Adaptive cross-blockchain anonymous account supervision method and device based on spatiotemporal graph learning

Abstract

The application discloses a kind of adaptive cross-blockchain anonymous account supervision method and device based on space-time graph learning, facing the time dynamicity and spatial heterogeneity of blockchain anonymous account behavior, constructs anonymous account space-time behavior graph model;Based on anonymous account space-time behavior graph model, for single anonymous account space-time behavior graph, utilize the space-time heterogenous graph learning mechanism designed to extract the space-time behavior characteristics in single anonymous account space-time behavior graph;Based on anonymous account space-time behavior graph model, for multiple anonymous account space-time behavior graphs, utilize the space-time heterogenous graph twin network designed to measure the space-time behavior characteristics between different anonymous accounts, obtain the space-time behavior similarity between different anonymous accounts;Face different blockchain environments, utilize the similarity perception graph transfer learning mechanism designed to adaptively optimize the measurement of the space-time behavior similarity between different anonymous accounts under cross-blockchain chain environment, realize adaptive cross-blockchain anonymous account identity association.The purpose of the present application is to accurately model the real-time and diversified transaction behavior of blockchain anonymous accounts, improve the real-time anonymous account transaction feature expression capability, effectively mine anonymous account space-time behavior characteristics, and achieve adaptive and efficient anonymous account identity association in cross-blockchain transaction ecology.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of blockchain security, and particularly relates to a self-adaptive cross-blockchain anonymous account supervision method and device based on space-time graph learning. BACKGROUND

[0002] With the rapid development of decentralized finance in the blockchain system, on-chain anonymous enhancement services represented by coin mixers are widely deployed and applied. These services are used by a large number of on-chain criminals to effectively confuse the flow of transaction funds. Criminals often use multiple sub-accounts to hide attack transactions and confuse attack benefits with the help of on-chain anonymous enhancement services, and complete contract vulnerability exploitation and illegal benefit money laundering without exposing the real identity, so that the blockchain system becomes a breeding ground for illegal activities. Therefore, it is urgent to supervise the blockchain system. Due to the transparency of the blockchain system, the complete transaction history of each on-chain account is available to the supervisory authorities, so that it is possible to identify and track malicious participants. However, the traditional account identity classification supervision scheme classifies account identities depending on known account behavior patterns, and it is difficult to identify unknown account behavior patterns hidden under on-chain anonymous enhancement services.

[0003] The account identity association supervision scheme associates multiple anonymous sub-accounts controlled by the same criminal based on the similarity of transaction patterns and behaviors, so as to identify the behavior patterns of unknown accounts in the environment of on-chain anonymous enhancement services. However, 1) the real blockchain transaction environment has the characteristics of heterogeneity and real-time change, and the existing account identity association supervision scheme usually models static and homogeneous account transaction features, which is difficult to accurately represent the dynamic transaction behavior features of the account; 2) the existing account identity association supervision scheme is mostly based on heuristic rules and is designed for a specific blockchain ecosystem, which makes it difficult to achieve migratory account identity association across blockchains; 3) the existing account identity association supervision scheme only simply mines the topological behavior features of on-chain account transactions, and lacks in-depth mining of the space-time features of account transaction behaviors. SUMMARY

[0004] In view of the problems in the prior art, the application provides a self-adaptive cross-blockchain anonymous account supervision method and device based on space-time graph learning, which aims to accurately model the real-time and diversified transaction behaviors of blockchain anonymous accounts, improve the expression ability of real-time anonymous account transaction features, effectively mine the space-time behavior features of anonymous accounts, and realize adaptive and efficient anonymous account identity association in a cross-blockchain transaction ecosystem, thereby realizing effective and safe supervision of criminal anonymous sub-accounts in a large-scale on-chain transaction.

[0005] To solve the above technical problems, the application is implemented by the following technical scheme:

[0006] According to a first aspect of the present invention, a method for adaptive cross-blockchain anonymous account supervision based on spatiotemporal graph learning is provided, comprising:

[0007] Aiming at the temporal dynamics and spatial heterogeneity of blockchain anonymous account behavior, a spatiotemporal behavior graph model of anonymous accounts is constructed;

[0008] Based on the anonymous account spatiotemporal behavior graph model, for a single anonymous account spatiotemporal behavior graph, the designed temporal heterogeneous graph learning mechanism is used to extract the spatiotemporal behavior features within the spatiotemporal behavior graph of the single anonymous account;

[0009] Based on the anonymous account spatiotemporal behavior graph model, for multiple anonymous account spatiotemporal behavior graphs, the designed temporal heterogeneous graph twin network is used to measure the spatiotemporal behavior characteristics between different anonymous accounts, and the spatiotemporal behavior similarity between different anonymous accounts is obtained;

[0010] Aiming at different blockchain environments, the designed similarity perception graph-based transfer learning mechanism is used to adaptively tune the measurement of spatiotemporal behavior similarity between different anonymous accounts in cross-blockchain environments, thereby realizing adaptive cross-blockchain anonymous account identity association.

[0011] In a possible implementation of the first aspect, the temporal dynamics and spatial heterogeneity of blockchain anonymous account behavior are oriented to the construction of an anonymous account spatiotemporal behavior graph model, specifically:

[0012] Based on the temporal dynamics of on-chain account transaction behavior and the heterogeneity of transaction types and transaction accounts, a native account spatiotemporal behavior graph model is constructed;

[0013] The native account spatiotemporal behavior graph model is denoised based on a heuristic graph pruning algorithm to obtain the anonymous account spatiotemporal behavior graph model.

