CN113435770A - Transaction risk assessment method and device based on block chain - Google Patents
Transaction risk assessment method and device based on block chain Download PDFInfo
- Publication number
- CN113435770A CN113435770A CN202110768964.0A CN202110768964A CN113435770A CN 113435770 A CN113435770 A CN 113435770A CN 202110768964 A CN202110768964 A CN 202110768964A CN 113435770 A CN113435770 A CN 113435770A
- Authority
- CN
- China
- Prior art keywords
- risk
- early warning
- block chain
- transaction
- financial institution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Abstract
The invention discloses a transaction risk assessment method and a transaction risk assessment device based on a block chain, which relate to the technical field of the block chain, and the method comprises the following steps: extracting the risk type of the target client according to the historical risk data of the target client, and storing the extracted risk type on the block chain network; when a business transaction request of a target customer at any financial institution is received, inquiring the risk type of the target customer from the block chain network, and screening out a risk early warning model corresponding to each risk type from a risk early warning model subset of each financial institution; inputting the real-time transaction data of the target customer into each screened risk early warning model, and outputting a corresponding risk evaluation result; and determining whether to limit the transaction operation of the target client according to the risk type of the target client and the corresponding risk evaluation result by using an intelligent contract configured in advance on the block chain network. The invention can obtain more accurate risk evaluation results and effectively prevent risk business transaction.
Description
Technical Field
The invention relates to the technical field of block chains, in particular to a transaction risk assessment method and device based on a block chain.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The existing bank group usually has dozens of branches, each branch independently develops and uses a risk model of the branch, and the branches are not shared, so that the overall research and development cost of the group is very high, the sharing of a good wind control model in the group is particularly important, the research and development cost of the sub-branches under the group can be saved, an excellent model developed by the identified sub-branches can be used, and the benefit of the group is great. The advantage of unforgeable, public and transparent block chains can make the sharing efficiency of the wind control model higher, namely make the risk control more effective.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a transaction risk assessment method based on a block chain, which is used for solving the technical problem that an existing business system of a financial institution lacks an effective mechanism to control the transaction risk of a client, and comprises the following steps: extracting the risk types of the target client according to the historical risk data of the target client to obtain a risk type set of the target client, and storing the risk type set to a block chain network, wherein the risk type set comprises: one or more risk types; when a business transaction request of a target customer at any financial institution is received, inquiring a risk type set of the target customer from a block chain network, and screening a risk early warning model corresponding to each risk type in the risk type set from a risk early warning model subset of each financial institution, wherein the risk early warning model subset of each financial institution comprises: risk early warning models corresponding to a plurality of risk types; acquiring real-time transaction data of a target customer according to the service transaction request, inputting the real-time transaction data of the target customer into each screened risk early warning model, and outputting a risk evaluation result of each risk early warning model; acquiring a risk early warning identifier of a target client according to a risk type set of the target client and a risk evaluation result of a risk early warning model corresponding to each risk type in the risk type set by using an intelligent contract configured in advance on a block chain network; and determining whether to limit the transaction operation of the target customer according to the risk early warning identification of the target customer.
The embodiment of the invention also provides a transaction risk assessment device based on the block chain, which is used for solving the technical problem that the business system of the existing financial institution lacks an effective mechanism to control the transaction risk of the client, and the device comprises: the block chain data storage module is used for extracting the risk types of the target client according to the historical risk data of the target client to obtain a risk type set of the target client and storing the risk type set to the block chain network, wherein the risk type set comprises: one or more risk types; the risk early warning model selection module is used for inquiring a risk type set of a target client from a block chain network when a business transaction request of the target client at any financial institution is received, and screening a risk early warning model corresponding to each risk type in the risk type set from a risk early warning model subset of each financial institution, wherein the risk early warning model subset of each financial institution comprises: risk early warning models corresponding to a plurality of risk types; the risk assessment module is used for acquiring real-time transaction data of the target client according to the business transaction request, inputting the real-time transaction data of the target client into each screened risk early warning model and outputting a risk assessment result of each risk early warning model; the risk early warning module is used for acquiring a risk early warning identifier of the target client according to the risk type set of the target client and a risk evaluation result of a risk early warning model corresponding to each risk type in the risk type set by using an intelligent contract configured in advance on the block chain network; and the transaction behavior control module is used for determining whether to limit the transaction operation of the target client according to the risk early warning identification of the target client.
The embodiment of the invention also provides computer equipment for solving the technical problem that the business system of the existing financial institution lacks an effective mechanism for controlling the transaction risk of the client.
The embodiment of the invention also provides a computer readable storage medium for solving the technical problem that the business system of the existing financial institution lacks an effective mechanism for controlling the transaction risk of the client, and the computer readable storage medium stores a computer program for executing the transaction risk assessment method based on the block chain.
