A method and system for discovering one-way common relationship of blockchain addresses

Abstract

The present invention provides a method and system for discovering a unidirectional common relationship of blockchain addresses, the method comprising the following steps: obtaining an initial address; obtaining a candidate address having a transaction relationship with the initial address based on the initial address, and constructing a first relationship graph based on the initial address and the candidate address; dividing the initial address and the candidate address in the first relationship graph into at least one node group based on the connection relationship in the first relationship graph; for each node group, obtaining an affiliated address having a transaction relationship with the initial address or the candidate address in the node group, and constructing a second relationship graph based on the initial address, the candidate address and the affiliated address of each node group; calculating the embedding vector of each node based on the basic index of each node in the second relationship graph, constructing the node corresponding to the initial address and the node corresponding to the candidate address in the second relationship graph into a node pair, calculating the similarity of the two nodes in the node pair based on the embedding vector, and determining whether the candidate address is a regulatory address.

Description

Technical Field

[0001] The present invention relates to the field of blockchain technology, and in particular to a method and system for discovering a one-way common relationship of blockchain addresses. Background Art

[0002] Blockchain technology, with its decentralization, transparency and immutability, is gradually changing the operating models of multiple industries.

[0003] However, it is precisely these characteristics that bring about the necessity of user supervision. First of all, although the anonymity of blockchain guarantees transaction privacy, it also requires supervision of users. By implementing measures such as identity verification and transaction monitoring, suspicious activities can be discovered and tracked in a timely manner to protect legitimate users. In addition, user supervision can also enhance the overall trust of the blockchain ecosystem. A transparent and fair regulatory environment can enhance users' confidence in blockchain technology and jointly promote the popularization and application of blockchain technology.

[0004] To sum up, user supervision of blockchain is a necessary means to maintain financial security and promote technological innovation. While promoting the development of blockchain technology, it is necessary to attach importance to and strengthen user supervision. However, existing technologies lack user selectivity, and large-scale supervision of all users leads to a large workload. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method for discovering a one-way common relationship of blockchain addresses to eliminate or improve one or more defects existing in the prior art.

[0006] One aspect of the present invention provides a method for discovering a one-way common relationship of a blockchain address, the method comprising the following steps:

[0007] Obtaining an input initial address, where the initial address is a pre-selected suspicious address;

[0008] Acquire a candidate address having a transaction relationship with the initial address based on the initial address, and construct a first relationship graph based on the initial address and the candidate addresses;

[0009] Based on the connection relationship in the first relationship graph, divide the initial address and the candidate address in the first relationship graph into at least one node group;

[0010] For each node group, obtain an affiliated address having a transaction relationship with an initial address or a candidate address in the node group, and construct a second relationship graph based on the initial address, candidate address, and affiliated address of each node group, wherein each initial address, candidate address, or affiliated address corresponds to a node in the second relationship graph, and edges are set between connected nodes in the second relationship graph;

[0011] The weight value of each edge in the second relationship graph is calculated based on the basic indicator of each node in the second relationship graph, the embedding vector of each node is calculated by a random walk algorithm based on the weight value of each edge, the node corresponding to each initial address in the second relationship graph and the node corresponding to each candidate address are constructed into a node pair, the similarity of two nodes in the node pair is calculated based on the embedding vector, and whether the candidate address is a regulatory address is determined based on the similarity.

[0012] The above scheme is adopted. The initial address in this scheme is a suspicious address pre-selected by the staff. The candidate address is determined based on the transaction relationship with the initial address, and a first relationship graph is constructed based on the initial address and the candidate address. The nodes in the first relationship graph with a connection relationship are divided into a node group, and then expanded based on the initial address and the candidate address of each node group to obtain a second relationship graph. The embedding vector of the node is calculated by the basic indicator of each node in the second relationship graph. The similarity of two nodes in the node pair is calculated based on the embedding vector. If the similarity between the two is high, it is determined that the candidate address has a high similarity with the pre-selected suspicious address, and the two have a transaction relationship, and the address needs to be regulated. This scheme can automatically screen the candidate addresses, efficiently select the regulated addresses, and reduce the difficulty of supervision.

