Blockchain transaction associated address discovery method and device

Abstract

The present application provides a method and device for discovering blockchain transaction associated addresses, which relates to the field of financial information processing technology. The method includes: determining whether the current associated address set obtained by the FP-growth algorithm contains a destination node address that has an indirect transaction relationship with the target node address in the blockchain, and if so, expanding the feature associated data set based on the optimal reachable path between the target node address and the destination node address; for the feature associated data set, re-acquire the associated node address based on the FP-growth algorithm to form a new associated address set, and re-determine whether the new associated address set contains an associated node address with an indirect transaction relationship. The present application can improve the comprehensiveness and reliability of mining blockchain transaction associated addresses, and thus can effectively improve the effectiveness of applications such as abnormal transaction identification based on blockchain transaction associated address discovery results.

Description

Technical Field

[0001] The present application relates to the field of financial information processing technology, and in particular to a method and device for discovering addresses associated with blockchain transactions. Background Art

[0002] Discovering the correlation between blockchain addresses has potential uses in many aspects. For example, the correlation between the node addresses where transactions occur in the blockchain can be used in scenarios such as abnormal transaction identification and verification and confirmation of user identity. Discovering the correlation between blockchain addresses plays an important role in many aspects of blockchain technology and helps to better understand and apply blockchain technology.

[0003] At present, the existing blockchain transaction associated address discovery method usually uses the FP-growth (Frequent-Pattern Growth) algorithm to mine associated node addresses (referred to as associated addresses) that have transaction associations with a target node address in the blockchain. Among them, the FP-Growth algorithm is an efficient algorithm for discovering or mining frequent item sets, that is, an association analysis algorithm, which compresses the database providing frequent item sets into a frequent pattern tree (FP-tree), but still retains the item set association information. The algorithm only needs to traverse the data set twice to mine the associated address process, which greatly improves the efficiency of associated address discovery. At the same time, because the FP-Growth algorithm compresses the transaction data and only saves valid information, it can effectively optimize storage requirements and reduce memory resource consumption.

[0004] However, although the blockchain transaction associated address discovery method using the FP-growth algorithm has the advantages of high efficiency and low memory resource consumption, the use of the FP-growth algorithm to mine the association between addresses may result in missing information. For example, there is no direct transaction interaction relationship between a certain associated node address mined by the FP-growth algorithm and the target node address, but the two are indeed associated in certain transaction characteristics. In this case, the association relationship between other node addresses and the target node address in the indirect transaction path between the two is easily missed, which leads to the problem that the existing blockchain transaction associated addresses obtained based on the FP-growth algorithm are easy to miss and incomplete. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method and device for discovering blockchain transaction associated addresses to eliminate or improve one or more defects existing in the prior art.

[0006] One aspect of the present application provides a method for discovering a blockchain transaction associated address, comprising:

[0007] Determination step: determining whether the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, wherein the associated address set is used to store each associated node address that has a transaction association relationship with the target node address;

[0008] If so, the associated node address that has an indirect transaction relationship with the target node address in the blockchain is determined as the destination node address, the optimal reachable path is selected from each reachable path between the target node address and the destination node address, and the feature association data set of the target node address in the blockchain is expanded based on other node addresses except the target node address in the optimal reachable path;

[0009] For the current feature association data set, each associated node address having a transaction association relationship with the target node address is obtained based on the FP-growth algorithm to form a new associated address set.

[0010] In some embodiments of the present application, it also includes:

[0011] If it is determined that the current associated address set obtained by the FP-growth algorithm does not contain an associated node address that has an indirect transaction relationship with the target node address in the blockchain, then the associated address set is used as the associated address set result data corresponding to the target node address;

[0012] The associated address set result data is output to perform abnormal transaction identification and / or user identity authentication.

[0013] In some embodiments of the present application, before the determining step, the method further includes:

[0014] Construct a feature association data set corresponding to the target node address;

[0015] For the current feature association data set, each associated node address having a transaction association relationship with the target node address is obtained based on the FP-growth algorithm to form a corresponding associated address set.

[0016] In some embodiments of the present application, constructing a feature association data set corresponding to the target node address includes:

[0017] Receive a blockchain transaction associated address discovery request, wherein the blockchain transaction associated address discovery request includes: a target node address in the blockchain and a maximum number of search layers of the blockchain;

[0018] Based on a breadth-first search algorithm, searching in the blockchain for each node address whose shortest path distance to the target node address is less than or equal to the maximum search level of the blockchain;

[0019] According to the target node address and the transaction information corresponding to each of the node addresses, a blockchain transaction topology graph corresponding to the target node address is constructed, wherein each node in the blockchain transaction topology graph represents the target node address and each of the node addresses one-to-one, and the edge connecting each of the nodes in the blockchain transaction topology graph is used to represent the transaction information between the two nodes connected by the edge, and the arrow of the edge is used to represent the transaction direction between the two nodes connected by the edge;

[0020] Searching for nodes that meet multiple preset transaction features in the blockchain transaction topology graph to form a feature association data set of the target node address in the blockchain.