According to the transaction risk assessment method, device, computer equipment and computer readable storage medium based on the block chain, provided by the embodiment of the invention, after the risk type of a target client is obtained by utilizing historical risk data of the target client, the risk type of the target client is stored in the block chain network, further, based on the risk type of the target client stored in the block chain network, a risk early warning model capable of predicting the corresponding risk type is screened out from a risk early warning model subset of each financial institution, risk early warning is carried out on the target client by utilizing the screened risk early warning model to obtain a risk assessment result of the target client, and finally, whether the transaction operation of the target client is limited or not is determined by utilizing an intelligent contract pre-configured on the block chain network according to the risk assessment result of the target client.
According to the embodiment of the invention, the corresponding risk early warning model is obtained based on the target client risk type set stored in the blockchain network, the risk early warning is carried out on the target client, a more accurate risk evaluation result can be obtained, the transaction behavior of the target client is controlled by using the risk evaluation result, and the risk business transaction can be effectively prevented.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a flowchart of a transaction risk assessment method based on a blockchain according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a transaction risk assessment system based on a blockchain according to an embodiment of the present invention;
FIG. 3 is a flow chart of a machine learning method provided in an embodiment of the present invention;
FIG. 4 is a flow chart of model parameter updating provided in an embodiment of the present invention;
fig. 5 is a flow chart of a block chain network according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a transaction risk assessment apparatus based on a blockchain according to an embodiment of the present invention;
fig. 7 is a flowchart of an alternative transaction risk assessment method based on a blockchain according to an embodiment of the present invention;
fig. 8 is a schematic diagram of a computer device provided in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
The embodiment of the present invention provides a transaction risk assessment method based on a block chain, and fig. 1 is a flow chart of the transaction risk assessment method based on the block chain provided in the embodiment of the present invention, as shown in fig. 1, the method includes:
s101, extracting the risk types of the target client according to the historical risk data of the target client to obtain a risk type set of the target client, and storing the risk type set to a block chain network, wherein the risk type set comprises: one or more risk types.
It should be noted that the blockchain network in the embodiment of the present invention may be a blockchain network constructed by using the business systems of the respective financial institutions as blockchain storage nodes; or a separate blockchain network to which the business systems of the respective financial institutions access through blockchain clients. The business systems of the financial institutions can directly communicate with the blockchain network, so that the business systems of the financial institutions can store the transaction data and the risk data of the clients in the financial institutions onto the blockchain network, and the business systems of any financial institution can inquire the transaction data and the risk data of the target clients in all the financial institutions through the blockchain network.
Optionally, in order to protect data privacy of each financial institution, when the transaction data and risk data of the target customer at each financial institution are stored on the blockchain network, encryption processing may be performed on the transaction data and risk data to be uploaded, for example, digest information of the transaction data and risk data is generated, only the digest information corresponding to the transaction data and risk data is stored on the blockchain network, and encryption processing may also be performed on the transaction data and risk data, and the encrypted transaction data and risk data are stored on the blockchain network.
The risk types extracted in the embodiment of the present invention include, but are not limited to: risk of account theft, risk of illegal funds transfer, risk of customer churn, risk of fraud, risk of default, etc. The risk present may vary from client to client. There may be more than one risk present per customer.
In an embodiment, the transaction risk assessment method based on the blockchain provided in the embodiment of the present invention may further construct a risk type set of the target customer by: extracting the risk types of the similar clients or the associated clients according to historical risk data of the similar clients or the associated clients, wherein the similar clients are clients with similarity to the target clients exceeding a preset threshold value, and the associated clients are clients with association relation with the target clients; and adding the risk types of the similar clients and the associated clients into the risk type set of the target client.
In a specific implementation manner, for the determination of the similar customers, the euclidean distance between the first customer and the second customer can be calculated according to the attribute information of the multiple dimensions of the first customer and the second customer to characterize the similarity of the first customer and the second customer, and the first customer and the second customer with the similarity higher than the preset threshold value are determined as the similar customers. The determination of the associated customer may be that two customers have business transactions, for example, a customer and a target customer have a transfer transaction, and the transfer amount exceeds a preset amount, or the transfer number exceeds a preset number, the customer is determined as the associated customer of the target customer.
S102, when a business transaction request of a target customer at any financial institution is received, inquiring a risk type set of the target customer from the blockchain network, and screening a risk early warning model corresponding to each risk type in the risk type set from a risk early warning model subset of each financial institution, wherein the risk early warning model subset of each financial institution comprises: and the risk early warning models correspond to a plurality of risk types.
It should be noted that each financial institution has a risk early warning model subset, the risk early warning model subset includes multiple risk early warning models, each risk early warning model is used for predicting different risk types, after a corresponding risk early warning model is selected according to each risk type stored by a target customer on a block chain network, the selected risk early warning models can be used for carrying out risk assessment on the target customer, for example, a support vector machine model and a bayesian model are used for predicting default risks, and three deep learning models are used for predicting illegal fund transfer risks.
S103, acquiring real-time transaction data of the target customer according to the business transaction request, inputting the real-time transaction data of the target customer into each screened risk early warning model, and outputting a risk evaluation result of each risk early warning model.
Because the transaction data and the risk data of the target client at each financial institution are stored in the blockchain network, the risk evaluation is performed on the target client by using the transaction data and the risk data of the target client stored in the blockchain network, and a more accurate risk evaluation result can be obtained.