[0013] In some embodiments of the present invention, in the step of obtaining a candidate address having a transaction relationship with the initial address based on the initial address, an address having a transaction relationship with the initial address and having a first distance from the initial address is obtained as the candidate address; in the step of obtaining a subsidiary address having a transaction relationship with the initial address or the candidate address in the node group, an address having a transaction relationship with the initial address or the candidate address in the node group and having a second distance from the initial address or the candidate address is obtained as the subsidiary address.

[0014] In some embodiments of the present invention, in the step of obtaining an address that has a transaction relationship with the initial address and is at a first distance from the initial address as a candidate address, the transaction relationship with the initial address is input to the initial address or output from the initial address; in the step of obtaining an address that has a transaction relationship with the initial address or the candidate address in the node group and is at a second distance from the initial address or the candidate address as a subsidiary address, the transaction relationship with the initial address or the candidate address in the node group is input to the initial address or the candidate address and output from the initial address or the candidate address.

[0015] In some embodiments of the present invention, in the step of obtaining an address that has a transaction relationship with the initial address and is at a first distance from the initial address as a candidate address, the first distance is a 1-hop distance; in the step of obtaining an address that has a transaction relationship with the initial address or the candidate address in the node group and is at a second distance from the initial address or the candidate address as a subsidiary address, the second distance is a 2-hop distance.

[0016] In some embodiments of the present invention, the step of calculating the weight value of each edge in the second relationship graph based on the basic index of each node in the second relationship graph includes:

[0017] Calculate the first edge index for each basic index of each edge based on the basic indexes of the two nodes at both ends of the edge;

[0018] Performing standardization based on all first edge indices of all edges, obtaining a second edge index corresponding to each basic index of each edge;

[0019] The weight value of each edge is calculated based on all the second edge indices of each edge.

[0020] In some embodiments of the present invention, in the step of calculating the first edge indicator for each basic indicator of each edge based on the basic indicators of the two nodes at both ends of the edge, the difference between each basic indicator of the two nodes is calculated, and the square is calculated as the first edge indicator corresponding to the basic indicator.

[0021] In some embodiments of the present invention, in the step of calculating the weight value of each edge based on all second edge indices of each edge, the sum of all second edge indices of each edge is calculated as the weight value of the edge.

[0022] In some embodiments of the present invention, in the step of calculating the embedding vector of each node by a random walk algorithm based on the weight value of each edge, a node2vec algorithm is used to calculate the embedding vector of each node based on the weight value of each edge.

[0023] In some embodiments of the present invention, in the step of calculating the similarity between two nodes in a node pair based on the embedding vector, the cosine similarity between the two nodes based on the embedding vector is calculated as the similarity value.

[0024] In some embodiments of the present invention, the method includes multiple processing rounds, in each processing round the first distance is set to a different distance value, and in each processing round candidate addresses at different distances from the initial address are determined.

[0025] The second aspect of the present invention also provides a blockchain address unidirectional common relationship discovery system, the system includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, the processor is used to execute the computer instructions stored in the memory, when the computer instructions are executed by the processor, the system implements the steps implemented by the method as described above.

[0026] The third aspect of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps implemented by the aforementioned blockchain address unidirectional common relationship discovery method.

[0027] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention can be specifically pointed out and obtained in the specification and the accompanying drawings.

[0028] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention.