[0021] In some embodiments of the present application, the transaction features include mutual transfer features, transaction amount exceeding threshold features, institution preference features, time preference features, and amount preference features extracted from the transaction information;

[0022] Correspondingly, the feature association data set includes:

[0023] The mutual transfer feature association data set is used to store the node addresses corresponding to the nodes of the two parties in the mutual transfer relationship;

[0024] The transaction amount exceeding threshold feature associated data set is used to store the node addresses corresponding to the nodes of both parties of the transfer when the percentage of the transfer amount to the funds held by the parties exceeds the percentage threshold;

[0025] The institutional preference feature association data set is used to store the node addresses corresponding to each node that has transactions with the trading institution;

[0026] Each time preference feature associated data set is used to store the node addresses corresponding to each node whose transaction frequency exceeds the frequency threshold in different time periods;

[0027] Each amount preference feature associated data set is used to store the node addresses corresponding to each node whose transaction amount belongs to different financial intervals.

[0028] In some embodiments of the present application, the selecting the best reachable path from each reachable path between the target node address and the destination node address, and expanding the feature association data set of the target node address in the blockchain based on other node addresses other than the target node address in the best reachable path, includes:

[0029] Searching for all reachable paths between the target node address and the destination node address in the blockchain transaction topology graph;

[0030] If the number of the reachable paths between the target node address and the destination node address is not unique, then respectively calculating the edge weight of each edge in each of the reachable paths;

[0031] Determining the path weight of each of the reachable paths according to the edge weight of each edge in each of the reachable paths;

[0032] Select the reachable path with the largest path weight from among the reachable paths as the optimal reachable path;

[0033] The other node addresses except the target node address in the optimal reachable path are added to the current newly added expansion interval corresponding to the current feature association data set, so as to expand the feature association data set.

[0034] Another aspect of the present application provides a blockchain transaction associated address discovery device, comprising:

[0035] A judgment module, used to perform a judgment step: judging whether the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, wherein the associated address set is used to store each associated node address that has a transaction association relationship with the target node address;

[0036] An optimal reachable path selection module, for, if it is determined that the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, then determining the associated node address that has an indirect transaction relationship with the target node address in the blockchain as the destination node address, selecting the optimal reachable path from each reachable path between the target node address and the destination node address, and expanding the feature association data set of the target node address in the blockchain based on other node addresses except the target node address in the optimal reachable path;

[0037] The frequent item set mining module is used to obtain, for the current feature association data set, each associated node address having a transaction association relationship with the target node address based on the FP-growth algorithm to form a new associated address set.

[0038] The third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for discovering associated addresses of blockchain transactions when executing the computer program.

[0039] The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for discovering associated addresses of blockchain transactions.

[0040] The fifth aspect of the present application provides a computer program product, including a computer program, which implements the blockchain transaction associated address discovery method when executed by a processor.

[0041] The blockchain transaction associated address discovery method provided by the present application comprises the following steps: determining whether the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, wherein the associated address set is used to store each associated node address that has a transaction associated relationship with the target node address; if so, determining the associated node address that has an indirect transaction relationship with the target node address in the blockchain as the destination node address, selecting the best reachable path from each reachable path between the target node address and the destination node address, and based on the associated node addresses other than the target node address in the best reachable path, Other node addresses expand the feature association data set of the target node address in the blockchain; for the current feature association data set, based on the FP-growth algorithm, each associated node address that has a transaction association relationship with the target node address is obtained to form a new associated address set, which can improve the iterative discovery efficiency of blockchain transaction associated addresses and reduce memory resource consumption. It can solve the address omission problem of blockchain transaction associated addresses obtained based on the FP-growth algorithm, improve the comprehensiveness and reliability of mining blockchain transaction associated addresses, and thus effectively improve the effectiveness of applications such as abnormal transaction identification based on blockchain transaction associated address discovery results.

[0042] Additional advantages, purposes, and features of the present application will be partially described in the following description, and will become partially apparent to those skilled in the art after studying the following, or may be learned from the practice of the present application. The purposes and other advantages of the present application can be achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0043] Those skilled in the art will understand that the purposes and advantages that can be achieved by the present application are not limited to the above specific description, and the above and other purposes that can be achieved by the present application will be more clearly understood based on the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the present application, constitute a part of the present application, and do not constitute a limitation of the present application. The components in the drawings are not drawn to scale, but are only for the purpose of illustrating the principles of the present application. In order to facilitate the illustration and description of some parts of the present application, the corresponding parts in the drawings may be enlarged, that is, they may become larger relative to other components in the exemplary device actually manufactured according to the present application. In the drawings:

[0045] Figure 1 This is a first flow chart of a method for discovering addresses associated with blockchain transactions in one embodiment of the present application.

[0046] Figure 2 This is a second flow chart of a method for discovering addresses associated with blockchain transactions in one embodiment of the present application.

[0047] Figure 3 This is a third flow chart of the method for discovering blockchain transaction associated addresses in one embodiment of the present application.