[0014] In a possible implementation of the first aspect, the native account spatiotemporal behavior graph model is specifically:

[0015]

[0016] Where, It represents the self-blockchain transaction network centered on the anonymous account a on the to-be-supervised chain, i.e., the native account spatiotemporal behavior graph model of the anonymous account a. Representing the self-blockchain transaction network The depth of the breadth-first search traversal; V represents the set of on-chain address nodes traversed in the breadth-first search; E represents the set of all on-chain transactions traversed in the breadth-first search; Indicates the address node set V on the chain to the address type on the chain is a mapping from the set of on-chain transactions E to the set of on-chain transaction types is a mapping from the set of on-chain transactions E to the set of on-chain transaction types is a mapping from the set of on-chain transactions E to the set of on-chain transaction types is a mapping from the set of on-chain transactions E to the set of on-chain transaction times s denotes the transaction start time, denotes the transaction duration.

[0017] The heuristic graph pruning algorithm is used to denoise the native account spatio-temporal behavior graph model, and specifically:

[0018] An overload node set in the native account spatio-temporal behavior graph model is identified, and the overload node set in the native account spatio-temporal behavior graph model is:

[0019]

[0020] wherein Ψ(i) represents the on-chain address type of node i; D + (i) represents the in-degree of node i; D - (i) represents the out-degree of node i. denotes the tolerance value of the overload node.

[0021] A set of stale node neighbors under a branch subgraph connected to the overload node is classified, and the set of stale node neighbors under the branch subgraph connected to the overload node is:

[0022]

[0023] wherein denotes the neighbor node found by the first-order breadth-first search of the overload node m in the native account spatio-temporal behavior graph model . denotes the first neighbor nodes in the neighbor nodes that perform on-chain transactions earliest. is a denoising coefficient.

[0024] The branch subgraph connected to the stale node neighbor is pruned, and the denoising of the native account spatio-temporal behavior graph model is completed to obtain the anonymous account spatio-temporal behavior graph model.

[0025] In a possible implementation manner of the first aspect, the designed timing heterogeneous graph learning mechanism is specifically:

[0026] A heterogeneous timing edge aggregation method is designed for the edge signal in the anonymous account spatio-temporal behavior graph model, and the initial node features of each graph node are calculated.

[0027] The initial node feature obtained according to the heterogeneous time sequence edge aggregation method is taken as a point aggregation initial feature, a heterogeneous time sequence point aggregation method is designed for an intra-account anonymous space-time behavior graph model point signal, and node embedding of each graph node is calculated;

[0028] According to the node embedding of each graph node, a graph pooling method is designed for an intra-account anonymous space-time behavior graph model subgraph signal, and graph embedding of the account anonymous space-time behavior graph model is calculated.

[0029] In a possible implementation manner of the first aspect, the heterogeneous time sequence edge aggregation method designed for the intra-account anonymous space-time behavior graph model edge signal is specifically:

[0030] For a given node u in the account anonymous space-time behavior graph model, denotes a given edge type a neighbor edge set of u, each edge an attention score of the edge is calculated as follows:

[0031]

[0032] In the formula, is a transpose matrix of an attention parameter; f i is vectorized transaction information of the edge i in the edge type The attention score of the edge i is calculated using a nonlinear activation function Relu; the attention-based importance weight of the edge i is further normalized by a Softmax function is calculated as follows:

[0033]

[0034] According to the attention-based importance weight of the neighbor edge set a multi-head attention method is applied to aggregate information of the neighbor edges, and edge aggregation of the node u in the edge type is calculated as follows:

[0035]

[0036]

[0037] In the formula, denotes a connection operation; Relu denotes a Relu nonlinear activation function; H is a number of attention heads used in the multi-head attention method; for each edge aggregation a timestamp thereof is defined as the latest interaction inis calculated as follows:

[0038]

[0039] Aggregate by edge Timestamp Sort the edge aggregation in ascending order, and the initial node feature of each node u is calculated as follows:

[0040]

[0041]

[0042] q u =LSTM([Sequence u ])

[0043] In the formula, LSTM is a long short-term memory network; Sort + Indicates that the time series is sorted in ascending order.

[0044] In a possible implementation of the first aspect, the method for designing heterogeneous time-series point aggregation for interior point signals in an anonymous account spatiotemporal behavior graph model is specifically as follows:

[0045] For a given node x in the anonymous account spatiotemporal behavior graph model, Node type The set of adjacent nodes in the node Time attribute From the adjacent side Latest timestamp It is calculated as follows:

[0046]

[0047] According to time attributes Generate the temporal importance weight of node u It is calculated as follows:

[0048]

[0049] According to the time importance weight Generate Node Type Intra-class point aggregation of midpoint x It is calculated as follows:

[0050]

[0051] Where, MLP (k) Indicates a multi-layer perceptron with k layers; Is the node x in the node type The k-th layer embedding result in ; is the input of the kth layer, and Neighbor The temporal importance weight of , indicating that the influence of neighbors on node x changes over time;

[0052] According to the intra-class point aggregation, the node embedding of node x in type β Attention score The calculation is as follows:

[0053]

[0054] Where LeakyRelu is the zero negative correction activation function; is the transposed attention parameter;

[0055] According to the node embedding of the node x in type β The attention score of node x, the inter-class point aggregation, is the node embedding, which is calculated as follows:

[0056]

[0057] Where, ρ x is the between-class point aggregation of node x.

[0058] In a possible implementation of the first aspect, the graph pooling method for subgraph signals in the anonymous account spatiotemporal behavior graph model is specifically:

[0059]

[0060] Where, ρ i is the heterogeneous temporal node embedding of node i; a i is the attention weight of node i, a i The specific calculation is as follows:

[0061]

[0062] Where, is the transpose of the learnable attention vector; W is the learnable weight matrix; V is the node set of the anonymous account spatiotemporal graph model.

