Transaction safety monitoring method for vending machine

Abstract

A transaction security monitoring method for an unmanned vending machine relates to the technical field of transaction security monitoring, and comprises the following steps: constructing a transaction security cloud monitoring center, and collecting encrypted and uploaded transaction data of the unmanned vending machine; when a new block chain node is added at the tail part of the block chain network, carrying out identity secondary identification test or transaction data authenticity evaluation; constructing a transaction data authenticity evaluation model, obtaining various types of feature threshold evaluation intervals corresponding to transaction data in the new block chain node, obtaining various types of features in the new block chain node, comparing the various types of features with the corresponding various types of feature threshold evaluation intervals, and evaluating the authenticity of the transaction data. Carrying out identity secondary identification test or commodity delivery operation according to the comparison result; and carrying out identity secondary identification test, and carrying out real-time updating of the transaction data authenticity evaluation model or carrying out new block chain node elimination operation according to a test result of the identity secondary identification test, so as to ensure the safety requirement of the transaction data of the unmanned vending machine.

Description

Technical Field

[0001] The present invention relates to the technical field of transaction security monitoring, and in particular to a transaction security monitoring method for an unmanned vending machine. Background Art

[0002] With the development of the Internet of Things, mobile payment and commercial automation, intelligent unmanned sales have become a development trend in the retail industry, and unmanned retail vending machines have also attracted much attention. The transaction data of unmanned vending machines involves users' personal information and consumption behavior, and there is a potential risk of privacy leakage. The monitoring method may miss detection or false alarms, that is, failure to detect fraud in time or mistakenly misinterpret normal transactions as fraud, which will lead to security issues that cannot be effectively resolved or cause unnecessary troubles to users. How to collect and analyze transaction data in order to detect any abnormal patterns or suspicious transactions, such as stealing credit cards or using false payment information, is a problem that we urgently need to solve. A transaction security monitoring method for unmanned vending machines is now provided. Summary of the invention

[0004] In order to solve the above technical problems, the object of the present invention is to provide a transaction security monitoring method for an unmanned vending machine, comprising the following steps:

[0005] Step S1: Build a transaction security cloud monitoring center, use the unmanned vending machine as a blockchain node, and collect the transaction data encrypted and uploaded by the unmanned vending machine;

[0006] Step S2: when a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the number of other blockchain nodes in the blockchain network that are consistent with the identity information in the new blockchain node is obtained, and a secondary identity recognition test or transaction data authenticity assessment is performed based on the number;

[0007] Step S3: construct a transaction data authenticity assessment model based on the graph convolutional long short-term memory network, output the transaction data in the new blockchain node corresponding to the threshold assessment interval of each type of feature through the transaction data authenticity assessment model, extract features of the transaction data in the new blockchain node, generate various types of features, compare each type of feature with the corresponding threshold assessment interval of each type of feature, and perform secondary identity recognition test or product outbound operation according to the comparison result;

[0008] Step S4: Perform a secondary identity recognition test, and update the transaction data authenticity assessment model in real time or remove new blockchain nodes based on the test results of the secondary identity recognition test.

[0009] Furthermore, the process of building a transaction security cloud monitoring center includes:

[0010] A transaction security cloud monitoring center is constructed using blockchain technology. The transaction security monitoring center is provided with a number of blockchain nodes. The blockchain nodes are communicatively connected to the unmanned vending machines within a preset range, and each blockchain node is linked to each other to form a blockchain network. Each unmanned vending machine is provided with a data uplink end, and the data uplink segment is used to upload transaction data to the blockchain node.

[0011] Furthermore, the unmanned vending machine is provided with an interactive interface, through which the user can perform order selection operations, scan code payment operations and biometric data recognition operations;

[0012] When the user performs a scan code payment operation through the interactive interface, the user's identity information and transaction data are obtained based on the order scan code payment operation. The transaction data includes transaction amount, transaction frequency, transaction time period and vending machine location data, and the identity information and transaction data are encrypted and uploaded to the blockchain node.

[0013] Furthermore, the process of encrypting and uploading identity information and transaction data to the blockchain node includes:

[0014] The public key and private key of each vending machine are preset through an asymmetric encryption algorithm, the identity information and transaction data are preprocessed in data format and converted into binary data of fixed length. The binary data is encrypted by the private key of the vending machine to generate an encrypted data packet, which is uploaded to the blockchain node. The blockchain node decrypts the received encrypted data packet through the public key of the vending machine to generate identity information and transaction data. Subsequently, a new blockchain node is added to the end of the blockchain network, and the identity information and transaction data are packaged into the new blockchain node.

[0015] Furthermore, when a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the number of other blockchain nodes in the blockchain network that are consistent with the identity information in the new blockchain node is obtained, and the process of performing a secondary identity recognition test or transaction data authenticity assessment based on the number includes:

[0016] When a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the identity information in the new blockchain node is matched with the identity information of other blockchain nodes in the blockchain network, and other blockchain nodes in the blockchain network whose identity information is consistent with the identity information in the new blockchain node are obtained, and the node number of the other blockchain nodes is obtained, and a node number threshold is preset. If the node number of the other blockchain nodes is less than the node number threshold, a secondary identity recognition test is performed;

[0017] If the number of nodes of other blockchain nodes is greater than or equal to the node number threshold, the identity information in the new blockchain node is input into the transaction data authenticity assessment model, and the transaction data authenticity assessment model outputs the threshold assessment intervals of each type of feature, and the transaction data in the new blockchain node is feature extracted to generate each type of feature, and each type of feature is compared with the corresponding threshold assessment interval of each type of feature;

[0018] If all types of features are within the corresponding threshold assessment intervals of each type of feature, the product is shipped out;

[0019] If each type of feature is not within the corresponding threshold evaluation interval of each type of feature, a secondary identity recognition test is performed, and the transaction data authenticity evaluation model is updated in real time based on the test results of the secondary identity recognition test.

[0020] Furthermore, the process of constructing a transaction data authenticity assessment model based on graph convolutional long short-term memory network includes:

[0021] A transaction data authenticity assessment model is constructed based on a graph convolutional long short-term memory network, the identity information and transaction data of each blockchain node in the blockchain network are retrieved, the blockchain nodes are aggregated based on the identity information, the features of different transaction time periods in several blockchain nodes with the same identity information are spliced ​​according to the blockchain nodes, and a three-dimensional feature matrix is ​​constructed. The features include transaction amount and transaction frequency. The three-dimensional feature matrix includes three dimensions: features, transaction time period, and vending machine location data;

[0022] An adaptive adjacency matrix is ​​constructed based on the three-dimensional feature matrix. The adaptive adjacency matrix is ​​determined by the similarity between each blockchain node in the three-dimensional feature matrix. Graph data is constructed based on the three-dimensional feature matrix and the adaptive adjacency matrix. A multi-layer convolution operation is performed on the graph data using a graph convolutional neural network.

[0023] After multi-layer graph convolution operations, the collection order of spatial features of each blockchain node in the three-dimensional feature matrix is ​​obtained according to the transaction time period in the three-dimensional feature matrix, and the features with spatial features of each blockchain node in the three-dimensional feature matrix are input into the long short-term memory network according to the collection order. The spatiotemporal features of each blockchain node are output through the long short-term memory network, and so on, the spatiotemporal features of each blockchain node corresponding to each different identity information in the blockchain network are obtained;

[0024] A transaction data authenticity assessment model is built based on the RBF neural network, and the spatiotemporal characteristics of each blockchain node corresponding to different identity information in the blockchain network are used as the test set and training set of the transaction data authenticity assessment model;

[0025] Input the training set into the transaction data authenticity assessment model for training until the loss function training is stable, and save the model parameters, test the transaction data authenticity assessment model through the test set until it meets the preset requirements, and output the transaction data authenticity assessment model;

[0026] According to the transaction data authenticity assessment model, the spatiotemporal feature prediction data of different identities are output.

[0027] Furthermore, the transaction data authenticity evaluation model is used to output the threshold evaluation intervals of each type of feature, the transaction data in the new blockchain node is feature extracted, each type of feature is generated, and each type of feature is compared with the corresponding threshold evaluation interval of each type of feature. The process includes:

[0028] Obtaining various types of feature threshold evaluation intervals for different identities based on the spatiotemporal feature prediction data of different identities, wherein the various types of feature threshold evaluation intervals include transaction amount threshold intervals and transaction frequency threshold intervals corresponding to different unmanned vending machine location data in different time periods;

[0029] According to the identity information in the new blockchain node, the corresponding feature threshold evaluation intervals of each type are obtained; according to the transaction data in the new blockchain node, the vending machine location data, the time period of the transaction time period, the transaction amount and the transaction frequency are obtained; the transaction amount threshold interval and the transaction frequency threshold interval corresponding to the vending machine location data and the time period of the transaction time period are obtained; and the transaction amount and transaction frequency are compared with the transaction amount threshold interval and the transaction frequency threshold interval.

[0030] Furthermore, the process of performing a secondary identity recognition test and performing a real-time update of a transaction data authenticity assessment model or a new blockchain node removal operation based on the test result of the secondary identity recognition test includes:

[0031] The transaction security cloud monitoring center is provided with an identity recognition biometric database, which includes biometric data pre-entered by the user. The unmanned vending machine sends an identity secondary recognition test instruction through an interactive interface. The user performs a biometric data recognition operation according to the identity secondary recognition test instruction, generates the user's temporary biometric data and sends it to the identity recognition biometric database for biometric data matching, and determines whether there is biometric data in the identity recognition biometric database that is consistent with the temporary biometric data;

[0032] If it exists, the spatiotemporal characteristics of the new blockchain node are obtained, and based on the spatiotemporal characteristics of each blockchain node corresponding to each different identity information in the blockchain network and the test set and training set of the new blockchain node as the transaction data authenticity assessment model, the spatiotemporal characteristics of the new blockchain node are added to the test set and the training set to obtain a new test set and training set, and the transaction data authenticity assessment model is retrained and updated based on the new test set and training set to obtain an updated transaction data authenticity assessment model;

[0033] If it does not exist, an identity authentication failure message is sent to the vending machine and the new blockchain node is removed.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. When a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, and the number of other blockchain nodes in the blockchain network that are consistent with the identity information in the new blockchain node is obtained. If the number of other blockchain nodes is less than the node number threshold, a secondary identity recognition test is performed to avoid the inability of the transaction data authenticity assessment model to obtain a more accurate user transaction data authenticity assessment due to sparse or missing historical transaction behavior records of users in the blockchain network;

[0036] 2. Construct a transaction data authenticity assessment model based on the graph convolutional long short-term memory network. The transaction data authenticity assessment model outputs the threshold assessment intervals of various types of features corresponding to the transaction data in the new blockchain node, obtains the transaction amount threshold intervals and transaction frequency threshold intervals corresponding to the user's different vending machine location data in different time periods, and realizes reasonable prediction of the user's transaction data behavior. The transaction data in the new blockchain node is feature extracted to generate various types of features, and each type of feature is compared with the corresponding threshold assessment interval of each type of feature. When the user's transaction behavior does not match the user's reasonable threshold interval, a secondary identity recognition test is performed. If the user's biometric data verification is passed, the transaction data authenticity assessment model is updated in real time to ensure that the transaction data authenticity assessment model can always effectively identify fraud and ensure the security requirements of the transaction data of the vending machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic diagram of a transaction security monitoring method for an unmanned vending machine according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0041] like Figure 1 As shown, a transaction security monitoring method for an unmanned vending machine includes the following steps:

[0042] Step S1: Build a transaction security cloud monitoring center, use the unmanned vending machine as a blockchain node, and collect the transaction data encrypted and uploaded by the unmanned vending machine;

[0043] Step S2: when a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the number of other blockchain nodes in the blockchain network that are consistent with the identity information in the new blockchain node is obtained, and a secondary identity recognition test or transaction data authenticity assessment is performed based on the number;

[0044] Step S3: construct a transaction data authenticity assessment model based on the graph convolutional long short-term memory network, output the transaction data in the new blockchain node corresponding to the threshold assessment interval of each type of feature through the transaction data authenticity assessment model, extract features of the transaction data in the new blockchain node, generate various types of features, compare each type of feature with the corresponding threshold assessment interval of each type of feature, and perform secondary identity recognition test or product outbound operation according to the comparison result;

[0045] Step S4: Perform a secondary identity recognition test, and update the transaction data authenticity assessment model in real time or remove new blockchain nodes based on the test results of the secondary identity recognition test.

[0046] It should be further explained that, in the specific implementation process, the process of building a transaction security cloud monitoring center includes:

[0047] A transaction security cloud monitoring center is constructed using blockchain technology. The transaction security monitoring center is provided with a number of blockchain nodes. The blockchain nodes are communicatively connected to the unmanned vending machines within a preset range, and each blockchain node is linked to each other to form a blockchain network. Each unmanned vending machine is provided with a data uplink end, and the data uplink segment is used to upload transaction data to the blockchain node.

[0048] It should be further explained that, in the specific implementation process, the unmanned vending machine is provided with an interactive interface, through which the user performs order selection operations, scan code payment operations and biometric data recognition operations;

[0049] When the user performs a scan code payment operation through the interactive interface, the user's identity information and transaction data are obtained based on the order scan code payment operation. The transaction data includes transaction amount, transaction frequency, transaction time period and vending machine location data. It should be noted that the process of obtaining the vending machine location data is to obtain the longitude and latitude information of the location of the vending machine through GIS means, use the longitude and latitude information of each vending machine as the vending machine location data, and encrypt the identity information and transaction data and upload them to the blockchain node.

[0050] It should be further explained that, in the specific implementation process, the process of encrypting and uploading identity information and transaction data to the blockchain node includes:

[0051] The public key and private key of each vending machine are preset through an asymmetric encryption algorithm, the identity information and transaction data are preprocessed in data format and converted into binary data of fixed length. The binary data is encrypted by the private key of the vending machine to generate an encrypted data packet, which is uploaded to the blockchain node. The blockchain node decrypts the received encrypted data packet through the public key of the vending machine to generate identity information and transaction data. Subsequently, a new blockchain node is added to the end of the blockchain network, and the identity information and transaction data are packaged into the new blockchain node.

[0052] It should be further explained that, in the specific implementation process, when a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the number of other blockchain nodes in the blockchain network that are consistent with the identity information in the new blockchain node is obtained, and the process of performing a secondary identity recognition test or transaction data authenticity assessment based on the number includes:

[0053] When a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the identity information in the new blockchain node is matched with the identity information of other blockchain nodes in the blockchain network, and other blockchain nodes in the blockchain network whose identity information is consistent with the identity information in the new blockchain node are obtained, and the node number of the other blockchain nodes is obtained, and a node number threshold is preset. If the node number of the other blockchain nodes is less than the node number threshold, a secondary identity recognition test is performed;

[0054] If the number of nodes of other blockchain nodes is greater than or equal to the node number threshold, the identity information in the new blockchain node is input into the transaction data authenticity assessment model, and the transaction data authenticity assessment model outputs the threshold assessment intervals of each type of feature, and the transaction data in the new blockchain node is feature extracted to generate each type of feature, and each type of feature is compared with the corresponding threshold assessment interval of each type of feature;

[0055] If all types of features are within the corresponding threshold assessment intervals of each type of feature, the product is shipped out;

[0056] If each type of feature is not within the corresponding threshold evaluation interval of each type of feature, a secondary identity recognition test is performed, and the transaction data authenticity evaluation model is updated in real time based on the test results of the secondary identity recognition test.

[0057] It should be further explained that, in the specific implementation process, the process of building a transaction data authenticity assessment model based on graph convolutional long short-term memory network includes:

[0058] A transaction data authenticity assessment model is constructed based on a graph convolutional long short-term memory network, the identity information and transaction data of each blockchain node in the blockchain network are retrieved, the blockchain nodes are aggregated based on the identity information, the features of different transaction time periods in several blockchain nodes with the same identity information are spliced ​​according to the blockchain nodes, and a three-dimensional feature matrix is ​​constructed. The features include transaction amount and transaction frequency. The three-dimensional feature matrix includes three dimensions: features, transaction time period, and vending machine location data;

[0059] It should be further explained that the formula of the three-dimensional feature matrix is:

[0060] Q = concact{W1,W2,...,Wj,...,WL}, j = 1,2,...,L, where Q represents a three-dimensional feature matrix, is the two-dimensional data matrix of the j-th blockchain node constructed, concact represents the concatenation of the two-dimensional data matrices of each blockchain node according to the blockchain nodes, and L represents the total number of blockchain nodes;

[0061] =( , ,... ,..., ), n=1,2,...,k;

[0062] in, It represents the characteristics of the nth transaction time period of the jth blockchain node, and the characteristics include transaction amount and transaction frequency. Among them, n represents the temporal relationship of obtaining each feature of the jth blockchain node, converting the transaction time period of each feature into a corresponding collection sequence, and k represents the total number of orders of the collection sequence.

[0063] An adaptive adjacency matrix is ​​constructed based on the three-dimensional feature matrix. The adaptive adjacency matrix is ​​determined by the similarity between each blockchain node in the three-dimensional feature matrix. Graph data is constructed based on the three-dimensional feature matrix and the adaptive adjacency matrix. A multi-layer convolution operation is performed on the graph data using a graph convolutional neural network.

[0064] It should be further explained that an adaptive adjacency matrix is ​​constructed based on the three-dimensional feature matrix, and the adaptive adjacency matrix is ​​determined by the similarity between each blockchain node in the three-dimensional feature matrix, wherein the formula for constructing the similarity between each blockchain node in the three-dimensional feature matrix is:

[0065] ;

[0066] Among them, q(dp) represents the similarity between the d-th blockchain node and the p-th blockchain node; The transaction amount of the dth blockchain node in the tth transaction time period; represents the average transaction amount of the dth blockchain node; The transaction amount of the pth blockchain node in the tth transaction time period; represents the average transaction amount of the p-th blockchain node; The transaction frequency of the dth blockchain node in the tth transaction time period; represents the average transaction frequency of the dth blockchain node; The transaction frequency of the pth blockchain node in the tth transaction time period; represents the average transaction frequency of the pth blockchain node; s represents the total number of transaction time periods, , Represents the weight factor.

[0067] The similarity between each blockchain node is used as the attention weight between each blockchain node. The graph convolutional neural network is used to perform multi-layer convolution operations on the graph data. The attention weight is combined with each blockchain node for feature aggregation, and the self-representation of the blockchain node is updated. The embedded representation of the blockchain node is obtained according to the neighbor aggregation mechanism. The formula for aggregating adjacent nodes is:

[0068] ,in, represents the embedded representation of blockchain nodes, ) represents the activation function, represents the feature transformation parameter matrix, Represents a collection of other blockchain nodes.

[0069] After multi-layer graph convolution operations, the collection order of spatial features of each blockchain node in the three-dimensional feature matrix is ​​obtained according to the transaction time period in the three-dimensional feature matrix, and the features with spatial features of each blockchain node in the three-dimensional feature matrix are input into the long short-term memory network according to the collection order. The spatiotemporal features of each blockchain node are output through the long short-term memory network, and so on, the spatiotemporal features of each blockchain node corresponding to each different identity information in the blockchain network are obtained;

[0070] A transaction data authenticity assessment model is built based on the RBF neural network, and the spatiotemporal characteristics of each blockchain node corresponding to different identity information in the blockchain network are used as the test set and training set of the transaction data authenticity assessment model;

[0071] Input the training set into the transaction data authenticity assessment model for training until the loss function training is stable, and save the model parameters, test the transaction data authenticity assessment model through the test set until it meets the preset requirements, and output the transaction data authenticity assessment model;

[0072] According to the transaction data authenticity assessment model, the spatiotemporal feature prediction data of different identities are output.

[0073] It should be further explained that, in the specific implementation process, the transaction data authenticity evaluation model is used to output the threshold evaluation intervals of various types of features, the transaction data in the new blockchain node is feature extracted, various types of features are generated, and the process of comparing each type of feature with the corresponding threshold evaluation intervals of each type of feature includes:

[0074] Obtaining various types of feature threshold evaluation intervals for different identities based on the spatiotemporal feature prediction data of different identities, wherein the various types of feature threshold evaluation intervals include transaction amount threshold intervals and transaction frequency threshold intervals corresponding to different unmanned vending machine location data in different time periods;

[0075] According to the identity information in the new blockchain node, the corresponding feature threshold evaluation intervals of each type are obtained; according to the transaction data in the new blockchain node, the vending machine location data, the time period of the transaction time period, the transaction amount and the transaction frequency are obtained; the transaction amount threshold interval and the transaction frequency threshold interval corresponding to the vending machine location data and the time period of the transaction time period are obtained; and the transaction amount and transaction frequency are compared with the transaction amount threshold interval and the transaction frequency threshold interval.

[0076] It should be further explained that, in the specific implementation process, the process of conducting a secondary identity recognition test and performing a real-time update of the transaction data authenticity assessment model or the new blockchain node removal operation based on the test results of the secondary identity recognition test includes:

[0077] The transaction security cloud monitoring center is equipped with an identity recognition biometric database, which includes biometric data pre-entered by users, including face data, iris data, etc. The unmanned vending machine sends an identity secondary recognition test instruction through an interactive interface, and the user performs a biometric data recognition operation according to the identity secondary recognition test instruction, generates the user's temporary biometric data and sends it to the identity recognition biometric database for biometric data matching, and determines whether there is biometric data in the identity recognition biometric database that is consistent with the temporary biometric data;

[0078] If it exists, the spatiotemporal characteristics of the new blockchain node are obtained, and based on the spatiotemporal characteristics of each blockchain node corresponding to each different identity information in the blockchain network and the test set and training set of the new blockchain node as the transaction data authenticity assessment model, the spatiotemporal characteristics of the new blockchain node are added to the test set and the training set to obtain a new test set and training set, and the transaction data authenticity assessment model is retrained and updated based on the new test set and training set to obtain an updated transaction data authenticity assessment model;

[0079] If it does not exist, an identity authentication failure message is sent to the vending machine and the new blockchain node is removed.

[0080] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A transaction security monitoring method for an unmanned vending machine, characterized in that: The following steps are involved: Step S1: Build a transaction security cloud monitoring center, use the unmanned vending machine as a blockchain node, and collect the transaction data encrypted and uploaded by the unmanned vending machine; Step S2: when a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the number of other blockchain nodes in the blockchain network that are consistent with the identity information in the new blockchain node is obtained, and a secondary identity recognition test or transaction data authenticity assessment is performed based on the number; Step S3: construct a transaction data authenticity assessment model based on the graph convolutional long short-term memory network, output the transaction data in the new blockchain node corresponding to the threshold assessment interval of each type of feature through the transaction data authenticity assessment model, extract features of the transaction data in the new blockchain node, generate various types of features, compare each type of feature with the corresponding threshold assessment interval of each type of feature, and perform secondary identity recognition test or product outbound operation according to the comparison result; Step S4: Perform a secondary identity recognition test, and update the transaction data authenticity assessment model in real time or remove new blockchain nodes based on the test results of the secondary identity recognition test.

2. A transaction security monitoring method for an unmanned vending machine according to claim 1, characterized in that: The process of building a transaction security cloud monitoring center includes: A transaction security cloud monitoring center is constructed using blockchain technology. The transaction security monitoring center is provided with a number of blockchain nodes. The blockchain nodes are communicatively connected to the unmanned vending machines within a preset range, and each blockchain node is linked to each other to form a blockchain network. Each unmanned vending machine is provided with a data uplink end, and the data uplink segment is used to upload transaction data to the blockchain node.

3. A transaction security monitoring method for an unmanned vending machine according to claim 2, characterized in that: The unmanned vending machine is provided with an interactive interface, through which the user performs order selection operations, scan code payment operations and biometric data recognition operations; after the user performs the scan code payment operation through the interactive interface, the user's identity information and transaction data are obtained according to the order scan code payment operation, and the transaction data includes the transaction amount, transaction frequency, transaction time period and unmanned vending machine location data, and the identity information and transaction data are encrypted and uploaded to the blockchain node.

4. A transaction security monitoring method for an unmanned vending machine according to claim 3, characterized in that: The process of encrypting and uploading identity information and transaction data to the blockchain node includes: The public key and private key of each vending machine are preset through an asymmetric encryption algorithm, the identity information and transaction data are preprocessed in data format and converted into binary data of fixed length. The binary data is encrypted by the private key of the vending machine to generate an encrypted data packet, which is uploaded to the blockchain node. The blockchain node decrypts the received encrypted data packet through the public key of the vending machine to generate identity information and transaction data. Subsequently, a new blockchain node is added to the end of the blockchain network, and the identity information and transaction data are packaged into the new blockchain node.

5. A transaction security monitoring method for an unmanned vending machine according to claim 4, characterized in that: When a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the number of other blockchain nodes in the blockchain network that are consistent with the identity information in the new blockchain node is obtained, and the process of performing a secondary identity recognition test or transaction data authenticity assessment based on the number includes: When a new blockchain node is added to the end of the blockchain network, the identity information and transaction data in the new blockchain node are extracted, the identity information in the new blockchain node is matched with the identity information of other blockchain nodes in the blockchain network, and other blockchain nodes in the blockchain network whose identity information is consistent with the identity information in the new blockchain node are obtained, and the node number of the other blockchain nodes is obtained, and a node number threshold is preset. If the node number of the other blockchain nodes is less than the node number threshold, a secondary identity recognition test is performed; If the number of nodes of other blockchain nodes is greater than or equal to the node number threshold, the identity information in the new blockchain node is input into the transaction data authenticity assessment model, and the transaction data authenticity assessment model outputs the threshold assessment intervals of each type of feature, and the transaction data in the new blockchain node is feature extracted to generate each type of feature, and each type of feature is compared with the corresponding threshold assessment interval of each type of feature; If all types of features are within the corresponding threshold assessment intervals of each type of feature, the product is shipped out; If each type of feature is not within the corresponding threshold evaluation interval of each type of feature, a secondary identity recognition test is performed, and the transaction data authenticity evaluation model is updated in real time based on the test results of the secondary identity recognition test.

6. A transaction security monitoring method for an unmanned vending machine according to claim 5, characterized in that: The process of building a transaction data authenticity assessment model based on graph convolutional long short-term memory network includes: A transaction data authenticity assessment model is constructed based on a graph convolutional long short-term memory network, the identity information and transaction data of each blockchain node in the blockchain network are retrieved, the blockchain nodes are aggregated based on the identity information, the features of different transaction time periods in several blockchain nodes with the same identity information are spliced ​​according to the blockchain nodes, and a three-dimensional feature matrix is ​​constructed. The features include transaction amount and transaction frequency. The three-dimensional feature matrix includes three dimensions: features, transaction time period, and vending machine location data; An adaptive adjacency matrix is ​​constructed based on the three-dimensional feature matrix. The adaptive adjacency matrix is ​​determined by the similarity between each blockchain node in the three-dimensional feature matrix. Graph data is constructed based on the three-dimensional feature matrix and the adaptive adjacency matrix. A multi-layer convolution operation is performed on the graph data using a graph convolutional neural network. After multi-layer graph convolution operations, the collection order of spatial features of each blockchain node in the three-dimensional feature matrix is ​​obtained according to the transaction time period in the three-dimensional feature matrix, and the features with spatial features of each blockchain node in the three-dimensional feature matrix are input into the long short-term memory network according to the collection order. The spatiotemporal features of each blockchain node are output through the long short-term memory network, and so on, the spatiotemporal features of each blockchain node corresponding to each different identity information in the blockchain network are obtained; A transaction data authenticity assessment model is built based on the RBF neural network, and the spatiotemporal characteristics of each blockchain node corresponding to different identity information in the blockchain network are used as the test set and training set of the transaction data authenticity assessment model; Input the training set into the transaction data authenticity assessment model for training until the loss function training is stable, and save the model parameters, test the transaction data authenticity assessment model through the test set until it meets the preset requirements, and output the transaction data authenticity assessment model; According to the transaction data authenticity assessment model, the spatiotemporal feature prediction data of different identities are output.

7. A transaction security monitoring method for an unmanned vending machine according to claim 6, characterized in that: The process of outputting each type of feature threshold evaluation interval through the transaction data authenticity evaluation model, extracting features from the transaction data in the new blockchain node, generating each type of feature, and comparing each type of feature with the corresponding each type of feature threshold evaluation interval includes: Obtaining various types of feature threshold evaluation intervals for different identities based on the spatiotemporal feature prediction data of different identities, wherein the various types of feature threshold evaluation intervals include transaction amount threshold intervals and transaction frequency threshold intervals corresponding to different unmanned vending machine location data in different time periods; According to the identity information in the new blockchain node, the corresponding feature threshold evaluation intervals of each type are obtained; according to the transaction data in the new blockchain node, the vending machine location data, the time period of the transaction time period, the transaction amount and the transaction frequency are obtained; the transaction amount threshold interval and the transaction frequency threshold interval corresponding to the vending machine location data and the time period of the transaction time period are obtained; and the transaction amount and transaction frequency are compared with the transaction amount threshold interval and the transaction frequency threshold interval.

8. A transaction security monitoring method for an unmanned vending machine according to claim 7, characterized in that: The process of performing a secondary identity recognition test and performing a real-time update of a transaction data authenticity assessment model or a new blockchain node removal operation based on the test results of the secondary identity recognition test includes: The transaction security cloud monitoring center is provided with an identity recognition biometric database, which includes biometric data pre-entered by the user. The unmanned vending machine sends an identity secondary recognition test instruction through an interactive interface. The user performs a biometric data recognition operation according to the identity secondary recognition test instruction, generates the user's temporary biometric data and sends it to the identity recognition biometric database for biometric data matching, and determines whether there is biometric data in the identity recognition biometric database that is consistent with the temporary biometric data; If it exists, the spatiotemporal characteristics of the new blockchain node are obtained, and based on the spatiotemporal characteristics of each blockchain node corresponding to each different identity information in the blockchain network and the test set and training set of the new blockchain node as the transaction data authenticity assessment model, the spatiotemporal characteristics of the new blockchain node are added to the test set and the training set to obtain a new test set and training set, and the transaction data authenticity assessment model is retrained and updated based on the new test set and training set to obtain an updated transaction data authenticity assessment model; If it does not exist, an identity authentication failure message is sent to the vending machine and the new blockchain node is removed.

Images