[0048] Figure 4 It is a topology map corresponding to the associated address set that may be output through step 010 and step 020 in an application example of the present application.

[0049] Figure 5 This is a schematic diagram of all reachable paths between a target node address “0x1” and a destination node address “0x3” in an application example of the present application.

[0050] Figure 6 This is a schematic diagram of the overall iterative operation process of the iterative discovery process of blockchain transaction associated addresses in an application example of this application.

[0051] Figure 7 Schematic diagram of the structure of a blockchain transaction associated address discovery device in one embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the implementation modes and the accompanying drawings. Here, the illustrative implementation modes and descriptions of the present application are used to explain the present application, but are not intended to limit the present application.

[0053] It should also be noted here that in order to avoid obscuring the present application due to unnecessary details, only the structures and / or processing steps closely related to the scheme according to the present application are shown in the accompanying drawings, while other details that are not very relevant to the present application are omitted.

[0054] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0055] It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection involving an intermediate.

[0056] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0057] In order to improve the iterative discovery efficiency of blockchain transaction associated addresses and reduce memory resource consumption, and to solve the problem of address omissions in blockchain transaction associated addresses obtained based on the FP-growth algorithm, the embodiments of the present application respectively provide a blockchain transaction associated address discovery method, a blockchain transaction associated address discovery device for executing the blockchain transaction associated address discovery method, a physical device, a computer-readable storage medium and a computer program product, which can improve the comprehensiveness and reliability of mining blockchain transaction associated addresses, and thus effectively improve the effectiveness of applications such as abnormal transaction identification based on blockchain transaction associated address discovery results.

[0058] The details are described in detail through the following examples.

[0059] Based on this, the embodiment of the present application provides a blockchain transaction associated address discovery method that can be implemented by a blockchain transaction associated address discovery device, see Figure 1 The blockchain transaction associated address discovery method specifically includes the following contents:

[0060] Step 100: Judgment step: determine whether the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, wherein the associated address set is used to store each associated node address that has a transaction association relationship with the target node address.

[0061] In one or more embodiments of the present application, the target node address refers to the address of a node in the blockchain, and among the nodes in the blockchain, the node currently designated for transaction-associated address discovery is the current target node. The associated node address refers to the address of a node among the nodes in the blockchain that has a transaction-associated relationship with the target node address in the blockchain.

[0062] It can be understood that the transaction association relationship refers to the existence of an association relationship between the addresses of two nodes in the block regarding transactions such as transfers. There are direct transaction relationships in the transaction association relationship, and there may also be indirect transaction relationships. The direct transaction relationship refers to the existence of a direct transfer relationship between the two nodes, which can be displayed in the topology diagram as the two nodes being directly connected by only one edge; while the indirect transaction relationship refers to the absence of a direct transfer relationship between the two nodes, which can be displayed in the topology diagram as the two nodes needing to pass through a path formed by other nodes and multiple edges to be connected.

[0063] If it is determined in step 100 that the current associated address set contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, step 200 is executed.

[0064] Step 200: Determine an associated node address that has an indirect transaction relationship with a target node address in a blockchain as a destination node address, select an optimal reachable path from each reachable path between the target node address and the destination node address, and expand a feature association data set of the target node address in the blockchain based on other node addresses except the target node address in the optimal reachable path.

[0065] The reachable path refers to the node addresses and transaction information involved in the transaction from the target node address to the destination node address. For example, between node address A and node address C, if there is a direct transfer relationship between node address A and node address B, and there is also a transfer relationship between node address B and node address C, then node addresses A, B to C can be used as a reachable path from node address A to node address C.

[0066] Step 300: For the current feature association data set, based on the FP-growth algorithm, obtain each associated node address that has a transaction association relationship with the target node address to form a new associated address set.

[0067] It can be understood that in the blockchain transaction associated address discovery method provided in the present application, the basis for executing step 100 is to obtain the current associated address set obtained in advance by the FP-growth algorithm. The associated address set can be the associated address set obtained for the first time in the initialization calculation process after determining the target node address, or it can be a non-first associated address set calculated by step 300 in a certain round during the iterative process.

[0068] That is to say, the process from step 100 to step 300 provided in the embodiment of the present application can actually be an iterative process in the iterative discovery process of the blockchain transaction associated address. After each execution of step 300, step 100 can be returned to re-execute the next iterative process. In this process, the condition for ending the iteration is that the judgment condition of step 100 is no longer satisfied. That is to say, when it is determined by step 100 that the current associated address set obtained by the FP-growth algorithm does not contain an associated node address that has an indirect transaction relationship with the target node address in the blockchain, the iterative process is jumped out, which is specifically described in detail in step 400 of the following embodiment. Of course, if there is a preset iteration number threshold M, even if the judgment condition of step 100 is always satisfied, when the iteration number reaches the iteration number threshold, the iteration can be stopped, and the new associated address set obtained in step 300 in the current iteration process is output, where M is a positive integer greater than 1.

[0069] From the above description, it can be seen that the blockchain transaction associated address discovery method provided in the embodiment of the present application can solve the address omission problem of the blockchain transaction associated address obtained based on the FP-growth algorithm on the basis of improving the iterative discovery efficiency of the blockchain transaction associated address and reducing the memory resource consumption, and can improve the comprehensiveness and reliability of the mining of the blockchain transaction associated address, thereby effectively improving the effectiveness of applications such as abnormal transaction identification based on the blockchain transaction associated address discovery results.

[0070] In order to further improve the effectiveness and reliability of iterative discovery of blockchain transaction associated addresses, in a blockchain transaction associated address discovery method provided in an embodiment of the present application, see Figure 2 The blockchain transaction associated address discovery method further specifically includes the following contents:

[0071] If it is determined in step 100 that the current associated address set obtained by the FP-growth algorithm does not include an associated node address that has an indirect transaction relationship with the target node address in the blockchain, then step 400 is executed;

[0072] Step 400: Use the associated address set as the associated address set result data corresponding to the target node address, and output the associated address set result data for abnormal transaction identification and / or user identity authentication.

[0073] Specifically, discovering correlations between blockchain addresses has potential implications in multiple ways.

[0074] First, blockchain addresses are used to uniquely identify specific participants or contracts in a blockchain network. Each address is unique, which helps ensure the accuracy and security of transactions. Therefore, understanding the correlation between addresses can better understand and analyze transaction patterns and participant behaviors in a blockchain network.

[0075] Secondly, by discovering the correlation between addresses, deeper data analysis and mining can be performed. For example, it is possible to identify which addresses belong to the same entity or organization, and then understand the activity patterns and transaction preferences of these entities or organizations in the blockchain network. This helps to more accurately assess risks, predict market trends, and develop more effective strategies.

[0076] In addition, the correlation between addresses can also be used in security areas such as abnormal transaction identification. By analyzing the transaction records and fund flows between addresses, potential abnormal transaction behaviors can be identified and corresponding measures can be taken to prevent and combat them.

[0077] Finally, the discovery of correlations between blockchain addresses can also promote the application and development of blockchain technology in other fields. For example, in the field of controllable anonymity, the correlation between addresses can be used to verify and confirm the identity of users without exposing too much personal information. In the field of notarization, the openness, transparency and tamper-proof characteristics of blockchain technology can be used in combination with the correlation between addresses to ensure the authenticity and integrity of documents.

[0078] In one scenario example, when a data analyst inputs a target node address, the algorithm provided by this application outputs the address associated with the target node address. It can provide more valuable information to the data analyst. When the data analyst does not apply the algorithm provided by this application, he only holds one address. If the address analysis is blocked, the work of the data analyst will not be carried out. Therefore, one of the purposes of applying the algorithm provided by this application is to give the data analyst more analysis points to improve the effectiveness and reliability of subsequent applications.

[0079] In order to further improve the effectiveness and reliability of iterative discovery of blockchain transaction associated addresses, in a blockchain transaction associated address discovery method provided in an embodiment of the present application, see Figure 2, the method for discovering the associated address of a blockchain transaction further specifically includes the following contents before step 100:

[0080] Step 010: Construct a feature association data set corresponding to the target node address.

[0081] Step 020: For the current feature association data set, based on the FP-growth algorithm, obtain the addresses of each associated node that has a transaction association relationship with the target node address to form a corresponding associated address set.

[0082] In one example, after constructing the data set, the FP-growth algorithm is applied in step 020 to mine frequent item sets and find the address of the target node. The association rules are related and the confidence level is not less than 80%. Defined as the probability of node address B appearing when node address A has already appeared, the goal is to find a set of associated addresses , the size is , so that all elements in the associated address set All meet , and all elements in the set can be identified as the target node address At the same time, the algorithm also requires that the support of all elements in the element set is not less than 50%, where n is a positive integer greater than 1 and i is a positive integer.

[0083] In order to further improve the application effectiveness and construction efficiency of the feature association data set, in a blockchain transaction association address discovery method provided in an embodiment of the present application, see Figure 3 , step 010 in the blockchain transaction associated address discovery method specifically includes the following content:

[0084] Step 011: Receive a blockchain transaction associated address discovery request, wherein the blockchain transaction associated address discovery request includes: a target node address in the blockchain and a maximum number of search layers of the blockchain.

[0085] Specifically, the two inputs of step 011 are and , Represents an external account address of a blockchain, that is, the target node address; Represents the maximum number of search levels for the blockchain.

[0086] Step 012: Based on a breadth-first search algorithm, search in the blockchain for each node address whose shortest path distance to the target node address is less than or equal to the maximum search level of the blockchain.

[0087] In step 012, an address list can be output , Used to store the target node address found and input by the method provided by this application The associated addresses, that is, the node addresses whose shortest path distance to the target node address is less than or equal to the maximum search level of the blockchain.

[0088] That is, since the user enters two parameters and , so data can be obtained from the blockchain based on these two parameters. The specific method is: is the initial address, through breadth-first search ( ) algorithm to find the address of the target node The shortest path distance does not exceed All addresses.

[0089] Step 013: Based on the target node address and the transaction information corresponding to each of the node addresses, construct a blockchain transaction topology graph corresponding to the target node address, wherein each node in the blockchain transaction topology graph represents the target node address and each of the node addresses one-to-one, and the edge connecting each of the nodes in the blockchain transaction topology graph is used to represent the transaction information between the two nodes connected by the edge, and the arrow of the edge is used to represent the transaction direction between the two nodes connected by the edge.

[0090] At this time, the current feature association data set is initialized to an empty set by default, which can be abbreviated as an initial data set, and the expansion interval of the feature association data set is set to "expansion interval-0".

[0091] Step 014: Searching for nodes that meet multiple preset transaction characteristics in the blockchain transaction topology map to form a feature association data set of the target node address in the blockchain.

[0092] After step 014, the feature association data set, which was originally an empty set, has stored nodes that meet multiple preset transaction features. In one or more embodiments of the present application, the feature association data set can be abbreviated as a data set.

[0093] In order to further improve the effectiveness and reliability of constructing the feature association data set in step 014, in a blockchain transaction associated address discovery method provided in an embodiment of the present application, the transaction features specifically include mutual transfer features extracted from the transaction information, transaction amount exceeding threshold features, institution preference features, time preference features and amount preference features.

[0094] Among them, the mutual transfer feature can also be called "interactivity"; the transaction amount exceeding the threshold feature can also be called "generous behavior"; the institution preference feature can also be called "institution preference"; the time preference feature can also be called "time preference"; the amount preference feature can also be called "amount preference".

[0095] Correspondingly, the feature association data set specifically includes the following contents:

[0096] (1) A mutual transfer feature association dataset, which is used to store the node addresses corresponding to the nodes of the two parties in a mutual transfer relationship;

[0097] Specifically, interactivity refers to the mutual transfer between two addresses, which is represented in the blockchain transaction topology as two vertices with edges pointing to each other. This pair of addresses is said to be interactive. When such a pair of addresses is found, the pair of addresses are added one by one to the set corresponding to the feature.

[0098] (2) The transaction amount exceeding threshold feature association data set is used to store the node addresses corresponding to the nodes of both parties of the transaction when the percentage of the transfer amount to the funds held by the parties exceeds the percentage threshold;

[0099] Specifically, generous behavior refers to a transfer behavior that accounts for a very high proportion of the funds held by itself. Suppose there are node addresses A and B, node address A holds 100 yuan, and node address B holds 20 yuan. At this time, if node address A initiates a transfer of 90 yuan, then the transfer amount at this time accounts for 90% of the funds held by node address A itself. This proportion is extremely high, so this behavior is considered to be a generous behavior. Still in the above situation, if node address A transfers 50 yuan to node address B, although A's transfer ratio is not high (50%), node address B holds 70 yuan at this time, and the transfer accounts for 50 / 70=71% of its own amount, so the transfer is also considered to be a generous behavior. A generous behavior corresponds to a pair of addresses. When this pair of addresses is found, we add the pair of addresses one by one to the set corresponding to the feature.

[0100] (3) Institutional preference feature association data set, which is used to store the node addresses corresponding to each node that has transactions with the trading institution;

[0101] Specifically, institutional preference refers to whether the address has interacted with a certain exchange address. If so, it is added to the corresponding exchange set.

[0102] (4) Each time preference feature associated data set is used to store the node addresses corresponding to each node whose transaction frequency exceeds the frequency threshold in different time periods;

[0103] Specifically, time preference refers to the time interval of active transactions of the address. We divide 24 hours a day into 8 3-hour intervals. If the transaction frequency of the address reaches a peak in a certain time interval, then the address is added to the corresponding time interval set.

[0104] (5) Each amount preference feature association data set is used to store the node addresses corresponding to each node whose transaction amount belongs to different financial intervals.

[0105] Specifically, amount preference refers to the transaction amount of all statistical data, which can be divided into three amount ranges of low, medium and high according to the interval ratio of 2:6:2, and the corresponding transactions can be divided into an amount range set.

[0106] Then, after determining the data set from step 010 to step 020 and running the FP-growth algorithm, a set of associated addresses can be obtained. However, this discovery method will miss a lot of relevant information. For example, if a node address is The confidence level is 79.9%, then the address is consistent with the target node address In essence, it is also a highly correlated relationship. Directly using a certain confidence threshold (such as 80%) can easily lead to the omission of such associated node addresses. Secondly, the associated node addresses discovered in this way may not have a direct correlation in the transaction, which is reflected in the topology graph that the associated node address may not have an edge directly connected to the target node address. connection, but this gap situation is not unreasonable, which means that the associated node address has the same Other similar transaction features.

[0107] Based on this, in order to solve the above problem, after step 020, the modified steps 100 to 400 in the blockchain transaction associated address discovery method provided in the embodiment of the present application are executed.