[0063] In a possible implementation of the first aspect, the designed temporal heterogeneous graph twin network is specifically:

[0064] Construct a graph-level twin network for multiple anonymous account spatiotemporal behavior graphs. For a given anonymous account spatiotemporal behavior graph j, the graph embedding f j The calculation is as follows:

[0065]

[0066] Where Pool is the graph pooling method; V j is the node set of the anonymous account spatiotemporal behavior graph j; The node v is embedded in the last layer after L layers of heterogeneous time series edge aggregation and heterogeneous time series point aggregation:

[0067]

[0068] Where, HTAGG n It is a heterogeneous time series point aggregation method; is the set of neighbor nodes of node v; is the aggregate edge embedding of node v at level l+1:

[0069]

[0070] Where, HTAGG e It is a heterogeneous time series edge aggregation method; is the edge embedding from node u to node v at layer l;

[0071] Initialize with a random vector;

[0072] The designed temporal heterogeneous graph twin network is used to measure the spatiotemporal behavior characteristics between different anonymous accounts, specifically:

[0073] According to the spatiotemporal behavior graph of the anonymous account to be compared and The graph embedding f q and f p , use Euclidean distance to measure the spatiotemporal behavior similarity between different anonymous accounts:

[0074]

[0075] Where d is the graph embedding f q and f p The vector dimension of .

[0076] In a possible implementation of the first aspect, the method of adaptively tuning the measure of spatiotemporal behavior similarity between different anonymous accounts in a cross-blockchain environment using the designed similarity perception graph transfer learning mechanism is specifically as follows:

[0077] For a single blockchain scenario, pre-train the anonymous account spatiotemporal behavior graph model to obtain a pre-trained basic model. is the dataset on the source blockchain, and is the spatiotemporal behavior graph of the anonymous account for the i-th query-comparison sample pair, N represents whether the self nodes in the two graphs, i.e. the contrast account and the query account, are linked to the same off-chain identity, N S represents the number of query-contrast pairs in the dataset constructed from the source blockchain; the pre-training aims to minimize the loss function of the time-heterogeneous graph twin network on the source dataset

[0078]

[0079] wherein, and are the graph embeddings of and respectively; is the Euclidean distance between the two graph embeddings, and the parameters θ of the time-heterogeneous graph twin network are updated by gradient descent method:

[0080]

[0081] wherein, η is the learning rate;

[0082] According to the pre-trained base model, cross-blockchain model optimization is performed based on a similar perception graph transfer learning mechanism, is the dataset constructed from the target blockchain, and the target is to minimize the similar perception loss function on the dataset

[0083]

[0084] wherein, N T is the number of query-contrast pairs in the target blockchain dataset.

[0085] According to the second aspect of the present application, an adaptive cross-blockchain anonymous account supervision device based on spatio-temporal graph learning is provided, comprising:

[0086] A construction module is configured to construct a spatio-temporal behavior graph model of anonymous accounts in view of the time dynamics and spatial heterogeneity of the behavior of blockchain anonymous accounts.

[0087] An extraction module is configured to extract spatio-temporal behavior features within a single anonymous account spatio-temporal behavior graph based on the anonymous account spatio-temporal behavior graph model and using a designed time-heterogeneous graph learning mechanism for the single anonymous account spatio-temporal behavior graph.

[0088] A measurement module is configured to measure spatio-temporal behavior features between different anonymous accounts based on the anonymous account spatio-temporal behavior graph model and using a designed time-heterogeneous graph twin network for multiple anonymous account spatio-temporal behavior graphs, to obtain the spatio-temporal behavior similarity between different anonymous accounts.

[0089] ​The tuning module is used for different blockchain environments. It uses the designed similarity perception graph-based transfer learning mechanism to adaptively tune the measurement of spatiotemporal behavior similarity between different anonymous accounts in cross-blockchain environments, thereby realizing adaptive cross-blockchain anonymous account identity association.

[0090] According to a third aspect of the present invention, a device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for adaptive cross-blockchain anonymous account supervision based on spatiotemporal graph learning is implemented.

[0091] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning is implemented.

[0092] Compared with the prior art, the present invention has at least the following beneficial effects:

[0093] (1) This paper proposes a spatiotemporal behavior graph model for anonymous accounts, which not only effectively captures the temporal dynamics and spatial heterogeneity of on-chain account transaction behaviors, but also designs a heuristic rule-based graph pruning algorithm to denoise irrelevant transaction subgraphs, accurately modeling the real-time and diversified transaction behaviors of anonymous accounts on the blockchain, while reducing the space overhead of graph learning training.

[0094] (2) This paper proposes a time-series heterogeneous graph learning mechanism in the blockchain environment. For a single anonymous account's spatiotemporal behavior graph, it fully mines its spatiotemporal behavior characteristics from the perspective of time-series heterogeneous edge signals, point signals, and subgraph signals, thereby improving the ability to express the characteristic behavior of blockchain anonymous account transactions.

[0095] (3) The present invention proposes a twin network architecture for time-series heterogeneous graphs, constructs a graph-level twin network for the spatiotemporal behavior graphs of multiple anonymous accounts, and realizes the parallel measurement of the spatiotemporal behavior similarity between anonymous accounts on different chains in the same Euclidean space, thereby reducing the time overhead of learning and training time-series heterogeneous graphs and improving the efficiency of large-scale graph-level blockchain anonymous account behavior analysis.

[0096] (4) The present invention proposes a similarity-aware graph transfer learning mechanism. By pre-training the model in a single blockchain network and adjusting the model similarity metric in real time in a cross-blockchain environment, the problem of shortage of labeled data in graph learning of existing models in cross-blockchain scenarios is alleviated. Adaptive and efficient anonymous account identity association is achieved in the cross-blockchain ecosystem, and effective supervision of criminal anonymous sub-accounts is completed.