[0030] Figure 1 A schematic diagram of an implementation method of a one-way common relationship discovery method for blockchain addresses of the present invention;

[0031] Figure 2 is a schematic diagram of a first relationship diagram of the present invention;

[0032] Figure 3 It is a schematic diagram of the second relationship diagram of the present invention. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0034] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0035] like Figure 1As shown, the present invention proposes a method for discovering a one-way common relationship of blockchain addresses, which includes the following steps:

[0036] Step S100, obtaining an input initial address, wherein the initial address is a pre-selected suspicious address;

[0037] In the specific implementation process, the initial address is a suspicious address that needs to be supervised and pre-selected by the staff. This solution uses the suspicious address that needs to be supervised and pre-selected by the staff as the starting point for checking all addresses in the entire blockchain, which can facilitate the determination of other addresses that need to be supervised through the pre-selected suspicious addresses that need to be supervised.

[0038] Step S200, based on the initial address, obtaining a candidate address having a transaction relationship with the initial address, and constructing a first relationship graph based on the initial address and the candidate addresses;

[0039] In the specific implementation process, in the step of obtaining a candidate address having a transaction relationship with the initial address based on the initial address, the selected transaction relationship is a one-way transaction relationship, that is, a transaction in an input direction to the initial address or a transaction in an output direction from the initial address is selected, that is, if the selected transaction relationship is a transaction in an output direction from the initial address, and the initial address and a certain address only have transactions in an input direction to the initial address, then there is no connection relationship between the initial address and the address in the first relationship graph.

[0040] like Figure 2 As shown, Figure 2 is a schematic diagram of a first relationship diagram, Figure 2 0x1, 0x2, 0x3, and 0x4 are all nodes corresponding to the initial addresses. Figure 2 The other nodes in the are candidate addresses.

[0041] By adopting the above scheme, this scheme only considers the "one-way" situation in the process of constructing the first relationship diagram. The advantage of "one-way" over "undirected" is that it only analyzes a single direction and will not be disturbed by the transactions in the other direction involved in "undirected".

[0042] Step S300, based on the connection relationship in the first relationship graph, divide the initial address and the candidate address in the first relationship graph into at least one node group;

[0043] In the specific implementation process, Figure 2 As shown, based on the connection relationship, the addresses that have a connection relationship with 0x2, 0x3, and 0x4 are divided into one node group, and the address that has a connection relationship with 0x1 is divided into one node group.

[0044] In some embodiments of the present invention, nodes belonging to different node groups are rendered in different colors in the first relationship graph.

[0045] In a specific implementation process, in the two node groups in the first relationship graph, no node in one node group is connected to any node in the other node group.

[0046] Step S400, for each node group, obtaining an affiliated address having a transaction relationship with an initial address or a candidate address in the node group, and constructing a second relationship graph based on the initial address, candidate address and affiliated address of each node group, wherein each initial address, candidate address or affiliated address corresponds to a node in the second relationship graph, and edges are set between connected nodes in the second relationship graph;

[0047] In the specific implementation process, the second relationship graph is to further complete the part involved in a node group in the first relationship graph. Since the purpose of this solution is to determine the address of the common relationship with the initial address, the common relationship means that the two addresses have certain similarities in behavior. In order to better capture these relationships, this solution needs to enrich our data, so it is necessary to continue to complete the graph. The completion method is based on all nodes in the graph to ensure the comprehensiveness of the data.

[0048] like Figure 3 As shown, Figure 3 for Figure 2 The second relationship graph corresponding to the node group of 0x2, 0x3, and 0x4, Figure 3 Among them, 0x5, 0x6, 0x7, 0x8, and 0x9 are candidate nodes, and the remaining nodes are subsidiary nodes.

[0049] Step S500, calculate the weight value of each edge in the second relationship graph based on the basic indicator of each node in the second relationship graph, calculate the embedding vector of each node through a random walk algorithm based on the weight value of each edge, construct the node corresponding to each initial address in the second relationship graph and the node corresponding to each candidate address into a node pair, calculate the similarity of two nodes in the node pair based on the embedding vector, and determine whether the candidate address is a regulatory address based on the similarity.

[0050] In the specific implementation process, the basic indicators are the transaction data of the address corresponding to the node. Specifically, the basic indicators include total input amount, total output amount, in-degree, out-degree, balance and active time.

