Financial service full life cycle monitoring and analysis method and system

Abstract

The invention belongs to the technical field of data monitoring and analysis, and discloses a financial service full life cycle monitoring and analysis method and system. The method comprises the following steps: constructing a behavior data analysis model based on a cloud data center according to historical full life cycle behavior data of a plurality of financial products of a financial service platform; based on the financial service platform, encrypting real-time full-life-cycle behavior data of the financial product, and uploading the real-time full-life-cycle behavior data to the cloud data center; based on the cloud data center, decrypting the encrypted real-time full-life-cycle behavior data to obtain decrypted real-time full-life-cycle behavior data; according to the decrypted real-time full-life-cycle behavior data, a behavior data analysis model is used for behavior data analysis, a real-time behavior data analysis result is obtained, and a real-time financial product analysis report is generated. According to the invention, the problems of large analysis workload, poor accuracy, large monitoring cost investment, low efficiency and poor data security in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data monitoring and analysis, and specifically relates to a method and system for monitoring and analyzing the entire life cycle of financial services. Background Art

[0002] With the rapid development of the financial industry, more and more financial service platforms have entered the market. For example, the Hangxin product of the Hangxin platform is an electronic debt certificate that records the accounts receivable in the supply chain and is opened, used and managed on the Hangxin platform. This electronic debt certificate may be part of the supply chain financial instrument, which can help small and medium-sized enterprises better manage capital flow in the supply chain and improve the efficiency of capital use.

[0003] As the types and number of financial products continue to increase, monitoring and analysis of the entire life cycle of financial services has become an important task for the financial industry. Traditional methods for monitoring and analyzing the entire life cycle of financial services mainly rely on manual analysis and judgment, which is labor-intensive and inaccurate. With the explosive growth of data related to financial products, the requirements for computing resources and hardware configuration are getting higher and higher, with high costs and low efficiency. The existing financial service platform has poor data security and is vulnerable to malicious attacks, leading to data leakage. Summary of the invention

[0004] In order to solve the problems of large analysis workload and poor accuracy, high monitoring cost and low efficiency, and poor data security in the prior art, the present invention aims to provide a method and system for monitoring and analyzing the entire life cycle of financial services.

[0005] The technical solution adopted by the present invention is:

[0006] A method for monitoring and analyzing the entire life cycle of financial services, comprising the following steps:

[0007] Based on the cloud data center, a behavioral data analysis model is constructed based on the historical full life cycle behavioral data of several financial products on the financial service platform;

[0008] Based on the financial service platform, the real-time full life cycle behavior data of financial products is encrypted, the encrypted real-time full life cycle behavior data is obtained, and uploaded to the cloud data center;

[0009] Based on the cloud data center, the received encrypted real-time full life cycle behavior data is decrypted to obtain the decrypted real-time full life cycle behavior data;

[0010] Based on the decrypted real-time full-life cycle behavior data, use the behavior data analysis model to perform behavior data analysis, obtain real-time behavior data analysis results, and generate a real-time financial product analysis report.

[0011] Further, the historical full life cycle behavior data is composed of a number of historical cycle stage behavior data, and the historical full life cycle of the historical full life cycle behavior data includes a number of historical cycle stages, and each historical cycle stage corresponds one to one to a historical cycle stage behavior data;

[0012] The real-time full life cycle behavior data is composed of a number of real-time cycle stage behavior data. The real-time full life cycle of the real-time full life cycle behavior data includes a number of real-time cycle stages, and each real-time cycle stage corresponds to a real-time cycle stage behavior data one by one.

[0013] Furthermore, based on the cloud data center, according to the historical full life cycle behavior data of several financial products of the financial service platform, a behavior data analysis model is constructed, including the following steps:

[0014] Based on the cloud data center, collect historical full life cycle behavior data of several financial products on the financial service platform;

[0015] Preprocessing a number of historical full life cycle behavior data to obtain a number of preprocessed historical full life cycle behavior data;

[0016] Perform clustering on some pre-processed historical full life cycle behavior data to obtain some cluster centers and some cluster clusters;

[0017] Based on several pre-processed historical full-life cycle behavior data in the clustering clusters, a deep learning algorithm is used to build a corresponding behavior data analysis model, and all clustering clusters are traversed to obtain several behavior data analysis models.