[0097] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0098] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application, the following will briefly introduce the drawings needed to be used in the specific embodiment description. Obviously, the drawings described below are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0099] Figure 1 The flowchart of the adaptive cross-blockchain anonymous account supervision method based on spatio-temporal graph learning of the present application;

[0100] Figure 2 The flowchart of the adaptive cross-blockchain anonymous account supervision method based on spatio-temporal graph learning of the embodiment of the present application;

[0101] Figure 3 The native account spatio-temporal behavior graph model diagram of the embodiment of the present application;

[0102] Figure 4 The design diagram of the time sequence heterogeneous edge aggregation method in the time sequence heterogeneous graph learning mechanism of the embodiment of the present application;

[0103] Figure 5 The design diagram of the time sequence heterogeneous point aggregation method in the time sequence heterogeneous graph learning mechanism of the embodiment of the present application;

[0104] Figure 6 The time sequence heterogeneous graph twin network model diagram of the embodiment of the present application. DETAILED DESCRIPTION

[0105] In order to make the objectives, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the present application will be described in detail below in combination with the drawings. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0106] As a specific embodiment of the present application, as shown in Figure 1 and Figure 2 The present application provides an adaptive cross-blockchain anonymous account supervision method based on spatio-temporal graph learning, which specifically includes the following steps:

[0107] Step 1, facing the time dynamics and spatial heterogeneity of the behavior of the blockchain anonymous account, constructing an anonymous account spatio-temporal behavior graph model to accurately model the spatio-temporal behavior of the account on the chain.

[0108] In an implementation manner, the time dynamics and spatial heterogeneity of the blockchain-oriented anonymous account behavior are constructed into an anonymous account space-time behavior graph model, specifically including:

[0109] Step 1.1, according to the time dynamics of the on-chain account transaction behavior, and the transaction type and transaction account heterogeneity, a native account space-time behavior graph model is constructed.

[0110] In the embodiment, the native account space-time behavior graph model is specifically:

[0111]

[0112] In the formula, indicates the self-blockchain transaction network extended with the to-be-regulated on-chain anonymous account a as the center, that is, the native account space-time behavior graph model of the anonymous account a; indicates the self-blockchain transaction network The depth of the breadth-first search traversal; V indicates the set of on-chain address nodes traversed in the breadth-first search; E indicates the set of all on-chain transactions traversed in the breadth-first search; indicates the mapping from the set of on-chain address nodes V to the on-chain address type , ε is a real external owner account, b is a blockchain robot account, and s is a blockchain smart contract account; indicates the mapping from the set of on-chain transactions E to the on-chain transaction type , ∈ is an external transaction, c is a contract transaction, ι is an internal transaction, and τ is a token transaction; Γ:E→Ω indicates the mapping from the set of on-chain transactions E to the on-chain transaction time , ξ s indicates the transaction start time, indicates the duration of the transaction.

[0113] More specifically, the native account space-time behavior graph model is as shown in Figure 3 The time dynamics is reflected in the native account space-time behavior graph, in which the to-be-regulated on-chain anonymous account continuously generates new transactions, forming new transaction nodes and transaction edges, resulting in continuous evolution of the transaction behavior of the to-be-regulated on-chain anonymous account; the spatial heterogeneity is reflected in the heterogeneous points (multi-type on-chain addresses) and the heterogeneous edges (multi-type on-chain transactions), which are mapped to model the heterogeneity of the on-chain address type in the native account space-time behavior graph, the mapping is from the address set to the address type wherein the real external owner account ε, the blockchain robot account b, and the blockchain smart contract account s are defined as:

[0114] Definition 1: A real external owner account is an on-chain account controlled by a real person off-chain through a corresponding private key. The real person off-chain freely decides when, how, and with whom to transact.

[0115] Definition 2: A blockchain robot account is an on-chain account whose corresponding private key is controlled by a preset script to complete automated transaction control. It often plays the role of an automated trading robot in the blockchain ecosystem.

[0116] Definition 3: A blockchain smart contract account is a self-executing public script program that does not hold a private key and can automatically execute its preset script functions in the blockchain virtual machine. It is controlled by the smart contract code and its associated data storage.

[0117] Mapping Used to model the heterogeneity of on-chain transaction types in the native account spatiotemporal behavior graph, this mapping maps the transaction set ε to its type Among them, external transactions ∈, contract transactions c, internal transactions ι and token transactions τ are defined as:

[0118] Definition 4: External transactions are initiated and received by non-blockchain smart contract accounts and are used to transfer cryptocurrencies between non-blockchain smart contract accounts;

[0119] Definition 5: Contract transaction, initiated by a non-blockchain smart contract account and received by a blockchain smart contract account, is used to request blockchain smart contract services;

[0120] Definition 6: Internal transactions are initiated by blockchain smart contract accounts and received by non-blockchain smart contract accounts, and are used to withdraw cryptocurrencies hosted within the blockchain smart contract service.

[0121] Definition 7: Token transaction, the transaction object is blockchain token, which is used to transfer token assets between blockchain accounts.

[0122] Step 1.2: De-noise the native account spatiotemporal behavior graph model based on a heuristic graph pruning algorithm to obtain the anonymous account spatiotemporal behavior graph model.

[0123] In this embodiment, the native account spatiotemporal behavior graph model is denoised based on the heuristic graph pruning algorithm, specifically as follows:

[0124] First, identify the set of overloaded nodes in the native account spatiotemporal behavior graph model:

[0125]

[0126] Where Ψ(i) represents the on-chain address type of node i; D + (i) represents the in-degree of node i; D -(i) represents the out-degree of node i; Indicates the tolerance value of overloaded nodes.