The risk assessment result output in the embodiment of the invention can be whether the target customer has illegal fund transfer risk, whether default risk exists and the probability of risk occurrence.
It should be noted that the risk early warning model in the embodiment of the present invention may be a model that is obtained through machine learning training in advance and can predict the transaction risk of a target customer according to the transaction data and risk data of the target customer at each financial institution.
Optionally, there may be more than one risk early warning model for each financial institution, and the risk early warning models of the financial institutions may be the same or different. When a plurality of risk early warning models of each financial institution are available, the risk early warning models can be integrated through a pre-configured integration algorithm to obtain a more accurate risk early warning model. The machine learning model integration algorithm adopted in the embodiment of the invention includes but is not limited to the following three types: bagging algorithm, Boosting algorithm, and Stacking algorithm.
In specific implementation, different risk early warning models can be obtained through machine learning training aiming at different business transaction scenes, so that the business transaction risk of a customer can be predicted more accurately.
And S104, acquiring a risk early warning identifier of the target client according to the risk type set of the target client and the risk evaluation result of the risk early warning model corresponding to each risk type in the risk type set by using an intelligent contract configured in advance on the block chain network.
It should be noted that, in the embodiment of the present invention, the intelligent contract preconfigured on the blockchain network is a section of program code, and different transaction behaviors of the customer need to be limited for different service scenarios and different service logics, so different intelligent contracts can be configured. And performing risk evaluation on the target client by using the transaction data and the risk data of the target client stored on the blockchain network, and controlling the transaction operation executed by the target client at each financial institution by using an intelligent contract pre-configured on the blockchain network according to the risk evaluation result of the target client.
In the embodiment of the invention, the intelligent contract is configured with various integration algorithms for machine learning, and can synthesize the results of the models and finally obtain a final conclusion: i.e., whether the customer's transaction is at a corresponding risk (e.g., risk of illegal funds transfer, risk of default, etc.).
In the above integration algorithm, the accuracy of each risk early warning model used is evaluated based on a data source common to all financial institution nodes in the block chain, for example, the accuracy may be evaluated based on a data source uploaded by a super node, rather than based on respective data sources of a single financial institution. In this way, the performance of each model can be accurately evaluated, the performance among the models can be objectively evaluated, and the problems that a single financial institution exaggerates or underestimates the performance of the model and the evaluation performance is distorted due to inconsistent evaluation rules are avoided. For example, the transaction early warning model shows that the current transaction of the customer has a risk of illegal fund transfer or a high fraud risk, and the current transaction behavior of the customer should be terminated.
And S105, determining whether to limit the transaction operation of the target client according to the risk early warning identification of the target client.
It should be noted that the transaction risk assessment method based on the blockchain provided in the embodiment of the present invention may be applied to real-time monitoring of transaction behaviors of customers, and may also predict the churn risk of customers in batches, and notify the result to each financial institution (for example, a specific branch line under a certain bank group).
Fig. 2 illustrates a block chain-based transaction risk assessment system provided in an embodiment of the present invention, and as shown in fig. 2, the system includes: a blockchain network and business systems of a plurality of financial institutions (business systems of four financial institutions, respectively financial institution 1, financial institution 2, financial institution 3, and financial institution 4, are shown in fig. 2); the business system of each financial institution is in network communication with the block chain, the business system of each financial institution comprises a plurality of risk early warning models (three risk early warning models are shown in fig. 2, namely a model A, a model B and a model C), and for the business system of each financial institution, the plurality of risk early warning models can be used for independently predicting the business transaction risk of the customer, and also can be used for combining the plurality of risk early warning models to predict the business transaction risk of the customer.
It should be noted that the risk early warning models of the financial institutions in fig. 2 are only examples, and in an actual scenario, the financial institutions may use different numbers of risk early warning models and different types of risk early warning models.
In order to obtain a more accurate risk assessment result, in an embodiment, as shown in fig. 3, the transaction risk assessment method based on the blockchain provided in the embodiment of the present invention may further train and obtain a risk early warning model of each financial institution in different transaction scenarios through the following steps:
s301, acquiring a plurality of pre-configured transaction scenes;
s302, obtaining a risk early warning model subset of each financial institution through machine learning training according to a plurality of pre-configured transaction scenes, wherein the risk early warning model subset of each financial institution comprises: a plurality of risk early warning models for each financial institution under different transaction scenarios.
Optionally, in S302, machine learning is performed on any one of the following models, and a risk early warning model subset of each financial institution is obtained through training: support vector machine model, Bayesian model and neural network model.
In the embodiment, when a business transaction request of a target customer at any financial institution is received, a current business transaction scene is obtained, and according to the current business transaction scene and a risk type set of the target customer stored on a block chain network, a risk early warning model corresponding to a corresponding risk type in the current business transaction scene is screened from risk early warning model subsets of various financial institutions.
Further, in order to improve the generalization ability of the machine learning model, in an embodiment, as shown in fig. 4, the transaction risk assessment method based on the blockchain provided in the embodiment of the present invention may further implement updating of the model parameters by the following steps:
s401, uploading risk assessment results of target clients in each financial institution to a block chain network;
s402, updating parameters of the risk early warning models of the financial machines in different transaction scenes according to risk evaluation results of target customers stored in the blockchain network.