[0051] In the specific implementation process, when determining whether a candidate address is a regulatory address based on the similarity, a preset similarity threshold is compared with the calculated similarity. If the calculated similarity is greater than the similarity threshold, the corresponding candidate address is determined to be a regulatory address and is subject to key supervision.

[0052] In a specific implementation process, the similarity threshold may be set to 0.8.

[0053] In a specific implementation process, the nodes corresponding to the initial addresses in the second relationship graph are constructed as an input node set, the nodes corresponding to the candidate addresses are constructed as a candidate node set, and a Cartesian product is performed on the input node set and the candidate node set.

[0054] The above scheme is adopted. The initial address in this scheme is a suspicious address pre-selected by the staff. The candidate address is determined based on the transaction relationship with the initial address, and a first relationship graph is constructed based on the initial address and the candidate address. The nodes in the first relationship graph with a connection relationship are divided into a node group, and then expanded based on the initial address and the candidate address of each node group to obtain a second relationship graph. The embedding vector of the node is calculated by the basic indicator of each node in the second relationship graph. The similarity of two nodes in the node pair is calculated based on the embedding vector. If the similarity between the two is high, it is determined that the candidate address has a high similarity with the pre-selected suspicious address, and the two have a transaction relationship, and the address needs to be regulated. This scheme can automatically screen the candidate addresses, efficiently select the regulated addresses, and reduce the difficulty of supervision.

[0055] In some embodiments of the present invention, in the step of obtaining a candidate address having a transaction relationship with the initial address based on the initial address, an address having a transaction relationship with the initial address and having a first distance from the initial address is obtained as the candidate address; in the step of obtaining a subsidiary address having a transaction relationship with the initial address or the candidate address in the node group, an address having a transaction relationship with the initial address or the candidate address in the node group and having a second distance from the initial address or the candidate address is obtained as the subsidiary address.

[0056] In some embodiments of the present invention, both the first distance and the second distance can be 1 hop, 2 hops, 3 hops, etc.

[0057] In some embodiments of the present invention, in the step of obtaining an address that has a transaction relationship with the initial address and is at a first distance from the initial address as a candidate address, the transaction relationship with the initial address is input to the initial address or output from the initial address; in the step of obtaining an address that has a transaction relationship with the initial address or the candidate address in the node group and is at a second distance from the initial address or the candidate address as a subsidiary address, the transaction relationship with the initial address or the candidate address in the node group is input to the initial address or the candidate address and output from the initial address or the candidate address.

[0058] In the specific implementation process, in the step of obtaining an address that has a transaction relationship with the initial address or the candidate address in the node group and is at a second distance from the initial address or the candidate address as a subsidiary address, if there is any address that is not in the first relationship graph and there is a transaction relationship input to and output from the initial address or the candidate address, then the address is used as the subsidiary address.

[0059] In some embodiments of the present invention, in the step of obtaining an address that has a transaction relationship with the initial address and is at a first distance from the initial address as a candidate address, the first distance is a 1-hop distance; in the step of obtaining an address that has a transaction relationship with the initial address or the candidate address in the node group and is at a second distance from the initial address or the candidate address as a subsidiary address, the second distance is a 2-hop distance.

[0060] In some embodiments of the present invention, the step of calculating the weight value of each edge in the second relationship graph based on the basic index of each node in the second relationship graph includes:

[0061] Calculate the first edge index for each basic index of each edge based on the basic indexes of the two nodes at both ends of the edge;

[0062] Performing standardization based on all first edge indices of all edges, obtaining a second edge index corresponding to each basic index of each edge;

[0063] The weight value of each edge is calculated based on all the second edge indices of each edge.

[0064] In some embodiments of the present invention, in the step of calculating the first edge indicator for each basic indicator of each edge based on the basic indicators of the two nodes at both ends of the edge, the difference between each basic indicator of the two nodes is calculated, and the square is calculated as the first edge indicator corresponding to the basic indicator.

[0065] In some embodiments of the present invention, in the step of performing standardization on all first edge indicators based on all edges to obtain the second edge indicator corresponding to each basic indicator of each edge, all first edge indicators of all edges are obtained, and for each first edge indicator of a certain edge, the same first standard indicators of all edges are standardized with a standard deviation of 1 and a mean of 1 to obtain the second edge indicator corresponding to the first edge indicator.

[0066] In some embodiments of the present invention, in the step of calculating the weight value of each edge based on all second edge indices of each edge, the sum of all second edge indices of each edge is calculated as the weight value of the edge.

[0067] In some embodiments of the present invention, in the step of calculating the embedding vector of each node by a random walk algorithm based on the weight value of each edge, a node2vec algorithm is used to calculate the embedding vector of each node based on the weight value of each edge.

[0068] In the specific implementation process, the node2vec algorithm determines whether the algorithm tends to discover structural features or homogeneous features by controlling the PQ parameters. Since we tend to discover structural features between nodes, our random walk process tends to be BFS, so this solution sets P=1, Q=2. Since the node2vec algorithm discovers node features by random walk, different random walk methods determine the differences in node feature discovery. This patent proposes a random walk method suitable for such problems, which is described in detail below.

[0069] The random walk strategy of the node2vec algorithm needs to determine the probability of transferring to a node adjacent to the current node based on the edge weight W when the node is currently located. Therefore, the calculation method of the edge weight W defines the "common relationship", or what the "common relationship" is specifically. The so-called "common relationship" refers to structural similarity on the one hand, that is, two different nodes have similarities in the local graph structure. On the other hand, it means that on the basis of structural similarity, the nodes that make up these structures should have similarities in transaction characteristics, which is exactly the goal of calculating edge weights.

[0070] In some embodiments of the present invention, in the step of calculating the similarity between two nodes in a node pair based on the embedding vector, the cosine similarity between the two nodes based on the embedding vector is calculated as the similarity value.

[0071] In some embodiments of the present invention, the method includes multiple processing rounds, in each processing round the first distance is set to a different distance value, and in each processing round candidate addresses at different distances from the initial address are determined.

[0072] In some embodiments of the present invention, the processing rounds are numbered, and the distance value is increased by 1 each time a processing round is completed. In the first processing round, the initial first distance is set to 1 hop, and the above scheme is adopted. This scheme can classify each address based on the distance from the initial address, and judge other addresses step by step from near to far, and can automatically complete the global address judgment, and automatically and quickly determine the addresses that need to be focused on.

[0073] In some embodiments of the present invention, the staff may also set different values ​​of the first distance in different processing rounds to meet the verification requirements of the user. In the specific processing process, the second distance may also be set by the staff.

[0074] In the specific implementation process, as the analysis gradually deepens, the analysis accuracy of the analysis algorithm is also constantly decreasing. "Grading" means that users have the choice to freely control the depth of analysis. Users can conduct tentative analysis and continuously adjust the "grading" strategy according to the accuracy of the analysis feedback, thereby improving the overall use experience of the algorithm. At the same time, this solution uses the node2vec algorithm to calculate the embedding vectors between nodes and thus calculate the cosine similarity. A special method for calculating weights is proposed, so that the algorithm can better capture the graph structure characteristics in the blockchain graph network, thereby more accurately discovering the common relationship between nodes. Before embedding the vector, nodes with poor common relationship possibilities are eliminated in advance by dividing the node groups, which reduces the amount of calculation while improving the accuracy of the algorithm.

[0075] The beneficial effects of this program include:

[0076] 1. In the process of constructing the first relationship graph, this scheme adopts a common relationship discovery method in a single direction, which reduces noise interference in other directions.

[0077] 2. The node groups are divided by coloring, which can eliminate some nodes in advance, reduce the amount of algorithm calculation and improve the algorithm accuracy.

[0078] 3. This solution adopts the node2vec algorithm. The edge weight calculation method involved in the node2vec algorithm can help the algorithm better capture the graph structure characteristics.

[0079] An embodiment of the present invention also provides a blockchain address unidirectional common relationship discovery system, the system includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, the processor is used to execute the computer instructions stored in the memory, when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0080] The embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps implemented by the aforementioned blockchain address unidirectional common relationship discovery method. The computer-readable storage medium may be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0081] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0082] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0083] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for discovering one-way common relationships of blockchain addresses, characterized in that: The method comprises the following steps: Obtaining an input initial address, where the initial address is a pre-selected suspicious address; Acquire a candidate address having a transaction relationship with the initial address based on the initial address, and construct a first relationship graph based on the initial address and the candidate addresses; Based on the connection relationship in the first relationship graph, divide the initial address and the candidate address in the first relationship graph into at least one node group; For each node group, obtain an affiliated address having a transaction relationship with an initial address or a candidate address in the node group, and construct a second relationship graph based on the initial address, candidate address, and affiliated address of each node group, wherein each initial address, candidate address, or affiliated address corresponds to a node in the second relationship graph, and edges are set between connected nodes in the second relationship graph; The weight value of each edge in the second relationship graph is calculated based on the basic indicator of each node in the second relationship graph, the first edge indicator of each basic indicator of each edge is calculated based on the basic indicators of the two nodes at both ends of the edge, the difference of each basic indicator of the two nodes is calculated, and the square is calculated as the first edge indicator corresponding to the basic indicator; all the first edge indicators of all the edges are standardized to obtain the second edge indicator of each basic indicator of each edge; the sum of all the second edge indicators of each edge is calculated as the weight value of the edge; the embedding vector of each node is calculated by a random walk algorithm based on the weight value of each edge, the node corresponding to each initial address in the second relationship graph and the node corresponding to each candidate address are constructed into a node pair, the similarity of the two nodes in the node pair is calculated based on the embedding vector, and whether the candidate address is a regulatory address is determined based on the similarity.

2. The method for discovering one-way common relationships of blockchain addresses according to claim 1 is characterized in that: In the step of obtaining a candidate address having a transaction relationship with the initial address based on the initial address, an address having a transaction relationship with the initial address and having a first distance from the initial address is obtained as the candidate address; in the step of obtaining a subsidiary address having a transaction relationship with the initial address or the candidate address in the node group, an address having a transaction relationship with the initial address or the candidate address in the node group and having a second distance from the initial address or the candidate address is obtained as the subsidiary address.

3. The method for discovering one-way common relationships of blockchain addresses according to claim 2 is characterized in that: In the step of obtaining an address that has a transaction relationship with the initial address and is at a first distance from the initial address as a candidate address, the transaction relationship with the initial address is input to the initial address or output from the initial address; in the step of obtaining an address that has a transaction relationship with the initial address or the candidate address in the node group and is at a second distance from the initial address or the candidate address as a subsidiary address, the transaction relationship with the initial address or the candidate address in the node group is input to the initial address or the candidate address and output from the initial address or the candidate address.

4. The method for discovering one-way common relationships of blockchain addresses according to claim 1, characterized in that: In the step of calculating the embedding vector of each node by a random walk algorithm based on the weight value of each edge, the node2vec algorithm is used to calculate the embedding vector of each node based on the weight value of each edge.

5. The method for discovering one-way common relationships of blockchain addresses according to claim 1, characterized in that: In the step of calculating the similarity of two nodes in a node pair based on the embedding vector, the cosine similarity of the two nodes based on the embedding vector is calculated as the value of the similarity.

6. The method for discovering one-way common relationships of blockchain addresses according to claim 2, characterized in that: The method comprises a plurality of processing rounds, in each processing round the first distance is set to a different distance value, and in each processing round candidate addresses at different distances from an initial address are determined.

7. A blockchain address unidirectional common relationship discovery system, characterized in that: The system includes a computer device, which includes a processor and a memory. The memory stores computer instructions. The processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method as described in any one of claims 1 to 6.

Images