[0127] Next, classify the set of stale node neighbors under the branch subgraph connected to the overloaded node:

[0128]

[0129] Where, Represents the spatiotemporal behavior graph model of the overloaded node m in the native account The neighbor nodes found by the first-order breadth-first search; Indicates the earliest on-chain transaction among neighboring nodes. neighbor nodes; is the denoising coefficient.

[0130] Finally, the branch subgraph connected to the neighbors of the corrupted node is pruned to complete the denoising of the native account spatiotemporal behavior graph model and obtain the anonymous account spatiotemporal behavior graph model.

[0131] Step 2: Based on the anonymous account spatiotemporal behavior graph model, for a single anonymous account spatiotemporal behavior graph, the designed temporal heterogeneous graph learning mechanism is used to extract the spatiotemporal behavior features within the spatiotemporal behavior graph of the single anonymous account.

[0132] As a preferred embodiment, the temporal heterogeneous graph learning mechanism of the design is specifically as follows:

[0133] Step 2.1: Design a heterogeneous temporal edge aggregation method for edge signals within the anonymous account spatiotemporal behavior graph model to calculate the initial node features of each graph node.

[0134] Specifically, if Figure 4 As shown in FIG, in this embodiment, a heterogeneous temporal edge aggregation method is designed for edge signals in an anonymous account spatiotemporal behavior graph model, specifically including:

[0135] Step 2.1.1: Based on the anonymous account spatiotemporal behavior graph model, perform attention-based aggregation on the adjacent edges of each edge type. Introduce the transaction information of the adjacent edges into the edge feature aggregation process to obtain the intra-class edge aggregation. Specifically:

[0136] For a given node u in the anonymous account spatiotemporal behavior graph model, Indicates a given edge type The set of adjacent edges within u, each edge Attention score The calculation is as follows:

[0137]

[0138] Where, is the transposed matrix of attention parameters; f i Is the edge type The vectorized transaction information of edge i in the graph is used to calculate the attention score of edge i using the nonlinear activation function ReLU. Further normalized by the Softmax function, the importance weight of edge i based on the attention mechanism is The calculation is as follows:

[0139]

[0140] Based on the adjacent edge set The importance weight based on attention is applied, and the multi-head attention method is used to aggregate the information of adjacent edges. The node u is in the edge type Edge aggregation within The calculation is as follows:

[0141]

[0142]

[0143] Where, Represents the connection operation; Relu represents the Relu nonlinear activation function; H is the number of attention heads used in the multi-head attention method.

[0144] Step 2.1.2: Based on the intra-class edge aggregation, a long short-term memory network is used to fuse heterogeneous intra-class edge aggregations in chronological order to generate initial node features in the anonymous account spatiotemporal behavior graph model, specifically:

[0145] Aggregate the edges within each edge type class As time series input, this embodiment is for each Assign timestamp This timestamp is the time when node u is in the neighborhood and edge type The latest interaction time is calculated as follows:

[0146]

[0147] Aggregate by edge Timestamp Sort the edge aggregation in ascending order and calculate the initial node features of each node u as follows:

[0148]

[0149]

[0150] q u=LSTM([Sequence u ])

[0151] In the formula, LSTM is a long short-term memory network; Sort + Indicates that the time series is sorted in ascending order.

[0152] Step 2.2: Using the initial node features obtained by the heterogeneous time-series edge aggregation method as the initial features for point aggregation, a heterogeneous time-series point aggregation method is designed for point signals within the anonymous account spatiotemporal behavior graph model, and the node embedding of each graph node is calculated.

[0153] Specifically, if Figure 5 As shown, in this embodiment, a heterogeneous time series point aggregation method is designed for the internal point signals of the anonymous account spatiotemporal behavior graph model, specifically including:

[0154] Step 2.2.1: Using the node features generated by heterogeneous temporal edge aggregation as the initial features for point aggregation, a temporal importance mechanism is designed to generate weights for neighboring nodes, which can effectively evaluate the impact of neighboring nodes on the target node.

[0155] In this embodiment, the timing importance mechanism is as follows:

[0156] For a given node x in the anonymous account spatiotemporal behavior graph model, Node type The set of adjacent nodes in the node Time attribute From the adjacent side Latest timestamp It is calculated as follows:

[0157]

[0158] According to time attributes Generate the temporal importance weight of node u It is calculated as follows:

[0159]

[0160] Step 2.2.2: Based on the temporal importance weight, a graph isomorphic network is used to perform point aggregation within a single node type and calculate the intra-class point aggregation, as follows:

[0161] According to the time importance weight Generate Node Type Intra-class point aggregation of midpoint x It is calculated as follows:

[0162]

[0163] Where, MLP (k) Indicates a multi-layer perceptron with k layers; Is the node x in the node type The k-th layer embedding result in ; is the input of the kth layer, and Neighbor The temporal importance weight of , indicating that the influence of neighbors on node x changes over time.

[0164] Step 2.2.3: Based on the intra-class point aggregation, the graph attention mechanism is used to fuse heterogeneous types of intra-class point aggregation to generate inter-class point aggregation, completing the information aggregation of the point signals within the anonymous account spatiotemporal behavior graph model, i.e., node embedding, as follows:

[0165] According to the intra-class point aggregation, the node embedding of node x in type β Attention score The calculation is as follows:

[0166]

[0167] Where LeakyRelu is the zero negative correction activation function; is the transposed attention parameter;

[0168] According to the node embedding of the node x in type β The attention score of node x, the inter-class point aggregation, is the node embedding, which is calculated as follows:

[0169]

[0170] Where, ρ x is the between-class point aggregation of node x.