In one embodiment, as shown in fig. 5, the blockchain-based transaction risk assessment method provided in the embodiment of the present invention may construct a blockchain network by:
s501, the business systems of the financial institutions are used as block chain storage nodes to construct a block chain network, wherein the block chain data are stored in the block chain storage nodes in the block chain network based on a consensus algorithm.
In one embodiment, as shown in fig. 5, after building a blockchain network by using business systems of respective financial institutions as blockchain storage nodes, the method for assessing transaction risk based on blockchain provided in an embodiment of the present invention further includes:
s502, acquiring risk types, risk early warning model method types, risk early warning model numbers, transaction scenes corresponding to the risk early warning models and model accuracy rates of the risk early warning models of the financial institutions, wherein different method types correspond to different model training methods;
and S503, determining or updating the weight value of the block chain storage node corresponding to each financial institution in the consensus algorithm according to the risk type, the risk early warning model method type, the number of the risk early warning models, the transaction scene corresponding to each risk early warning model and the model accuracy of each risk early warning model.
In the embodiment of the invention, the weight value of the block chain storage node corresponding to each financial institution in the consensus algorithm is determined or updated according to the risk type of each financial institution, the risk early warning model method category, the number of risk early warning models, the transaction scene corresponding to each risk early warning model and the model accuracy of each risk early warning model, so that each data storage node in the block chain network can reach consensus more quickly, and the data storage efficiency of the block chain network is improved. For example, it is set up that: for each combination of different scenes and risk types, selecting a model with the highest early warning accuracy for each model early warning method to form a model set, namely, each combination of different scenes and risk types corresponds to one model set, then calculating the accuracy sum of the risk early warning models with the accuracy larger than a threshold value in each model set, then adding the sums corresponding to the model sets corresponding to the combinations of different scenes and risk types to obtain a sum s, and setting the weight of the mechanism as w ═ f(s), wherein f is a monotone increasing function.
In one embodiment, as shown in fig. 5, after building a blockchain network by using business systems of respective financial institutions as blockchain storage nodes, the method for assessing transaction risk based on blockchain provided in an embodiment of the present invention further includes:
and S504, configuring a super node in the block chain network, wherein the financial institution corresponding to the super node is used for managing and controlling a risk early warning model of the financial institution corresponding to each block chain storage node in the block chain network and a data source shared by each block chain storage node in the block chain network.
In a specific implementation, when each financial institution is a branch of a certain bank, the super node may be a blockchain storage node corresponding to the headquarters of the bank.
When the transaction risk assessment method based on the block chain provided in the embodiment of the present invention is applied to business transaction risk assessment of a bank customer, the method may specifically include:
1) a plurality of risk early warning models of the node mechanism are stored in the block chain, and each risk early warning model can be used for recognizing and predicting risks in financial transactions.
2) And classifying the prediction result types of the risk early warning models of the block chains into a plurality of risk early warning model subsets according to the risk types and the application scenes. For example, the risk categories include risk of account theft, risk of illegal fund transfer, risk of customer churn, risk of fraud, risk of default, etc., and the application scenarios include: for public, private, cross-border transactions, etc., the prediction categories may be: risk probability, risk category, risk time, etc.
3) And performing performance evaluation on the risk early warning models in the risk early warning model subset based on the data (including risk data) uploaded to the block chain, and storing evaluation results into the block chain. Each specific risk early warning model uses a specific method category, input parameters and key features, the method category can be a machine learning method such as a support vector machine, Bayes, a neural network and the like, and the input parameters and the key features depend on specific transaction data such as the number of times of identity verification and the like.
4) Each risk early warning model subset corresponds to an integration algorithm, an integrated unit is each risk early warning model of the subset, and the weight is related to the precision of each risk early warning model, namely the more accurate the risk early warning model is, the larger the weight is. This integration algorithm may be provided to each node structure for their selective use.
5) And the node mechanisms in the block chain select corresponding risk early warning model subsets according to the scenes of financial transactions and transaction data. And then, according to the risk early warning models of the risk early warning model subset, carrying out risk prediction on the transaction of the node mechanism. One option is: an integration algorithm corresponding to the subset is used. Certainly, the node structure can upload the risk early warning model of the node structure, and the risk early warning model subset of the block chain is updated in this way.
6) And uploading the risk prediction result and the subsequent risk evaluation result of the financial transaction of each node mechanism to the block chain, and then adjusting the performance parameters of the risk early warning model based on the data. The previous model evaluation may be due to the insufficiency of sample data, the precision of the evaluation is not accurate, and the newly appeared sample data can just make up the previous insufficiency.
