calculated using the following correlation matching formula:

[0147]

[0148] Among them, R xj,yk is the matching degree between the jth disassembly financing feature in the disassembly financing feature set and the kth disassembly investment feature in the disassembly investment feature set, con() is the covariance symbol, x j refers to the jth dismantling financing feature in the dismantling financing feature set, y k refers to the kth dismantling investment feature in the dismantling investment feature set, t is the feature sequence number, M is the number of features in the dismantling financing feature set, N is the number of features in the dismantling investment feature set, x t refers to the t-th dismantling financing feature in the dismantling financing feature set, y t refers to the t-th dismantling investment feature in the dismantling investment feature set, It refers to the mean feature of the disassembled financing feature set. It refers to the mean characteristic of the disassembled investment characteristic set;

[0149] According to all the matching degrees, the financing risk portrait set and the investment intention portrait set are matched to obtain the capital matching result.

[0150] In detail, the feature standardization operation refers to using a standardized formula to set the feature mean of the financing risk portrait set and the investment intention portrait set to 0 and the standard deviation to 1. The principal component screening refers to using the principal component analysis method to screen out features with larger weights for splitting. The correlation matching formula can determine the matching degree of features based on the distribution of features and feature covariance, thereby improving the accuracy of feature matching.

[0151] Specifically, the investment matching refers to selecting a financing risk profile in the financing risk portrait set as the target financing risk profile, taking the financing party corresponding to the target financing risk profile as the target financing party, taking the investment intention portrait in the investment intention portrait set with the greatest matching degree with the target financing risk portrait as the target investment intention portrait, taking the investor corresponding to the target investment intention portrait as the target investor, taking the target financing party and the target investor as matching results, and aggregating all matching results into the investor matching result.

[0152] In the embodiment of the present invention, by performing dimensional association decomposition and portrait matching operations on the financing risk portrait set and the investment intention portrait set, multi-dimensional matching verification of the financing party and the investment party portraits can be achieved, thereby improving the matching accuracy.

[0153] The embodiment of the present invention obtains a financing supply chain network set by performing supply structure analysis on the financing party data set, and can extract the supply chain structure of each financing party from the financing party data set, which can assist in judging the risks faced by each financing party, thereby improving the accuracy of subsequent risk portraits. By performing multi-dimensional financing feature extraction and demand risk assessment on the financing party data set, a primary financing risk portrait set is obtained, and a multi-level risk assessment of the financing party can be performed based on the financing party's finance, transaction, market environment, and business trends, thereby improving the accuracy of subsequent matching between investors and financiers. By performing topological stability analysis on the financing supply chain network set, a risk analysis of the supply chain stability of each financing party can be achieved, thereby improving the comprehensiveness of the risk assessment of the financing risk portrait set.

[0154] By performing investment return analysis on the investor data set, the investment intention portrait set can be obtained to analyze the preferences and risk tolerance of each investor for different types of investment, thereby improving the accuracy of subsequent matching. By performing dimensional association decomposition and portrait matching operations on the financing risk portrait set and the investment intention portrait set, multi-dimensional matching verification of the financing party and the investment party portrait can be achieved to improve the matching accuracy. Therefore, the investment and financing party matching method based on supply chain verification proposed in the present invention can solve the problem of low efficiency in matching investment and financing parties.

[0155] like Figure 4 , which is a functional module diagram of an investor and financier matching system based on supply chain verification provided by an embodiment of the present invention.

[0156] The investment and financing matching system 100 based on supply chain verification of the present invention can be installed in an electronic device. According to the functions implemented, the investment and financing matching system 100 based on supply chain verification can include a supply chain analysis module 101, a demand risk assessment module 102, a supply chain risk assessment module 103, a return analysis module 104 and a portrait matching module 105. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0157] In this embodiment, the functions of each module / unit are as follows:

[0158] The supply chain analysis module 101 is used to obtain a financing party data set and an investment party data set, perform supply structure analysis on the financing party data set, and obtain a financing supply chain network set;

[0159] The demand risk assessment module 102 is used to extract multi-dimensional financing features and conduct demand risk assessment on the financing party data set to obtain a primary financing risk portrait set;

[0160] The supply chain risk assessment module 103 is used to perform topological stability analysis on the financing supply chain network set to obtain a secondary financing risk portrait set, and generate a financing risk portrait set based on the primary financing risk portrait set and the secondary financing risk portrait set;

[0161] The return analysis module 104 is used to perform investment return analysis on the investor data set to obtain an investment intention portrait set;

[0162] The portrait matching module 105 is used to perform dimension association decomposition and portrait matching operations on the financing risk portrait set and the investment intention portrait set to obtain a capital matching result.

[0163] In detail, each module described in the investment and financing party matching system 100 based on supply chain verification in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The same technical means as the method of matching investors and financiers based on supply chain verification described in the previous section can produce the same technical effects, so I will not go into details here.

[0164] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0165] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0166] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0167] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0168] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0169] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or systems stated in the system embodiment can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any specific order.

[0170] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for matching investors and financiers based on supply chain verification, characterized in that: The method comprises: Obtaining a financing party data set and an investment party data set, performing supply structure analysis on the financing party data set, and obtaining a financing supply chain network set; Extracting multi-dimensional financing features and conducting demand risk assessment on the financing party data set to obtain a primary financing risk portrait set; Performing a topological stability analysis on the financing supply chain network set to obtain a secondary financing risk portrait set, and generating a financing risk portrait set based on the primary financing risk portrait set and the secondary financing risk portrait set; Performing investment return analysis on the investor data set to obtain an investment intention portrait set; The financing risk portrait set and the investment intention portrait set are subjected to dimension association decomposition and portrait matching operations to obtain a capital matching result.

2. The method for matching investors and financiers based on supply chain verification as claimed in claim 1, characterized in that: The supply structure analysis is performed on the financing party data set to obtain a financing supply chain network set, including: Selecting the financing party data in the financing party data set one by one as the target financing party data, extracting supply data from the target financing party data, and obtaining target supply data; Performing entity detection on the target supply data to obtain a financing entity group; Performing association detection on the financing entity group according to the target supply data to obtain supply association information; Performing network association on the financing entity group according to the supply association information to obtain a target supply chain network; The target supply chain networks of all target financing party data in the financing party data set are aggregated into a financing supply chain network set.

3. The method for matching investors and financiers based on supply chain verification as claimed in claim 2, characterized in that: The step of performing network association on the financing entity group according to the supply association information to obtain a target supply chain network includes: Performing network node mapping on the financing entity group to obtain an entity node group; Using the supply association information, performing an edge association operation on the entity node group to obtain a primary supply chain network; Simplifying the primary supply chain network to obtain a standard supply chain network; The supply association information is used to perform supply feature mapping on the standard supply chain network to obtain a target supply chain network.

4. The method for matching investors and financiers based on supply chain verification as claimed in claim 1, characterized in that: The multi-dimensional financing feature extraction and demand risk assessment are performed on the financing party data set to obtain a primary financing risk portrait set, including: Extracting financial features from the financing party data set to obtain a financing financial feature set; Extracting transaction features from the financing party data set to obtain a financing transaction feature set; Extracting background features from the financing party data set to obtain a financing background feature set; Extracting business characteristics from the financing party data set to obtain a financing business characteristic set; Performing financing feature fusion on the financing financial feature set, the financing operation feature set, the financing transaction feature set, and the financing background feature set to obtain a financing feature set; A risk assessment is performed on the financing feature set to obtain a primary financing risk portrait set.

5. The method for matching investors and financiers based on supply chain verification as claimed in claim 4, characterized in that: The risk assessment of the financing feature set is performed to obtain a primary financing risk profile set, including: Selecting financing features in the financing feature set one by one as target financing features, performing root node feature matching on the target financing features, and obtaining feature gains; Perform iterative branch decision on the target financing feature according to the feature gain to obtain a risk leaf node; Perform risk labeling on the target financing characteristics according to the risk leaf nodes to obtain a primary risk profile; The primary risk profiles of all target financing characteristics in the financing characteristic set are collected into a primary financing risk profile set.

6. The method for matching investors and financiers based on supply chain verification as claimed in claim 1, characterized in that: The topological stability analysis of the financing supply chain network set is performed to obtain a secondary financing risk portrait set, including: Selecting financing supply chain networks in the financing supply chain network set one by one as target supply chain networks, performing topological key node analysis on the target supply chain networks, and obtaining a target network node group; Performing path identification on the target supply chain network according to the target network node group to obtain a target network path; Performing risk factor analysis on the target network path to obtain target risk factors; Conduct stability analysis on the target risk factors to obtain a secondary risk profile; The secondary risk profiles of all target supply chain networks in the financing supply chain network set are collected into a secondary financing risk profile set.

7. The method for matching investors and financiers based on supply chain verification as claimed in claim 6, characterized in that: The topological key node analysis of the target supply chain network is performed to obtain a target network node group, including: Extracting nodes from the target supply network to obtain a physical node group; Performing in-and-out degree statistics on the entity node group according to the target supply network to obtain a network node degree group; Perform path overlap statistics on the entity node group according to the target supply network to obtain a node betweenness group; Performing path length statistics on the entity node group according to the target supply network to obtain a node distance group; The node criticality group corresponding to the entity node group is calculated according to the network node degree group, the node betweenness group and the node distance group using the following criticality analysis algorithm: Among them, E i is the i-th node criticality in the node criticality group, D i is the i-th network node degree in the network node degree group, C i is the betweenness of the ith node in the node betweenness array, γ is the preset adversarial coefficient, J i is the i-th node distance in the node distance group; The entity node group is threshold screened according to the node criticality group to obtain a target network node group.

8. The method for matching investors and financiers based on supply chain verification as claimed in claim 1, characterized in that: The investment return analysis is performed on the investor data set to obtain an investment intention portrait set, including: Extracting returns from the investor data set to obtain an expected return feature set; Performing investment structure analysis on the investor data set to obtain an investment structure feature set; A preference evaluation is performed on the expected return feature set and the investment structure feature set to obtain an investment intention portrait set.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for matching investors and financiers based on supply chain verification as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for matching investors and financiers based on supply chain verification as described in any one of claims 1 to 8 is implemented.

Images