[0108] Correspondingly, in order to further improve the effectiveness and reliability of the selection of the optimal reachable path, in a blockchain transaction associated address discovery method provided in an embodiment of the present application, see Figure 3 , step 200 in the blockchain transaction associated address discovery method specifically includes the following content:

[0109] Step 210: Determine the associated node address that has an indirect transaction relationship with the target node address in the blockchain as the destination node address, and search for all reachable paths between the target node address and the destination node address in the blockchain transaction topology graph.

[0110] Step 220: If the number of the reachable paths between the target node address and the destination node address is not unique, then the edge weight of each edge in each reachable path is calculated respectively.

[0111] Step 230: Determine the path weight of each of the reachable paths according to the edge weight of each edge in each of the reachable paths.

[0112] Specifically, the weight of each edge is the correlation between the two node addresses, also called the confidence value. Specifically, the weight of each path is the product of the weights of all the edges on the path. And find the path with the highest weight.

[0113] Step 240: Select the reachable path with the largest path weight from among the reachable paths as the optimal reachable path.

[0114] Step 250: adding other node addresses in the optimal reachable path except the target node address to the currently newly added expansion interval corresponding to the current feature association data set to expand the feature association data set.

[0115] Add the other node addresses except the target node address in the optimal reachable path to the newly added extension interval corresponding to the current feature association data set. If the current is the first round of iteration, add the other node addresses except the target node address in the optimal reachable path to the newly added "extension interval -1" corresponding to the current feature association data set. If the current is the second round of iteration, add the other node addresses except the target node address in the optimal reachable path to the newly added "extension interval -2" corresponding to the current feature association data set. And so on. After the Mth iteration, the "extension interval -M" of the data set should be added. Output the result at the same time.

[0116] In order to further illustrate the embodiment of the above-mentioned blockchain transaction associated address discovery method, the present application also provides an application example of the blockchain transaction associated address iterative discovery method, in which:

[0117] If you , , then through step 010 and step 020, the output corresponding to the associated address set may be as follows Figure 4 The topology diagram shown.

[0118] exist Figure 4 middle," " refers to the target node address, and the first node address is found through the above steps 010 and 020" " and destination node address" ", both are the target node addresses" "The associated node address. But the first node address" "with the target node address" "Directly connected, destination node address" "with the target node address" "Two nodes apart. It is generally believed that when other nodes have similar conditions, the target node address should be given priority." " neighbor nodes, which is in line with common sense. However, this interval situation is not unreasonable, which means that the destination node address " "Has the same address as the target node" "Similar other characteristics. In this case, it is natural to have a question, that is, the target node address" " and the destination node address " "Whether the nodes on the path between them also have the same address as the target node" "Related. Therefore, this application example proposes the following solution:

[0119] (1) Find the target node address " "With the destination node address that is not directly connected" ". See Figure 5 , there are 3 reachable paths, namely:

[0120] Path a: ;

[0121] Path b: ;

[0122] Path c: ;

[0123] in," "," "and" " are the node addresses corresponding to different nodes in the blockchain.

[0124] (2) For each edge on the path, find its weight.

[0125] Specifically, the weight of each edge is the correlation between the two node addresses, also called the confidence value. Taking the ath path as an example, the weights of the three edges are .in, refers to the target node address " "With the first node address" The weight of the edge between ”; Refers to the first node address " "With a node address" The weight of the edge between ”; Refers to the node address " "with node address" The weight of the edge between .

[0126] (3) Find the weight of each path.

[0127] Specifically, the weight of each path is the product of the weights of all edges on the path, and the path with the highest weight is found.

[0128] (4) For the address corresponding to each node on the path with the highest weight, add the "expansion interval -1" of the data set. For the first iteration, the "expansion interval -M" of the data set should be added after the Mth iteration. Output the results at the same time.

[0129] Then rerun the FP-growth algorithm, see Figure 6 , and repeat the iterative process based on the pre-iterative generator (virtual function module) until it is known that the current associated address set obtained by the FP-growth algorithm does not contain an associated node address that has an indirect transaction relationship with the target node address in the blockchain, stop the iteration, and output the current associated address set.

[0130] It is understandable that the application examples of this application can, to a certain extent, utilize the link relationship between the blockchain transaction topology graph, and gradually mine the association relationship between addresses in an iterative form, and propose a method for mining associated addresses based on the FP-growth algorithm, with the ultimate goal of mining the related addresses of the input address. However, the problem of information omission in the mining process of the FP-growth algorithm was considered during the mining process. A series of improved methods were then proposed. The core is that the reachable relationship between the associated address mined by the FP-growth algorithm and the input address is considered, and the nodes passed by the specific reachable path are re-added to the data set and the iterative process of mining using the FP-growth algorithm is used again. The problem of missing information in mining the blockchain transaction topology graph data by the FP-growth algorithm is overcome by hierarchical iterative mining.

[0131] In the above application scenarios, it can be found that the mining accuracy of the association mining algorithm is closely related to the analysis quality and work efficiency of data analysts. When the traditional mining algorithm based on the FP-growth algorithm is applied to the blockchain transaction topology map data, it often causes varying degrees of data loss due to the high information dimension of the blockchain transaction topology map. The algorithm proposed in this application is an address correlation mining algorithm specifically applied to the blockchain transaction topology map structure. It takes into account the connection relationship between nodes to overcome the data loss problem of the traditional mining algorithm, and ultimately can improve the analysis quality and work efficiency of data analysts.

[0132] The present application also provides a blockchain transaction associated address discovery device for executing all or part of the blockchain transaction associated address discovery method, see Figure 7 The blockchain transaction associated address discovery device specifically includes the following contents:

[0133] The judgment module 10 is used to perform a judgment step: judging whether the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, wherein the associated address set is used to store each associated node address that has a transaction association relationship with the target node address;

[0134] The optimal reachable path selection module 20 is used to, if it is determined that the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, determine the associated node address that has an indirect transaction relationship with the target node address in the blockchain as the destination node address, select the optimal reachable path from each reachable path between the target node address and the destination node address, and expand the feature association data set of the target node address in the blockchain based on other node addresses other than the target node address in the optimal reachable path;

[0135] The frequent itemset mining module 30 is used to obtain, for the current feature association data set, each associated node address having a transaction association relationship with the target node address based on the FP-growth algorithm to form a new associated address set.

[0136] The determination step may then be performed for the new associated address set.

[0137] The embodiment of the blockchain transaction associated address discovery device provided in the present application can be specifically used to execute the processing flow of the embodiment of the blockchain transaction associated address discovery method in the above-mentioned embodiment. Its functions will not be repeated here, and reference can be made to the detailed description of the above-mentioned blockchain transaction associated address discovery method embodiment.

[0138] The part of the blockchain transaction associated address discovery device that performs iterative discovery of blockchain transaction associated addresses can be executed in the server or completed in the client device. The specific selection can be based on the processing capacity of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor for specific processing of iterative discovery of blockchain transaction associated addresses.

[0139] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0140] The server and the client device may communicate with each other using any suitable network protocol, including network protocols that have not yet been developed on the date of filing this application. The network protocols may include, for example, TCP / IP, UDP / IP, HTTP, HTTPS, etc. Of course, the network protocols may also include, for example, RPC (Remote Procedure Call Protocol) and REST (Representational State Transfer) protocols used on top of the above protocols.

[0141] From the above description, it can be seen that the blockchain transaction associated address discovery device provided in the embodiment of the present application can solve the address omission problem of blockchain transaction associated addresses obtained based on the FP-growth algorithm on the basis of improving the iterative discovery efficiency of blockchain transaction associated addresses and reducing memory resource consumption, and can improve the comprehensiveness and reliability of mining blockchain transaction associated addresses, thereby effectively improving the effectiveness of applications such as abnormal transaction identification based on blockchain transaction associated address discovery results.

[0142] The embodiment of the present application also provides an electronic device, which may include a processor, a memory, a receiver and a transmitter, wherein the processor is used to execute the blockchain transaction associated address discovery method mentioned in the above embodiment, wherein the processor and the memory may be connected via a bus or other means, such as by bus connection. The receiver may be connected to the processor and the memory via wired or wireless means.

[0143] The processor may be a central processing unit (CPU). The processor may also 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, or a combination of the above chips.

[0144] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the blockchain transaction associated address discovery method in the embodiment of the present application. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, that is, the blockchain transaction associated address discovery method in the above method embodiment is implemented.

[0145] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The one or more modules are stored in the memory, and when executed by the processor, the blockchain transaction associated address discovery method in the embodiment is executed.

[0147] In some embodiments of the present application, the user equipment may include a processor, a memory, and a transceiver unit, which may include a receiver and a transmitter. The processor, memory, receiver, and transmitter may be connected through a bus system. The memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory to control the transceiver unit to send and receive signals.

[0148] As an implementation method, the functions of the receiver and the transmitter in the present application can be considered to be implemented through a transceiver circuit or a dedicated chip for transceiver, and the processor can be considered to be implemented through a dedicated processing chip, a processing circuit or a general chip.

[0149] As another implementation method, it is possible to use a general-purpose computer to implement the server provided in the embodiment of the present application, that is, to store the program code for implementing the functions of the processor, receiver, and transmitter in a memory, and the general-purpose processor implements the functions of the processor, receiver, and transmitter by executing the code in the memory.

[0150] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the aforementioned blockchain transaction associated address discovery method are implemented. The computer-readable storage medium can 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.

[0151] An embodiment of the present application also provides a computer program product, including a computer program, which implements the blockchain transaction associated address discovery method when executed by a processor.

[0152] 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 this application. 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 this application 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.

[0153] It should be clear that the present application 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 application 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 application.

[0154] In the present application, features described and / or illustrated for one embodiment may be used in the same manner or in a similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0155] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for discovering blockchain transaction associated addresses, characterized in that: include: Determination step: determining whether the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, wherein the associated address set is used to store each associated node address that has a transaction association relationship with the target node address; If so, the associated node address that has an indirect transaction relationship with the target node address in the blockchain is determined as the destination node address, the optimal reachable path is selected from each reachable path between the target node address and the destination node address, and the feature association data set of the target node address in the blockchain is expanded based on other node addresses except the target node address in the optimal reachable path; For the current feature association data set, each associated node address having a transaction association relationship with the target node address is obtained based on the FP-growth algorithm to form a new associated address set.

2. The method for discovering blockchain transaction associated addresses according to claim 1, characterized in that: Also includes: If it is determined that the current associated address set obtained by the FP-growth algorithm does not contain an associated node address that has an indirect transaction relationship with the target node address in the blockchain, then the associated address set is used as the associated address set result data corresponding to the target node address; The associated address set result data is output to perform abnormal transaction identification and / or user identity authentication.

3. The method for discovering blockchain transaction associated addresses according to claim 1, characterized in that: Before the judging step, the method further includes: Construct a feature association data set corresponding to the target node address; For the current feature association data set, each associated node address having a transaction association relationship with the target node address is obtained based on the FP-growth algorithm to form a corresponding associated address set.

4. The method for discovering blockchain transaction associated addresses according to claim 3, characterized in that: The constructing of the feature association data set corresponding to the target node address includes: Receive a blockchain transaction associated address discovery request, wherein the blockchain transaction associated address discovery request includes: a target node address in the blockchain and a maximum number of search layers of the blockchain; Based on a breadth-first search algorithm, searching in the blockchain for each node address whose shortest path distance to the target node address is less than or equal to the maximum search level of the blockchain; According to the target node address and the transaction information corresponding to each of the node addresses, a blockchain transaction topology graph corresponding to the target node address is constructed, wherein each node in the blockchain transaction topology graph represents the target node address and each of the node addresses one-to-one, and the edge connecting each of the nodes in the blockchain transaction topology graph is used to represent the transaction information between the two nodes connected by the edge, and the arrow of the edge is used to represent the transaction direction between the two nodes connected by the edge; Searching for nodes that meet multiple preset transaction features in the blockchain transaction topology graph to form a feature association data set of the target node address in the blockchain.

5. The method for discovering blockchain transaction associated addresses according to claim 4, characterized in that: The transaction features include mutual transfer features, transaction amount exceeding threshold features, institution preference features, time preference features and amount preference features extracted from the transaction information; Correspondingly, the feature association data set includes: The mutual transfer feature association data set is used to store the node addresses corresponding to the nodes of the two parties in the mutual transfer relationship; The transaction amount exceeding threshold feature associated data set is used to store the node addresses corresponding to the nodes of both parties of the transfer when the percentage of the transfer amount to the funds held by the parties exceeds the percentage threshold; The institutional preference feature association data set is used to store the node addresses corresponding to each node that has transactions with the trading institution; Each time preference feature associated data set is used to store the node addresses corresponding to each node whose transaction frequency exceeds the frequency threshold in different time periods; Each amount preference feature associated data set is used to store the node addresses corresponding to each node whose transaction amount belongs to different financial intervals.

6. The method for discovering blockchain transaction associated addresses according to claim 4, characterized in that: The step of selecting the best reachable path from each reachable path between the target node address and the destination node address, and expanding the feature association data set of the target node address in the blockchain based on other node addresses other than the target node address in the best reachable path, includes: Searching for all reachable paths between the target node address and the destination node address in the blockchain transaction topology graph; If the number of the reachable paths between the target node address and the destination node address is not unique, then respectively calculating the edge weight of each edge in each of the reachable paths; Determining the path weight of each of the reachable paths according to the edge weight of each edge in each of the reachable paths; Select the reachable path with the largest path weight from among the reachable paths as the optimal reachable path; The other node addresses except the target node address in the optimal reachable path are added to the current newly added expansion interval corresponding to the current feature association data set, so as to expand the feature association data set.

7. A blockchain transaction associated address discovery device, characterized in that: include: A judgment module, used to perform a judgment step: judging whether the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, wherein the associated address set is used to store each associated node address that has a transaction association relationship with the target node address; An optimal reachable path selection module, for, if it is determined that the current associated address set obtained by the FP-growth algorithm contains an associated node address that has an indirect transaction relationship with the target node address in the blockchain, then determining the associated node address that has an indirect transaction relationship with the target node address in the blockchain as the destination node address, selecting the optimal reachable path from each reachable path between the target node address and the destination node address, and expanding the feature association data set of the target node address in the blockchain based on other node addresses except the target node address in the optimal reachable path; The frequent item set mining module is used to obtain, for the current feature association data set, each associated node address having a transaction association relationship with the target node address based on the FP-growth algorithm to form a new associated address set.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for discovering blockchain transaction associated addresses as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for discovering blockchain transaction associated addresses as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for discovering blockchain transaction associated addresses as described in any one of claims 1 to 6 is implemented.

Images