7) The weight of each mechanism node in the consensus algorithm in the block chain depends on the method type of the risk early warning model uploaded by the node structure, the number of the risk early warning models, the transaction scene corresponding to each risk early warning model and the model accuracy of each risk early warning model. For example, the following settings are set: for each combination of different scenes and risk types, selecting a model with the highest early warning accuracy for each model early warning method to form a model set, namely, each combination of different scenes and risk types corresponds to one model set, then calculating the accuracy sum of the risk early warning models with the accuracy larger than a threshold value in each model set, then adding the sums corresponding to the model sets corresponding to the combinations of different scenes and risk types to obtain a sum s, and setting the weight of the mechanism as w ═ f(s), wherein f is a monotone increasing function.
8) In the blockchain, there is a super node, which may be a wind control mechanism corresponding to the head office, for managing and controlling the threshold in the wind control model in the blockchain, such as 7).
In the embodiment of the invention, the block chain is used for recording the transaction data and the risk data of the public client in each mechanism. The risk of the customer is then assessed based on the risk data of the various institutions. According to the risk assessment result and the preset intelligent contract, the transaction behavior of the client is limited, the service can be effectively provided for the client, and meanwhile, the transaction risks of various businesses can be effectively reduced.
Based on the same inventive concept, an embodiment of the present invention further provides a transaction risk assessment apparatus based on a block chain, as described in the following embodiments. Because the principle of the device for solving the problems is similar to the transaction risk assessment method based on the blockchain, the implementation of the device can refer to the implementation of the transaction risk assessment method based on the blockchain, and repeated details are not repeated.
Fig. 6 is a schematic diagram of a transaction risk assessment apparatus based on a blockchain according to an embodiment of the present invention, as shown in fig. 6, the apparatus includes: the system comprises a block chain data storage module 601, a risk early warning model selection module 602, a risk assessment module 603, a risk early warning module 604 and a transaction behavior control module 605.
The block chain data storage module 601 is configured to extract risk types of a target client according to historical risk data of the target client, obtain a risk type set of the target client, and store the risk type set onto a block chain network, where the risk type set includes: one or more risk types; a risk early warning model selection module 602, configured to, when a business transaction request of a target customer at any one financial institution is received, query a risk type set of the target customer from a blockchain network, and screen a risk early warning model corresponding to each risk type in the risk type set from a risk early warning model subset of each financial institution, where the risk early warning model subset of each financial institution includes: risk early warning models corresponding to a plurality of risk types; the risk assessment module 603 is configured to input the transaction data and risk data of the target customer, which are stored in the blockchain network, into the risk early warning models of the financial institutions, and output risk assessment results of the target customer at the financial institutions; the risk early warning module 604 is configured to obtain real-time transaction data of a target client according to a service transaction request, input the real-time transaction data of the target client into each screened risk early warning model, and output a risk evaluation result of each risk early warning model; and the transaction behavior control module 605 is configured to obtain a risk early warning identifier of the target customer according to the risk type set of the target customer and a risk evaluation result of a risk early warning model corresponding to each risk type in the risk type set by using an intelligent contract configured in advance on the block chain network.
In one embodiment, as shown in fig. 7, the device for risk assessment based on blockchain provided in an embodiment of the present invention further includes: and a client risk type set building module 606, configured to extract risk types of the similar clients or the associated clients according to historical risk data of the similar clients or the associated clients, and add the risk types of the similar clients and the associated clients to the risk type set of the target client, where the similar clients are clients whose similarity to the target client exceeds a preset threshold, and the associated clients are clients having an association relationship with the target client.
In one embodiment, as shown in fig. 7, the device for risk assessment based on blockchain provided in an embodiment of the present invention further includes: a transaction scenario configuration module 607, configured to obtain a plurality of pre-configured transaction scenarios; a risk early warning model training module 608, configured to obtain a risk early warning model subset of each financial institution through machine learning training according to a plurality of preconfigured transaction scenarios, where the risk early warning model subset of each financial institution includes: a plurality of risk early warning models for each financial institution under different transaction scenarios. In this embodiment, the risk early warning model selection module 602 is further configured to, when a service transaction request of a target customer at any financial institution is received, obtain a current service transaction scenario, and screen out a risk early warning model corresponding to a corresponding risk type in the current service transaction scenario from a risk early warning model subset of each financial institution according to the current service transaction scenario and a risk type set of the target customer stored on the block chain network.
Optionally, the risk early warning model training module 608 may perform machine learning on any one of the following models, and train to obtain a risk early warning model subset of each financial institution: support vector machine model, Bayesian model and neural network model.
In one embodiment, as shown in fig. 7, the device for risk assessment based on blockchain provided in an embodiment of the present invention further includes: a risk assessment result uplink module 609, configured to upload the risk assessment results of the target client at each financial institution to the blockchain network; and the risk early warning model updating module 610 is used for updating parameters of the risk early warning models of the financial machines in different transaction scenes according to the risk assessment results of the target customers stored on the block chain network.
In one embodiment, as shown in fig. 7, the device for risk assessment based on blockchain provided in an embodiment of the present invention further includes: the block chain network building module 611 is configured to use the service system of each financial institution as a block chain storage node to build a block chain network, where each block chain storage node in the block chain network stores block chain data based on a consensus algorithm.