[0171] Step 2.3: Based on the node embedding of each graph node, a graph pooling method is designed for the subgraph signal in the anonymous account spatiotemporal behavior graph model, and the graph embedding of the anonymous account spatiotemporal behavior graph model is calculated.

[0172] As a preferred embodiment, this embodiment designs an attention-based pooling mechanism, which assigns attention weights to the embedding of each node and combines them to form the final graph embedding, so that nodes that are more relevant to the spatiotemporal pattern of the anonymous account α to be regulated receive higher weights. The graph embedding of the anonymous account spatiotemporal behavior graph model is defined as follows:

[0173]

[0174] Where, ρ i is the heterogeneous temporal node embedding of node i; a iis the attention weight of node i, a i The specific calculation is as follows:

[0175]

[0176] Where q T is the transpose of the learnable attention vector; W is the learnable weight matrix; V is the node set of the anonymous account spatiotemporal graph model.

[0177] Step 3: Based on the anonymous account spatiotemporal behavior graph model, for multiple anonymous account spatiotemporal behavior graphs, the designed temporal heterogeneous graph twin network is used to measure the spatiotemporal behavior characteristics between different anonymous accounts to obtain the spatiotemporal behavior similarity between different anonymous accounts.

[0178] As a preferred embodiment, Figure 6 As shown, the temporal heterogeneous graph twin network specifically includes:

[0179] Step 3.1: Build a graph-level twin network for multiple anonymous account spatiotemporal behavior graphs to implement large-scale graph-level anonymous account behavior analysis in parallel. The details are as follows:

[0180] For a given anonymous account spatiotemporal behavior graph j, graph embedding f j The calculation is as follows:

[0181]

[0182] Where Pool is the graph pooling method; V j is the node set of the anonymous account spatiotemporal behavior graph j; The node v is embedded in the last layer after L layers of heterogeneous time series edge aggregation and heterogeneous time series point aggregation:

[0183]

[0184] Where, HTAGG n It is a heterogeneous time series point aggregation method; is the set of neighbor nodes of node v; is the aggregate edge embedding of node v at level l+1:

[0185]

[0186] Where, HTAGG e It is a heterogeneous time series edge aggregation method; is the edge embedding from node u to node v at layer l;

[0187] Initialized by a random vector.

[0188] In this embodiment, each time-series heterogeneous graph twin network includes graph twin sub-network A and graph twin sub-network B. The network weights are shared between the twin sub-networks, and it can simultaneously support the parallel generation of graph embeddings of two anonymous account spatiotemporal behavior graphs for similarity comparison.

[0189] Step 3.2: Use the designed temporal heterogeneous graph twin network to measure the spatiotemporal behavior characteristics between different anonymous accounts, as follows:

[0190] According to the spatiotemporal behavior graph of the anonymous account to be compared and The graph embedding f q and f p , use Euclidean distance to measure the spatiotemporal behavior similarity between different anonymous accounts:

[0191]

[0192] Where d is the graph embedding f q and f p The vector dimension of .

[0193] Step 4: For different blockchain environments, the designed similarity perception graph-based transfer learning mechanism is used to adaptively tune the measurement of spatiotemporal behavior similarity between different anonymous accounts in the cross-blockchain environment, realize adaptive cross-blockchain anonymous account identity association, and then realize anonymous account supervision.

[0194] As a preferred embodiment, the similarity perception graph-based transfer learning mechanism specifically includes:

[0195] Step 4.1: Pre-train the basic model.

[0196] For a single blockchain scenario, pre-train the anonymous account spatiotemporal behavior graph model to obtain a pre-trained basic model. is the dataset on the source blockchain, and is the spatiotemporal behavior graph of the anonymous account for the i-th query-comparison sample pair, Represents the self node in the two graphs, that is, whether the comparison account and query account are linked to the same off-chain identity, N S Represents the number of query-comparison pairs in the dataset constructed from the source blockchain; the purpose of pre-training is to minimize the number of samples in the source dataset of the temporal heterogeneous graph twin network. The loss function on

[0197]

[0198] Where, and They are and Graph embedding of is the Euclidean distance between the two graph embeddings, and the parameters θ of the temporal heterogeneous graph twin network are updated by gradient descent:

[0199]

[0200] Where η is the learning rate.

[0201] Step 4.2: Perform cross-blockchain model optimization based on the similarity perception graph transfer learning mechanism, as follows;

[0202] Based on the pre-trained basic model, cross-blockchain model tuning is performed based on the similarity perception graph transfer learning mechanism. It is a dataset constructed from the target blockchain, and the goal is to minimize the similarity perception loss function on the dataset

[0203]

[0204] Where N T is the number of query-comparison pairs in the target blockchain dataset.

[0205] In another embodiment of the present invention, an adaptive cross-blockchain anonymous account supervision device based on spatiotemporal graph learning is provided, which is used to implement an adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning in the above embodiment, specifically comprising:

[0206] A construction module is used to construct a spatiotemporal behavior graph model of anonymous accounts based on the temporal dynamics and spatial heterogeneity of blockchain anonymous account behavior;

[0207] An extraction module is used to extract the spatiotemporal behavior features in a single anonymous account spatiotemporal behavior graph based on the anonymous account spatiotemporal behavior graph model and using a designed temporal heterogeneous graph learning mechanism;

[0208] A measurement module is used to measure the spatiotemporal behavior characteristics between different anonymous accounts based on the anonymous account spatiotemporal behavior graph model and the designed temporal heterogeneous graph twin network for multiple anonymous account spatiotemporal behavior graphs, thereby obtaining the spatiotemporal behavior similarity between different anonymous accounts;

[0209] The tuning module is used for different blockchain environments. It uses the designed similarity perception graph-based transfer learning mechanism to adaptively tune the measurement of spatiotemporal behavior similarity between different anonymous accounts in cross-blockchain environments, thereby realizing adaptive cross-blockchain anonymous account identity association.

[0210] All relevant contents of each step involved in the embodiment of the aforementioned adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning can be referred to the functional description of the functional module corresponding to the adaptive cross-blockchain anonymous account supervision device based on spatiotemporal graph learning in the embodiment of the present invention, and will not be repeated here. The division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, the functional modules in various embodiments of the present invention can be integrated into one processor, or they can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0211] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of an adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning.

[0212] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides storage space, which stores the terminal's operating system. In addition, the storage space also stores one or more instructions suitable for being loaded and executed by the processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk storage. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the above-mentioned embodiment regarding an adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning.

[0213] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0214] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0215] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0216] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0217] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0218] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning, characterized in that: include: Aiming at the temporal dynamics and spatial heterogeneity of blockchain anonymous account behavior, a spatiotemporal behavior graph model of anonymous accounts is constructed; Based on the anonymous account spatiotemporal behavior graph model, for a single anonymous account spatiotemporal behavior graph, the designed temporal heterogeneous graph learning mechanism is used to extract the spatiotemporal behavior features within the spatiotemporal behavior graph of the single anonymous account; Based on the anonymous account spatiotemporal behavior graph model, for multiple anonymous account spatiotemporal behavior graphs, the designed temporal heterogeneous graph twin network is used to measure the spatiotemporal behavior characteristics between different anonymous accounts, and the spatiotemporal behavior similarity between different anonymous accounts is obtained; The designed temporal heterogeneous graph twin network constructs a graph-level twin sub-network for the spatiotemporal behavior graphs of multiple anonymous accounts; Aiming at different blockchain environments, the designed similarity perception graph-based transfer learning mechanism is used to adaptively tune the measurement of the spatiotemporal behavior similarity between different anonymous accounts in a cross-blockchain environment, thereby realizing adaptive cross-blockchain anonymous account identity association; the designed similarity perception graph-based transfer learning mechanism is as follows: for a single blockchain scenario, the anonymous account spatiotemporal behavior graph model is pre-trained to obtain a pre-trained basic model; based on the pre-trained basic model, cross-blockchain model tuning is performed based on the similarity perception graph transfer learning mechanism.

2. The adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning according to claim 1 is characterized in that: The above-mentioned anonymous account spatiotemporal behavior graph model is constructed based on the temporal dynamics and spatial heterogeneity of the blockchain anonymous account behavior, specifically: Based on the temporal dynamics of on-chain account transaction behavior and the heterogeneity of transaction types and transaction accounts, a native account spatiotemporal behavior graph model is constructed; The native account spatiotemporal behavior graph model is denoised based on a heuristic graph pruning algorithm to obtain the anonymous account spatiotemporal behavior graph model.

3. The adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning according to claim 2 is characterized in that: The native account spatiotemporal behavior graph model is specifically: Where, Indicates anonymous accounts on the supervision chain A self-blockchain transaction network that is expanded as the center, that is, an anonymous account The native account spatiotemporal behavior graph model; Representing the self-blockchain transaction network The depth of breadth-first search traversal; Represents the set of on-chain address nodes traversed in breadth-first search; Represents the set of all on-chain transactions traversed in a breadth-first search; Indicates the address node set from the chain To the on-chain address type The mapping, For the real external owner account, For blockchain robot accounts, It is a blockchain smart contract account; Represents a collection of transactions from the chain On-chain transaction type The mapping, For external transactions, For contract transactions, For insider trading, For token transactions; Represents a collection of transactions from the chain On-chain transaction time The mapping, Indicates the transaction start time, Indicates the duration of the transaction; The heuristic graph pruning algorithm is used to denoise the native account spatiotemporal behavior graph model, specifically: Identify an overloaded node set in the native account spatiotemporal behavior graph model, where the overloaded node set in the native account spatiotemporal behavior graph model is: Where, Representation node The on-chain address type; Representation node The in-degree of Representation node The out-degree of Indicates the tolerance value of overloaded nodes; The rotten node neighbor set under the branch subgraph connected to the overloaded node is classified into: Where, Indicates an overloaded node In the native account space-time behavior graph model The neighbor nodes found by the first-order breadth-first search; Indicates the earliest on-chain transaction among neighboring nodes. neighbor nodes; is the denoising coefficient; The branch subgraph connected to the neighbors of the corrupted node is pruned to complete the denoising of the native account spatiotemporal behavior graph model and obtain the anonymous account spatiotemporal behavior graph model.

4. The adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning according to claim 3 is characterized in that: The temporal heterogeneous graph learning mechanism designed is specifically as follows: A heterogeneous temporal edge aggregation method is designed for edge signals in the spatiotemporal behavior graph model of anonymous accounts to calculate the initial node features of each graph node. Based on the initial node features obtained by the heterogeneous time-series edge aggregation method as the initial features for point aggregation, a heterogeneous time-series point aggregation method is designed for point signals within the anonymous account spatiotemporal behavior graph model, and the node embedding of each graph node is calculated; Based on the node embedding of each graph node, a graph pooling method is designed for the subgraph signals in the anonymous account spatiotemporal behavior graph model, and the graph embedding of the anonymous account spatiotemporal behavior graph model is calculated.

5. The adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning according to claim 4 is characterized in that: The heterogeneous temporal edge aggregation method for edge signals in the anonymous account spatiotemporal behavior graph model is specifically designed as follows: For a given node in the anonymous account spatiotemporal behavior graph model , Indicates a given edge type Inside The set of adjacent edges of Attention score , calculated as follows: Where, is the transposed matrix of attention parameters; Is the edge type Middle side Vectorized transaction information for edge , use the nonlinear activation function Relu to calculate the attention score; for edge Attention score Further normalization is performed through the Softmax function, and the edge The importance weight of the attention mechanism , calculated as follows: Based on the adjacent edge set Attention-based importance weights, applying multi-head attention methods to aggregate information of adjacent edges, nodes On edge type Edge aggregation within , calculated as follows: Where, Indicates a connection operation; Represents the Relu nonlinear activation function; is the number of attention heads used in the multi-head attention method; for each edge aggregation The timestamp is defined as The latest interaction in is calculated as follows: Aggregate by edge Timestamp Sort the edge aggregation in ascending order, each node The initial node features are calculated as follows: Where, Long short-term memory network; Indicates that the time series is sorted in ascending order.

6. The adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning according to claim 5 is characterized in that: The heterogeneous time series point aggregation method designed for the internal point signal of the anonymous account spatiotemporal behavior graph model is specifically as follows: For a given node in the anonymous account spatiotemporal behavior graph model , Node type The set of adjacent nodes in the node Time attribute From the adjacent side Latest timestamp , which is calculated as follows: According to time attributes Generate Node The temporal importance weight of , which is calculated as follows: According to the time importance weight , generate node type midpoint Intra-class point aggregation , which is calculated as follows: Where, Indicates the number of network layers Multilayer Perceptron of layers; is a node In the node type The Layer embedding results; It is layer input, and ; Neighbor The temporal importance weight of the node The impact of changes over time; According to the intra-class point aggregation, nodes In type Node embedding within Attention score The calculation is as follows: Where, is the zero-negative rectification activation function; is the transposed attention parameter; According to the node In type Node embedding within The attention score of node The inter-class point aggregation is the node embedding, which is calculated as follows: Where, is a node Between-class point aggregation.

7. The adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning according to claim 6 is characterized in that: The graph pooling method for subgraph signals in the spatiotemporal behavior graph model for anonymous accounts is specifically as follows: Where, is a node Heterogeneous temporal node embedding; is a node The attention weight, The specific calculation is as follows: Where, is the transpose of the learnable attention vector; is a learnable weight matrix; It is a node set of the anonymous account space-time graph model.

8. The adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning according to claim 7 is characterized in that: The designed temporal heterogeneous graph twin network is specifically: Construct a graph-level twin network for multiple anonymous account spatiotemporal behavior graphs. For a given anonymous account spatiotemporal behavior graph , graph embedding The calculation is as follows: Where Pool is the graph pooling method; It is the spatiotemporal behavior graph of anonymous accounts The node set of is a node go through Layer heterogeneous time series edge aggregation and heterogeneous time series point aggregation are embedded in the nodes of the last layer: Where, It is a heterogeneous time series point aggregation method; is a node The set of neighbor nodes of is a node In the Aggregate edge embedding of layers: Where, It is a heterogeneous time series edge aggregation method; It is in Layer slave node To Node edge embeddings of Initialize with a random vector; The designed temporal heterogeneous graph twin network is used to measure the spatiotemporal behavior characteristics between different anonymous accounts, specifically: According to the spatiotemporal behavior graph of the anonymous account to be compared and Graph embedding and , use Euclidean distance to measure the spatiotemporal behavior similarity between different anonymous accounts: Where, It is a graph embedding and The vector dimension of .

9. The adaptive cross-blockchain anonymous account supervision method based on spatiotemporal graph learning according to claim 8 is characterized in that: The aforementioned method utilizes the designed similarity perception graph-based transfer learning mechanism to adaptively tune the measurement of spatiotemporal behavior similarity between different anonymous accounts in a cross-blockchain environment, specifically: For a single blockchain scenario, pre-train the anonymous account spatiotemporal behavior graph model to obtain a pre-trained basic model. is the dataset on the source blockchain, and It is The spatiotemporal behavior graph of anonymous accounts for query-comparison sample pairs, Represents the self node in the two graphs, that is, comparing accounts and querying whether accounts are linked to the same off-chain identity, Represents the number of query-comparison pairs in the dataset constructed from the source blockchain; the purpose of pre-training is to minimize the number of samples in the source dataset of the temporal heterogeneous graph twin network. The loss function on : Where, and They are and Graph embedding of is the Euclidean distance between the two graph embeddings, the parameter of the temporal heterogeneous graph twin network Update via gradient descent: Where, is the learning rate; Based on the pre-trained basic model, cross-blockchain model tuning is performed based on the similarity perception graph transfer learning mechanism. It is a dataset constructed from the target blockchain, and the goal is to minimize the similarity perception loss function on the dataset : Where, is the number of query-comparison pairs in the target blockchain dataset.

10. An adaptive cross-blockchain anonymous account supervision device based on spatiotemporal graph learning, characterized in that: include: A construction module is used to construct a spatiotemporal behavior graph model of anonymous accounts based on the temporal dynamics and spatial heterogeneity of blockchain anonymous account behavior; An extraction module is used to extract the spatiotemporal behavior features in a single anonymous account spatiotemporal behavior graph based on the anonymous account spatiotemporal behavior graph model and using a designed temporal heterogeneous graph learning mechanism; A measurement module is used to measure the spatiotemporal behavior characteristics between different anonymous accounts based on the anonymous account spatiotemporal behavior graph model and the designed temporal heterogeneous graph twin network for multiple anonymous account spatiotemporal behavior graphs, thereby obtaining the spatiotemporal behavior similarity between different anonymous accounts; The tuning module is used for different blockchain environments. It uses the designed similarity perception graph-based transfer learning mechanism to adaptively tune the measurement of spatiotemporal behavior similarity between different anonymous accounts in cross-blockchain environments, thereby realizing adaptive cross-blockchain anonymous account identity association.

Images