[0018] Furthermore, the FCM clustering algorithm is used to cluster a number of pre-processed historical full-life cycle behavior data to obtain a number of cluster centers and a number of cluster clusters.

[0019] Furthermore, the behavioral data analysis model is constructed based on the N-RF-MLP-BiLSTM algorithm.

[0020] Furthermore, it also includes: based on a trusted third party, performing key initialization and digital identity authentication on all financial service platforms connected to the cloud data center, generating public-private key pairs and signature information for each financial service platform, returning the private key and signature information in the public-private key pair to the corresponding financial service platform, and publishing the public key in the public-private key pair to the cloud data center.

[0021] Furthermore, based on the financial service platform, the real-time full life cycle behavior data of the financial product is encrypted to obtain the encrypted real-time full life cycle behavior data, and the encrypted data is uploaded to the cloud data center, including the following steps:

[0022] Based on the financial service platform, collect the real-time full life cycle behavior data of any financial product, and encrypt the real-time full life cycle behavior data according to the private key in the public-private key pair of the financial service platform to obtain the encrypted real-time full life cycle behavior data;

[0023] According to the signature information of the financial service platform, the encrypted real-time full life cycle behavior data is signed to obtain the signature data of the encrypted real-time full life cycle behavior data, and the encrypted real-time full life cycle behavior data and signature data are uploaded to the cloud data center.

[0024] Further, based on the cloud data center, the received encrypted real-time full life cycle behavior data is decrypted to obtain the decrypted real-time full life cycle behavior data, including the following steps:

[0025] Based on the cloud data center, a trusted third party is called to verify the signature data. If the signature verification passes, the next step is entered. Otherwise, the corresponding encrypted real-time full life cycle behavior data is intercepted by a firewall.

[0026] The received encrypted real-time full life cycle behavior data is decrypted according to the public key in the public-private key pair to obtain the decrypted real-time full life cycle behavior data.

[0027] Further, based on the decrypted real-time full life cycle behavior data, a behavior data analysis model is used to perform behavior data analysis, obtain real-time behavior data analysis results, and generate a real-time financial product analysis report, including the following steps:

[0028] Obtain the Euclidean distance between the decrypted real-time full-life cycle behavior data and several cluster centers, and obtain the matching behavior data analysis model corresponding to the matching cluster center with the closest Euclidean distance;

[0029] The decrypted real-time full life cycle behavior data is parsed and divided into real-time cycle stage behavior data of N1 real-time cycle stages, where N1 is the total number of real-time cycle stages of the real-time full life cycle behavior data;

[0030] Use the matching behavior data analysis model to extract the real-time cycle stage behavior data features of the real-time cycle stage behavior data;

[0031] Perform feature fusion on N1 real-time periodic stage behavior data features to obtain real-time full life cycle behavior data features;

[0032] Based on the real-time full life cycle behavior data characteristics, behavior data analysis and prediction are carried out to obtain real-time behavior data analysis results;

[0033] Generate real-time financial product analysis reports for financial products based on preset financial product analysis report templates.

[0034] A financial service life cycle monitoring and analysis system, used to implement a financial service life cycle monitoring and analysis method, the system includes a cloud data center, a trusted third party and several financial service platforms, the cloud data center and the trusted third party are respectively connected to the financial service platform in communication, and the cloud data center is connected to the trusted third party in communication;

[0035] The cloud data center is provided with a model building unit, a data decryption unit and a data analysis unit, and the data analysis unit is provided with a behavior data analysis model.

[0036] The beneficial effects of the present invention are:

[0037] The present invention discloses a method and system for monitoring and analyzing the entire life cycle of financial services. By constructing a behavioral data analysis model, it realizes automated and intelligent analysis of real-time full life cycle behavioral data of financial products, can dig out the deep relationship between data features and financial product conditions, improves the efficiency and accuracy of analysis, avoids relying on manpower, reduces manpower cost investment, and reduces workload; a cloud data center is used to uniformly monitor and analyze a number of financial products of a number of financial service platforms, reduces the requirements for computing resources and hardware configuration, is suitable for data analysis scenarios with large data volumes, reduces hardware cost investment, improves monitoring efficiency, strengthens data exchange, and increases data value; an asymmetric encryption algorithm and digital identity authentication technology are combined to improve the security protection level of the cloud data center and the financial service platform, and improve data security.

[0038] Other beneficial effects of the present invention will be further described in the specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flowchart of the financial service full life cycle monitoring and analysis method in the present invention.

[0040] Figure 2 It is a structural block diagram of the financial service full life cycle monitoring and analysis system in the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0042] Embodiment 1:

[0043] like Figure 1 As shown, this embodiment provides a financial service full life cycle monitoring and analysis method, including the following steps:

[0044] S1: Based on the cloud data center, a behavioral data analysis model is constructed based on the historical full life cycle behavioral data of several financial products on the financial service platform, including the following steps:

[0045] S1-1: Based on the cloud data center, collect historical full life cycle behavior data of several financial products on the financial service platform;

[0046] The historical full life cycle behavior data is composed of a number of historical cycle stage behavior data, and the historical full life cycle of the historical full life cycle behavior data includes a number of historical cycle stages, and each historical cycle stage corresponds to a historical cycle stage behavior data one by one;

[0047] In addition to the above-mentioned historical full-life cycle behavior data, relevant data on the full life cycle of financial products can also be collected, including financial product information and financial market data;

[0048] The full life cycle of a financial product includes the following life cycle stages: opening (users create new electronic debt certificates on the financial service platform and record the specific information of their accounts receivable), using (users transfer the electronic debt certificates they hold between other members of the supply chain, or use them to obtain financing), managing (the financial service platform provides tools to manage these electronic debt certificates, including tracking the status, expiration date, repayment status, etc. of the certificates), trading (the financial service platform allows users to buy and sell electronic debt certificates and provides liquidity support), financing (users use the electronic debt certificates as collateral to apply for financing from financial institutions through the financial service platform), and settlement (when accounts receivable expire, the financial service platform provides settlement services to ensure the safety and timely arrival of funds). Different financial products may include at least one, multiple, or all of the above life cycle stages.

[0049] S1-2: Preprocessing a number of historical full life cycle behavior data to obtain a number of preprocessed historical full life cycle behavior data;

[0050] S1-3: Use the Fuzzy C-Means (FCM) clustering algorithm to cluster a number of pre-processed historical full life cycle behavior data to obtain a number of cluster centers and a number of cluster clusters, including the following steps:

[0051] S1-3-1: Use the FCM clustering algorithm to randomly generate fuzzy clustering parameters and several initial cluster centers, and generate the initial membership of several pre-processed historical full life cycle behavior data to several initial cluster centers;

[0052] S1-3-2: According to the current membership degree and the current cluster center, use the Lagrange multiplier method to obtain the merge function value and the change value. If the merge function value is greater than the merge function value threshold, or the change value is greater than the change value threshold, then proceed to the next step. Otherwise, output the final cluster center.

[0053] The formula is:

[0054]

[0055] ΔJ t =J t -J t-1

[0056] In the formula, J t , J t-1 is the combined function value at time t and t-1; ΔJ t is the change value; i' is the characteristic value of the historical full life cycle behavior data after preprocessing of the i'th 'th period; d i'j' is the distance from the i'th preprocessed historical life cycle behavior data to the j'th current cluster center; u i'j' is the current membership of the historical full life cycle behavior data after preprocessing of the i'th cluster to the j'th cluster center; α is a hyperparameter; m is the total number of data; c is the total number of cluster centers; j' is the cluster center indicator; i' is the indicator of the historical full life cycle behavior data after preprocessing; t is the indicator of the number of iterations;

[0057] S1-3-3: Iteratively update the initial membership degree and the initial cluster center to obtain updated membership degree and updated cluster center, and return to the previous step until several final cluster centers are obtained;

[0058] The formula is:

[0059]

[0060] In the formula, is the updated membership of the historical full life cycle behavior data after preprocessing of the i'th cluster center; d i'j' ,d i'k' is the distance from the i'th pre-processed historical full life cycle behavior data to the j'th and k'th updated cluster centers; k' is the cluster center indicator;

[0061]

[0062] In the formula, z j' is the cluster center updated for the j'th cluster; x' i' is the historical life cycle behavior data after preprocessing of the i'th item; is the updated membership of the i'th preprocessed historical full life cycle behavior data to the j'th cluster center;

[0063] S1-3-4: according to the Euclidean distance between each pre-processed historical life cycle behavior data and several final cluster centers, the pre-processed historical life cycle behavior data is divided to obtain several cluster clusters;

[0064] S1-4: Based on several pre-processed historical full-life cycle behavior data in the clusters, use the deep learning algorithm to build the corresponding behavior data analysis model, and traverse all clusters to obtain several behavior data analysis models;

[0065] The behavior data analysis model is constructed based on the N-Random Forest (RF)-Multilayer Perceptron (MLP)-Bidirectional Long Short-Term Memory (BiLSTM) algorithm, where N is the total number of historical cycle stages of the historical full life cycle behavior data, and the behavior data analysis model includes N cycle stage behavior feature extraction modules constructed based on the RF algorithm, a cycle stage behavior feature fusion module constructed based on the MLP algorithm, and a full life cycle behavior data analysis module constructed based on the BiLSTM algorithm. The cycle stage behavior feature fusion module is connected to the N cycle stage behavior feature extraction modules and the full life cycle behavior data analysis module respectively;

[0066] The cycle stage behavior feature extraction module is used for the historical cycle stage behavior data features of the historical cycle stage behavior data. The trained RF structure includes several classification and regression trees (CART), which can screen the key features of the input historical cycle stage behavior data and improve the ability of the historical cycle stage behavior data features to represent the user behavior in the cycle stage.

[0067] The cycle stage behavior feature fusion module performs feature fusion on N historical cycle stage behavior data features to obtain historical full life cycle behavior data features;

[0068] The full life cycle behavior data analysis module is used to perform behavior data analysis and prediction based on the historical full life cycle behavior data characteristics, obtain historical behavior data analysis results, and accurately mine the deep relationship between historical behavior data analysis prediction labels and data characteristics, thereby improving the accuracy of behavior data analysis;

[0069] S1.1: Based on a trusted third party, perform key initialization and digital identity authentication for all financial service platforms connected to the cloud data center, generate a public-private key pair and signature information for each financial service platform, return the private key and signature information in the public-private key pair to the corresponding financial service platform, and publish the public key in the public-private key pair to the cloud data center, including the following steps:

[0070] S1.1-1: Collect the IP addresses, attribute information and platform IDs of all financial service platforms connected to the cloud data center, and send the IP addresses, attribute information and corresponding platform IDs to a trusted third party;

[0071] S1.1-2: Based on a trusted third party and the attribute information of the financial service platform, an asymmetric encryption algorithm is used to generate keys to obtain the corresponding public-private key pair, including the following steps:

[0072] S1.1-2-1: Initialize the key to generate the public parameter GP, master key MSK and initial key PK. The formula is:

[0073]

[0074] Where GP is the public parameter; MSK is the master key; PK is the initial key; a is the integer domain Z p Random numbers; H1, H2, H3, H4, H5, H6, H u All are target hash functions; g, g1, g a are all random numbers that are generators of the cyclic group G; e(g,g) a is a bilinear map of random numbers g;

[0075] S1.1-2-2: Based on the public parameters GP, master key MSK, initial key PK and attribute information V of the financial service platform u , generate the corresponding public-private key pair of the financial service platform, the public-private key pair includes the private key SK u and public key PK u , the formula is:

[0076] SK u = {MSK,V u ,K=g a g ab ,L u =g b ,(K=H3(V u ) b )}

[0077] PK u =g SKu *PK

[0078] In the formula, SK u is the private key of the financial service platform u; b is the integer domain Z p Random number; L u , K is the private key parameter of the financial service platform u; H3 is the target hash function of the public parameter GP; u is the indicator of the financial service platform; MSK is the master key; PK is the initial key; PK u is the public key of the financial service platform u; g b , g a , g ab is the random number of the generator of the cyclic group G; V u The attribute information of the financial service platform u;

[0079] S1.1-3: Perform digital identity authentication based on the private key in the public-private key pair and the corresponding platform ID to obtain the signature information of the corresponding financial service platform. The formula is:

[0080]

[0081] Where k is a random number; K u Registration parameter for the financial service platform u; KID u The registration ID of the financial service platform u; KID u and the corresponding K u The signature information {K u ,KID u}; H1 is the target hash function; ID u SK is the platform ID of the financial service platform u; u The private key of the financial service platform u; is the prime order; P is the base point of the prime domain;

[0082] S1.1-4: According to the IP address, the private key SK in the public-private key pair u And signature information {K u ,KID u}, return to the corresponding financial service platform, and the public key PK in the public-private key pair u Publish to cloud data center;

[0083] S2: Based on the financial service platform, the real-time full life cycle behavior data of financial products is encrypted, the encrypted real-time full life cycle behavior data is obtained, and uploaded to the cloud data center, including the following steps:

[0084] S2-1: Based on the financial service platform, collect the real-time full life cycle behavior data of any financial product, and encrypt the real-time full life cycle behavior data according to the private key in the public-private key pair of the financial service platform to obtain the encrypted real-time full life cycle behavior data;

[0085] The real-time full life cycle behavior data is composed of a number of real-time cycle stage behavior data. The real-time full life cycle of the real-time full life cycle behavior data includes a number of real-time cycle stages, and each real-time cycle stage corresponds to a real-time cycle stage behavior data one by one.

[0086] The formula is:

[0087] M u =E(SK u ,m u )

[0088] Where M u is the encrypted real-time full-life cycle behavior data of the financial service platform u; E(*) is the asymmetric encryption function; m u Real-time full life cycle behavior data for the financial service platform u; SK u is the private key of the financial service platform u; u is the indicator amount of the financial service platform;

[0089] S2-2: Sign the encrypted real-time full life cycle behavior data according to the signature information of the financial service platform to obtain the signature data of the encrypted real-time full life cycle behavior data, and upload the encrypted real-time full life cycle behavior data and signature data to the cloud data center;

[0090] The formula is:

[0091]

[0092] In the formula, r is a random number; is the prime order; P is the base point of the prime domain; H2 is the target hash function; K u Registration parameters for the financial service platform u; KID u is the registration ID of the financial service platform u; ID u is the entity ID of the financial service platform u; the signature data is {ID u ,M u ,γ'={K u ,R u ,B u}}; R u ,B u ,γ' are the signature parameters of the financial service platform u;

[0093] S3: Based on the cloud data center, the received encrypted real-time full life cycle behavior data is decrypted to obtain the decrypted real-time full life cycle behavior data, including the following steps:

[0094] S3-1: Based on the cloud data center, call a trusted third party to verify the signature data. If the signature verification passes, proceed to the next step. Otherwise, use the firewall to intercept the corresponding encrypted real-time full life cycle behavior data.

[0095] The formula is:

[0096] β u B u P=β u H2(R u ,M u ,ID u ,K u )R u +β u K u +β u H1(ID u ,K u )PK u

[0097] In the formula, β u PK is the signature authentication parameter of the financial service platform u; u is the public key of the financial service platform u; if the left formula is equal to the right formula, the signature authentication is successful;

[0098] S3-2: decrypting the received encrypted real-time full life cycle behavior data according to the public key in the public-private key pair to obtain the decrypted real-time full life cycle behavior data;

[0099] The formula is:

[0100] m' u =E - (PK u ,M u )

[0101] In the formula, m' u The decrypted real-time full life cycle behavior data of the financial service platform u; E - (*) is an asymmetric decryption function; PK u is the public key of the financial service platform u; M u It is the encrypted real-time full life cycle behavior data of the financial service platform u;

[0102] S4: Based on the decrypted real-time full-life cycle behavior data, use the behavior data analysis model to perform behavior data analysis, obtain real-time behavior data analysis results, and generate a real-time financial product analysis report, including the following steps:

[0103] S4-1: Obtain the Euclidean distance between the decrypted real-time full-life cycle behavior data and several cluster centers, and obtain the matching behavior data analysis model corresponding to the matching cluster center with the closest Euclidean distance;

[0104] S4-2: parsing the decrypted real-time full life cycle behavior data to divide it into real-time cycle stage behavior data of N1 real-time cycle stages, where N1 is the total number of real-time cycle stages of the real-time full life cycle behavior data;

[0105] S4-3: using the cycle phase behavior feature extraction module of the matching behavior data analysis model to extract the real-time cycle phase behavior data features of the real-time cycle phase behavior data;

[0106] S4-3-1: Use the RF structure trained in the periodic stage behavior feature extraction module of the matching behavior data analysis model to extract the feature contribution of several candidate features of the real-time periodic stage behavior data in the real-time periodic stage behavior data;

[0107] The formula is:

[0108]

[0109] In the formula, is the feature contribution of the jth candidate feature; is the feature contribution of the jth candidate feature in the i-th CART tree; i and j are the indicator quantities of the candidate features; n is the total number of CART trees;

[0110]

[0111] In the formula, GI m GI l GI r is the Gini index of CART tree node m', node l and node r'; p m'k" is the proportion of category k" in CART tree node m'; K is the total number of categories; m', l, r' are all node indicators; M is the total number of CART tree nodes; k" is the category indicator;

[0112] S4-3-2: normalizing the feature contributions of several candidate features to obtain corresponding normalized feature contributions;

[0113] The formula is:

[0114]

[0115] Where VIM j is the contribution of the feature after normalization; J is the total number of candidate features;

[0116] S4-3-3: Generate feature selection standard values ​​for several candidate features based on the normalized feature contribution;

[0117] The formula is:

[0118]

[0119] In the formula, CFC j The feature selection standard value for the jth candidate feature; VIM c' is the normalized feature contribution of the c'th candidate feature; c' is the indicator of the candidate feature;

[0120] S4-3-4: According to the feature selection standard value, a number of candidate features of real-time cycle stage behavior data are sorted in descending order, and the first M' candidate features of real-time cycle stage behavior data are selected as key features of real-time cycle stage behavior data, where M' is the total number of key features;

[0121] S4-3-5: combining M' real-time period stage behavior data key features to obtain real-time period stage behavior data features of the real-time period stage behavior data;

[0122] S4-3-6: traverse N1 real-time cycle stage behavior data to obtain N1 real-time cycle stage behavior data features;

[0123] S4-4: Use the cycle stage behavior feature fusion module to fuse the N1 real-time cycle stage behavior data features to obtain real-time full life cycle behavior data features;

[0124] S4-5: Use the full life cycle behavior data analysis module to perform behavior data analysis and prediction based on the real-time full life cycle behavior data characteristics to obtain real-time behavior data analysis results;

[0125] S4-6: Generate a real-time financial product analysis report for the financial product based on the preset financial product analysis report template.

[0126] Embodiment 2:

[0127] like Figure 2 As shown, this embodiment provides a financial service life cycle monitoring and analysis system, which is used to implement a financial service life cycle monitoring and analysis method. The system includes a cloud data center, a trusted third party, and several financial service platforms. The cloud data center and the trusted third party are respectively connected to the financial service platform in communication, and the cloud data center is connected to the trusted third party in communication;

[0128] A trusted third party for key initialization and digital identity authentication for all financial service platforms connected to the cloud data center;

[0129] The financial service platform is used to provide a number of financial products; encrypt the real-time full life cycle behavior data of financial products, obtain the encrypted real-time full life cycle behavior data, and upload it to the cloud data center;

[0130] The cloud data center is provided with a model building unit, a data decryption unit and a data analysis unit, and the data analysis unit is provided with a behavior data analysis model;

[0131] A model building unit, used to build a behavior data analysis model based on the historical full life cycle behavior data of several financial products on the financial service platform;

[0132] A data decryption unit, used to decrypt the received encrypted real-time full life cycle behavior data to obtain the decrypted real-time full life cycle behavior data;

[0133] The data analysis unit is used to perform behavioral data analysis based on the decrypted real-time full life cycle behavioral data using a behavioral data analysis model, obtain real-time behavioral data analysis results, and generate a real-time financial product analysis report.

[0134] The present invention discloses a method and system for monitoring and analyzing the entire life cycle of financial services. By constructing a behavioral data analysis model, it realizes automated and intelligent analysis of real-time full life cycle behavioral data of financial products, can dig out the deep relationship between data features and financial product conditions, improves the efficiency and accuracy of analysis, avoids relying on manpower, reduces manpower cost investment, and reduces workload; a cloud data center is used to uniformly monitor and analyze a number of financial products of a number of financial service platforms, reduces the requirements for computing resources and hardware configuration, is suitable for data analysis scenarios with large data volumes, reduces hardware cost investment, improves monitoring efficiency, strengthens data exchange, and increases data value; an asymmetric encryption algorithm and digital identity authentication technology are combined to improve the security protection level of the cloud data center and the financial service platform, and improve data security.

[0135] The present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.

Claims

1. A method for monitoring and analyzing the entire life cycle of financial services, characterized by: The steps include: Based on the cloud data center, a behavioral data analysis model is constructed based on the historical full life cycle behavioral data of several financial products on the financial service platform; Based on the financial service platform, the real-time full life cycle behavior data of financial products is encrypted, the encrypted real-time full life cycle behavior data is obtained, and uploaded to the cloud data center; Based on the cloud data center, the received encrypted real-time full life cycle behavior data is decrypted to obtain the decrypted real-time full life cycle behavior data; Based on the decrypted real-time full-life cycle behavior data, use the behavior data analysis model to perform behavior data analysis, obtain real-time behavior data analysis results, and generate a real-time financial product analysis report.

2. A method for monitoring and analyzing the entire life cycle of financial services according to claim 1, characterized in that: The historical full life cycle behavior data is composed of a number of historical cycle stage behavior data, and the historical full life cycle of the historical full life cycle behavior data includes a number of historical cycle stages, and each of the historical cycle stages corresponds to a historical cycle stage behavior data one by one; The real-time full life cycle behavior data is composed of a number of real-time cycle stage behavior data. The real-time full life cycle of the real-time full life cycle behavior data includes a number of real-time cycle stages, and each of the real-time cycle stages corresponds to a real-time cycle stage behavior data.

3. A method for monitoring and analyzing the entire life cycle of financial services according to claim 2, characterized in that: Based on the cloud data center, a behavioral data analysis model is constructed based on the historical full life cycle behavioral data of several financial products on the financial service platform, including the following steps: Based on the cloud data center, collect historical full life cycle behavior data of several financial products on the financial service platform; Preprocessing a number of historical full life cycle behavior data to obtain a number of preprocessed historical full life cycle behavior data; Perform clustering on some pre-processed historical full life cycle behavior data to obtain some cluster centers and some cluster clusters; Based on several pre-processed historical full-life cycle behavior data in the clustering clusters, a deep learning algorithm is used to build a corresponding behavior data analysis model, and all clustering clusters are traversed to obtain several behavior data analysis models.

4. A method for monitoring and analyzing the entire life cycle of financial services according to claim 3, characterized in that: The FCM clustering algorithm is used to cluster several pre-processed historical full-life cycle behavior data to obtain several cluster centers and several cluster clusters.

5. A method for monitoring and analyzing the entire life cycle of financial services according to claim 3, characterized in that: The behavioral data analysis model is built based on the N-RF-MLP-BiLSTM algorithm.

6. A method for monitoring and analyzing the entire life cycle of financial services according to claim 1, characterized in that: Also includes: Based on a trusted third party, key initialization and digital identity authentication are performed on all financial service platforms connected to the cloud data center, and public-private key pairs and signature information are generated for each financial service platform. The private key and signature information in the public-private key pair are returned to the corresponding financial service platform, and the public key in the public-private key pair is published to the cloud data center.

7. A method for monitoring and analyzing the entire life cycle of financial services according to claim 6, characterized in that: Based on the financial service platform, the real-time full life cycle behavior data of financial products is encrypted, the encrypted real-time full life cycle behavior data is obtained, and uploaded to the cloud data center, including the following steps: Based on the financial service platform, collect the real-time full life cycle behavior data of any financial product, and encrypt the real-time full life cycle behavior data according to the private key in the public-private key pair of the financial service platform to obtain the encrypted real-time full life cycle behavior data; According to the signature information of the financial service platform, the encrypted real-time full life cycle behavior data is signed to obtain the signature data of the encrypted real-time full life cycle behavior data, and the encrypted real-time full life cycle behavior data and signature data are uploaded to the cloud data center.

8. A method for monitoring and analyzing the entire life cycle of financial services according to claim 7, characterized in that: Based on the cloud data center, the received encrypted real-time full life cycle behavior data is decrypted to obtain the decrypted real-time full life cycle behavior data, including the following steps: Based on the cloud data center, a trusted third party is called to verify the signature data. If the signature verification passes, the next step is entered. Otherwise, the corresponding encrypted real-time full life cycle behavior data is intercepted by a firewall. The received encrypted real-time full life cycle behavior data is decrypted according to the public key in the public-private key pair to obtain the decrypted real-time full life cycle behavior data.

9. A method for monitoring and analyzing the entire life cycle of financial services according to claim 5, characterized in that: According to the decrypted real-time full life cycle behavior data, the behavior data analysis model is used to perform behavior data analysis, obtain real-time behavior data analysis results, and generate a real-time financial product analysis report, including the following steps: Obtain the Euclidean distance between the decrypted real-time full-life cycle behavior data and several cluster centers, and obtain the matching behavior data analysis model corresponding to the matching cluster center with the closest Euclidean distance; The decrypted real-time full life cycle behavior data is parsed and divided into real-time cycle stage behavior data of N1 real-time cycle stages, where N1 is the total number of real-time cycle stages of the real-time full life cycle behavior data; Use the matching behavior data analysis model to extract the real-time cycle stage behavior data features of the real-time cycle stage behavior data; Perform feature fusion on N1 real-time periodic stage behavior data features to obtain real-time full life cycle behavior data features; Based on the real-time full life cycle behavior data characteristics, behavior data analysis and prediction are carried out to obtain real-time behavior data analysis results; Generate real-time financial product analysis reports for financial products based on preset financial product analysis report templates.

10. A financial service life cycle monitoring and analysis system, used to implement the financial service life cycle monitoring and analysis method according to any one of claims 1 to 9, characterized in that: The system includes a cloud data center, a trusted third party, and several financial service platforms, wherein the cloud data center and the trusted third party are respectively connected to the financial service platform in communication, and the cloud data center is connected to the trusted third party in communication; The cloud data center is provided with a model building unit, a data decryption unit and a data analysis unit, and the data analysis unit is provided with a behavior data analysis model.

Images