In one embodiment, as shown in fig. 7, the device for risk assessment based on blockchain provided in an embodiment of the present invention further includes: a consensus algorithm updating module 612, configured to obtain risk types of the financial institutions, risk early warning model method categories, the number of risk early warning models, transaction scenarios corresponding to the risk early warning models, and model accuracy of each risk early warning model; and determining or updating the weighted value of the block chain storage node corresponding to each financial institution in the consensus algorithm according to the risk type of each financial institution, the risk early warning model method type, the number of risk early warning models, the transaction scene corresponding to each risk early warning model and the model accuracy of each risk early warning model, wherein different method types correspond to different model training methods.
In one embodiment, as shown in fig. 7, the device for risk assessment based on blockchain provided in an embodiment of the present invention further includes: a super node configuring module 613, configured to configure a super node in the blockchain network, where a financial institution corresponding to the super node is configured to manage and control a risk early warning model of the financial institution corresponding to each blockchain storage node in the blockchain network, and a data source shared by each blockchain storage node in the blockchain network.
Based on the same inventive concept, a computer device is further provided in the embodiments of the present invention to solve the technical problem that the business system of the existing financial institution lacks an effective mechanism to control the transaction risk of the customer, fig. 8 is a schematic diagram of a computer device provided in the embodiments of the present invention, as shown in fig. 8, the computer device 80 includes a memory 801, a processor 802, and a computer program stored on the memory 801 and operable on the processor 802, and when the processor executes the computer program, the above transaction risk assessment method based on the blockchain is implemented.
Based on the same inventive concept, the embodiment of the present invention further provides a computer-readable storage medium, so as to solve the technical problem that the business system of the existing financial institution lacks an effective mechanism for controlling the transaction risk of the client, where the computer-readable storage medium stores a computer program for executing the transaction risk assessment method based on the blockchain.
In summary, according to the transaction risk assessment method, apparatus, computer device, and computer readable storage medium provided in the embodiments of the present invention, after the risk type of the target client is obtained by extracting the historical risk data of the target client, the risk type of the target client is stored in the blockchain network, further, based on the risk type of the target client stored in the blockchain network, a risk early warning model capable of predicting a corresponding risk type is screened out from a subset of risk early warning models of each financial institution, a risk early warning is performed on the target client by using the screened risk early warning model, so as to obtain a risk assessment result of the target client, and finally, whether to limit the transaction operation of the target client is determined by using an intelligent contract pre-configured on the blockchain network according to the risk assessment result of the target client.
According to the embodiment of the invention, the corresponding risk early warning model is obtained based on the target client risk type set stored in the blockchain network, the risk early warning is carried out on the target client, a more accurate risk evaluation result can be obtained, the transaction behavior of the target client is controlled by using the risk evaluation result, and the risk business transaction can be effectively prevented.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (16)
1. A transaction risk assessment method based on a blockchain is characterized by comprising the following steps:
extracting the risk types of the target client according to historical risk data of the target client to obtain a risk type set of the target client, and storing the risk type set to a block chain network, wherein the risk type set comprises: one or more risk types;
when a business transaction request of the target customer at any financial institution is received, inquiring a risk type set of the target customer from a block chain network, and screening a risk early warning model corresponding to each risk type in the risk type set from a risk early warning model subset of each financial institution, wherein the risk early warning model subset of each financial institution comprises: risk early warning models corresponding to a plurality of risk types;
acquiring real-time transaction data of the target client according to the service transaction request, inputting the real-time transaction data of the target client into each screened risk early warning model, and outputting a risk evaluation result of each risk early warning model;
acquiring a risk early warning identifier of the target client according to a risk type set of the target client and a risk evaluation result of a risk early warning model corresponding to each risk type in the risk type set by using an intelligent contract configured in advance on the blockchain network;
and determining whether to limit the transaction operation of the target customer according to the risk early warning identification of the target customer.
2. The method of claim 1, wherein the method further comprises:
extracting risk types of similar customers or associated customers according to historical risk data of the similar customers or the associated customers, wherein the similar customers are customers with similarity to the target customers exceeding a preset threshold, and the associated customers are customers with association relation to the target customers;
and adding the risk types of the similar clients and the associated clients into the risk type set of the target client.
3. The method of claim 1, wherein the method further comprises:
acquiring a plurality of pre-configured transaction scenes;
obtaining a risk early warning model subset of each financial institution through machine learning training according to a plurality of pre-configured transaction scenes, wherein the risk early warning model subset of each financial institution comprises: a plurality of risk early warning models of each financial institution under different transaction scenes;
when a business transaction request of the target customer at any financial institution is received, acquiring a current business transaction scene, and screening a risk early warning model corresponding to a corresponding risk type in the current business transaction scene from a risk early warning model subset of each financial institution according to the current business transaction scene and a risk type set of the target customer stored on a block chain network.
4. The method of claim 2, wherein after inputting the transaction data and risk data of the target customer stored on the blockchain network into the risk pre-warning models of the respective financial institutions and outputting the risk assessment results of the target customer at the respective financial institutions, the method further comprises:
uploading the risk assessment results of the target customer at each financial institution to the blockchain network;
and updating parameters of the risk early warning models of the financial machines in different transaction scenes according to the risk evaluation results of the target customers stored on the blockchain network.
5. The method of any one of claims 1 to 4, wherein prior to storing the transaction data and risk data of the target customer at the respective financial institution on the blockchain network, the method further comprises:
and taking the service system of each financial institution as a block chain storage node to construct the block chain network, wherein each block chain storage node in the block chain network stores block chain data based on a consensus algorithm.
6. The method of claim 5, wherein after constructing the blockchain network with the business systems of the respective financial institutions as blockchain storage nodes, the method further comprises:
acquiring risk types, risk early warning model method types, risk early warning model numbers, transaction scenes corresponding to the risk early warning models and model accuracy rates of the risk early warning models of the financial institutions, wherein different method types correspond to different model training methods;
and determining or updating the weighted value of the block chain storage node corresponding to each financial institution in the consensus algorithm according to the risk type of each financial institution, the risk early warning model method category, the number of risk early warning models, the transaction scene corresponding to each risk early warning model and the model accuracy of each risk early warning model.
7. The method of claim 6, wherein after constructing the blockchain network with the business systems of the respective financial institutions as blockchain storage nodes, the method further comprises:
and configuring a super node in the block chain network, wherein a financial institution corresponding to the super node is used for managing and controlling a risk early warning model of the financial institution corresponding to each block chain storage node in the block chain network and a data source shared by each block chain storage node in the block chain network.
8. A blockchain-based transaction risk assessment apparatus, comprising:
the block chain data storage module is used for extracting the risk types of the target client according to historical risk data of the target client to obtain a risk type set of the target client and storing the risk type set to a block chain network, wherein the risk type set comprises: one or more risk types;
the risk early warning model selection module is used for querying a risk type set of the target client from a block chain network when receiving a business transaction request of the target client at any financial institution, and screening a risk early warning model corresponding to each risk type in the risk type set from a risk early warning model subset of each financial institution, wherein the risk early warning model subset of each financial institution comprises: risk early warning models corresponding to a plurality of risk types;
the risk assessment module is used for acquiring real-time transaction data of the target client according to the business transaction request, inputting the real-time transaction data of the target client into each screened risk early warning model and outputting a risk assessment result of each risk early warning model;
the risk early warning module is used for acquiring a risk early warning identifier of the target client according to a risk type set of the target client and a risk evaluation result of a risk early warning model corresponding to each risk type in the risk type set by using an intelligent contract configured in advance on the blockchain network;
and the transaction behavior control module is used for determining whether to limit the transaction operation of the target client according to the risk early warning identification of the target client.
9. The apparatus of claim 8, wherein the apparatus further comprises:
the client risk type set building module is used for extracting the risk types of similar clients or associated clients according to historical risk data of the similar clients or the associated clients, adding the risk types of the similar clients and the associated clients into the risk type set of the target client, wherein the similar clients are clients with similarity to the target client exceeding a preset threshold, and the associated clients are clients with incidence relation to the target client.
10. The apparatus of claim 8, wherein the apparatus further comprises:
the transaction scene configuration module is used for acquiring a plurality of pre-configured transaction scenes;
the risk early warning model training module is used for obtaining a risk early warning model subset of each financial institution through machine learning training according to a plurality of pre-configured transaction scenes, wherein the risk early warning model subset of each financial institution comprises: a plurality of risk early warning models of each financial institution under different transaction scenes;
the risk early warning model selection module is further used for acquiring a current business transaction scene when receiving a business transaction request of the target customer at any financial institution, and screening a risk early warning model corresponding to a corresponding risk type in the current business transaction scene from the risk early warning model subset of each financial institution according to the current business transaction scene and a risk type set of the target customer stored on the block chain network.
11. The apparatus of claim 8, wherein the apparatus further comprises:
a risk assessment result uplink module for uploading the risk assessment results of the target customer at each financial institution to the blockchain network;
and the risk early warning model updating module is used for updating parameters of the risk early warning models of the financial machines in different transaction scenes according to the risk assessment results of the target customers stored on the block chain network.
12. The apparatus of any of claims 8 to 11, further comprising:
and the block chain network construction module is used for constructing the block chain network by taking the service system of each financial institution as a block chain storage node, wherein each block chain storage node in the block chain network stores the block chain data based on a consensus algorithm.
13. The apparatus of claim 12, wherein the apparatus further comprises:
the consensus algorithm updating module is used for acquiring the risk types of the financial institutions, the risk early warning model method types, the number of risk early warning models, transaction scenes corresponding to the risk early warning models and the model accuracy of each risk early warning model; and determining or updating the weighted value of the block chain storage node corresponding to each financial institution in the consensus algorithm according to the risk type of each financial institution, the risk early warning model method type, the number of risk early warning models, the transaction scene corresponding to each risk early warning model and the model accuracy of each risk early warning model, wherein different method types correspond to different model training methods.
14. The apparatus of claim 13, wherein the apparatus further comprises:
and the super node configuration module is used for configuring a super node in the block chain network, wherein a financial institution corresponding to the super node is used for managing and controlling a risk early warning model of the financial institution corresponding to each block chain storage node in the block chain network and a data source shared by each block chain storage node in the block chain network.
15. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the blockchain based transaction risk assessment method according to any one of claims 1 to 7 when executing the computer program.
16. A computer-readable storage medium storing a computer program for executing the blockchain-based transaction risk assessment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110768964.0A CN113435770A (en) | 2021-07-07 | 2021-07-07 | Transaction risk assessment method and device based on block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110768964.0A CN113435770A (en) | 2021-07-07 | 2021-07-07 | Transaction risk assessment method and device based on block chain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113435770A true CN113435770A (en) | 2021-09-24 |
Family
ID=77759581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110768964.0A Pending CN113435770A (en) | 2021-07-07 | 2021-07-07 | Transaction risk assessment method and device based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113435770A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114066584A (en) * | 2021-11-05 | 2022-02-18 | 支付宝(杭州)信息技术有限公司 | Method and device for risk prevention and control of block chain |
| CN114240097A (en) * | 2021-12-02 | 2022-03-25 | 支付宝(杭州)信息技术有限公司 | Risk assessment method and device |
| CN115345734A (en) * | 2022-10-19 | 2022-11-15 | 山东新科凯邦通信器材有限公司 | Industrial chain financial wind control model construction method based on block chain |
| CN115760125A (en) * | 2023-01-09 | 2023-03-07 | 中企云链（北京）金融信息服务有限公司 | Production and fusion data risk control method and system based on block chain and storage medium |
| CN116630032A (en) * | 2023-07-17 | 2023-08-22 | 九一金融信息服务(北京)有限公司 | Intelligent post-credit management system based on blockchain |
| CN117034361A (en) * | 2023-07-31 | 2023-11-10 | 广州承启医学检验有限公司 | Gene detection and inspection laboratory information management method and system |
-
2021
- 2021-07-07 CN CN202110768964.0A patent/CN113435770A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114066584A (en) * | 2021-11-05 | 2022-02-18 | 支付宝(杭州)信息技术有限公司 | Method and device for risk prevention and control of block chain |
| CN114240097A (en) * | 2021-12-02 | 2022-03-25 | 支付宝(杭州)信息技术有限公司 | Risk assessment method and device |
| CN115345734A (en) * | 2022-10-19 | 2022-11-15 | 山东新科凯邦通信器材有限公司 | Industrial chain financial wind control model construction method based on block chain |
| CN115760125A (en) * | 2023-01-09 | 2023-03-07 | 中企云链（北京）金融信息服务有限公司 | Production and fusion data risk control method and system based on block chain and storage medium |
| CN116630032A (en) * | 2023-07-17 | 2023-08-22 | 九一金融信息服务(北京)有限公司 | Intelligent post-credit management system based on blockchain |
| CN116630032B (en) * | 2023-07-17 | 2023-10-31 | 九一金融信息服务(北京)有限公司 | Intelligent post-credit management system based on blockchain |
| CN117034361A (en) * | 2023-07-31 | 2023-11-10 | 广州承启医学检验有限公司 | Gene detection and inspection laboratory information management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113435770A (en) | Transaction risk assessment method and device based on block chain | |
| CN110084377B (en) | Method and device for constructing decision tree | |
| US20220343197A1 (en) | Systems and methods for providing machine learning model explainability information | |
| US11436615B2 (en) | System and method for blockchain transaction risk management using machine learning | |
| US20220067738A1 (en) | System and Method for Blockchain Automatic Tracing of Money Flow Using Artificial Intelligence | |
| WO2019213311A1 (en) | Conducting optimized cross-blockchain currency transactions using machine learning | |
| CN108734299A (en) | Quantum calculation machine study module | |
| KR102330423B1 (en) | Online default forecasting system using image recognition deep learning algorithm | |
| KR102344383B1 (en) | Method for analyzing loyalty of the customer to store based on artificial intelligence and system thereof | |
| US20240005399A1 (en) | Cryptocurrency mining selection system and method | |
| CN112799708A (en) | Method and system for jointly updating business model | |
| US20210239479A1 (en) | Predicted Destination by User Behavior Learning | |
| CN114693192A (en) | Wind control decision method and device, computer equipment and storage medium | |
| CN113436006A (en) | Loan risk prediction method and device based on block chain | |
| US11854018B2 (en) | Labeling optimization through image clustering | |
| US11954174B2 (en) | Sharing financial crime knowledge | |
| CN113689270A (en) | Method for determining black product device, electronic device, storage medium, and program product | |
| CN110414260B (en) | Data access method, device, system and storage medium | |
| WO2023103688A1 (en) | Federated machine learning based on partially secured spatio-temporal data | |
| AU2021218217A1 (en) | Systems and methods for preventative monitoring using AI learning of outcomes and responses from previous experience. | |
| US20230377004A1 (en) | Systems and methods for request validation | |
| US20240086923A1 (en) | Entity profile for access control | |
| US20230393909A1 (en) | Automatically managing event-related communication data using machine learning techniques | |
| CN111797126B (en) | Data processing method, device and equipment | |
| CN117726455A (en) | Message pushing method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |