A method and system for discovering a fee supply address in a blockchain

Abstract

The present invention provides a method and system for discovering a fee supply address in a blockchain, the method comprising the following steps: obtaining an address that has transactions with a target address as an address to be determined, obtaining transaction data of the address to be determined; calculating a positive interaction coefficient, a main currency cumulative transfer value coefficient, a main currency interaction coefficient, a lubrication support degree, a main currency balance maintenance degree, and a main currency cumulative transfer quantity coefficient based on the transaction data, and constructing a data vector corresponding to an address to be determined based on the positive interaction coefficient, the main currency cumulative transfer value coefficient, the main currency interaction coefficient, the lubrication support degree, the main currency balance maintenance degree, and the main currency cumulative transfer quantity coefficient; clustering the address to be determined based on the data vector, inputting the data vectors in the same cluster into a preset neural network model, and determining the cluster where the fee supply address is located through the neural network. This scheme uses the data vector of the address to be determined as a transaction feature to determine the fee supply address in the address to be determined.

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 fee supply address in a blockchain. Background Art

[0002] Most blockchain transactions require a fee. On the blockchain, a certain amount of transaction fees is required when sending a transaction.

[0003] In a blockchain network, fees are usually paid in primary coins. If the primary coin balance of an address is not enough to pay the transaction fee, then primary coins need to be transferred from other addresses to that address in order to pay the required fee. This often happens when a user wants to send a transaction but does not have enough balance. By sending primary coins from other addresses to the target address, it is ensured that the transaction can be successfully sent and confirmed by the network. These addresses are called fee supply addresses.

[0004] In the process of blockchain supervision, the address and its fee supply address can be regarded as the same entity. Since the associated addresses of each address are relatively large, the existing technology usually makes it difficult to identify the fee supply address. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method for discovering a fee supply address in a blockchain 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 fee supply address in a blockchain, the method comprising the following steps:

[0007] Get the addresses that have transactions with the target address and construct them into an address set;

[0008] The address to be determined is used as the address to be determined, and the transaction data of each address to be determined is obtained, wherein the transaction data includes the transaction quantity, the transaction value of each transaction, the handling fee value of each transaction, the currency quantity before each transaction is completed, and the occurrence time of each transaction;

[0009] For each address to be determined, the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient are calculated based on the transaction value and transaction quantity of each transaction, the main currency interaction coefficient is calculated based on the transaction quantity, the lubrication support is calculated based on the handling fee value of each transaction and the currency quantity before each transaction is completed, and the main currency balance maintenance is calculated based on the occurrence time of each transaction;

[0010] Based on the positive interaction coefficient, the main currency cumulative transfer value coefficient, the main currency interaction coefficient, the lubrication support degree, the main currency balance maintenance degree and the main currency cumulative transfer quantity coefficient, a data vector corresponding to an address to be determined is constructed;

[0011] The addresses to be determined are clustered based on the data vectors, and the data vectors in the same cluster are input into the preset neural network model. The cluster where the fee supply address is located is determined by the neural network.

[0012] The above scheme is adopted. This scheme calculates the data vector corresponding to each address to be determined based on the transaction data of each address to be determined. The values ​​of each dimension in the data vector are used as the transaction features of the address. All addresses to be determined are clustered through transaction features, and further combined into a data matrix through clustered data vectors. The addresses to be determined in the entire cluster are determined based on the pre-trained neural network model to improve the determination efficiency and accurately determine the fee supply address in the address to be determined.

[0013] In some embodiments of the present invention, in the step of inputting data vectors in the same cluster into a preset neural network model, the data vectors in the same cluster are organized into a data matrix, and the data matrix is ​​input into the preset neural network model.

[0014] In some embodiments of the present invention, in the step of determining the cluster where the handling fee supply address is located through a neural network, the pre-trained neural network model outputs the determination probability of the cluster for the handling fee supply address cluster, and compares the determination probability with a preset determination threshold to determine whether the cluster belongs to the handling fee supply address cluster. If so, the address to be determined in the cluster is determined to be the handling fee supply address.

[0015] In some embodiments of the present invention, in the step of calculating the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient based on the transaction value and transaction quantity of each transaction, the number of positive transactions from the address to be determined to the target address is determined based on the transaction value of each transaction, and the ratio of the number of positive transactions to the number of transactions of the two addresses is calculated as the positive interaction coefficient.

[0016] In some embodiments of the present invention, in the step of calculating the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient based on the transaction value and transaction quantity of each transaction, the positive transactions with the main currency as the transaction currency in the positive transactions between the address to be determined and the target address are screened, and the total amount of the main currency transferred cumulatively in the positive transactions with the main currency as the transaction currency is calculated, and the ratio of the total amount of the main currency transferred cumulatively in the positive transactions with the main currency as the transaction currency for a single address to be determined to the total amount of the main currency received cumulatively by the target address is calculated as the main currency cumulative transfer value coefficient.

[0017] In some embodiments of the present invention, in the step of calculating the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient based on the transaction value and transaction quantity of each transaction, the ratio of the cumulative number of transactions of the main currency transferred with the main currency as the transaction currency in the forward transaction between the address to be determined and the target address to the cumulative number of transactions of the main currency received by the target address is calculated as the main currency cumulative transfer quantity coefficient.

[0018] In some embodiments of the present invention, in the step of calculating the primary currency interaction coefficient based on the transaction quantity, the ratio of the transaction quantity between the address to be determined and the target address using the primary currency as the transaction currency to the transaction quantity between the address to be determined and the target address is calculated as the primary currency interaction coefficient.

[0019] In some embodiments of the present invention, in the step of calculating the lubrication support based on the handling fee value of each transaction and the amount of currency before each transaction is completed, the average of the handling fee values ​​is calculated based on the handling fee value of each transaction between the address to be determined and the target address, the poverty index is calculated based on the average of the handling fee values, and the poverty index is compared with the amount of main currency before each transaction is completed. The ratio of the number of transactions in which the amount of main currency before each transaction between the address to be determined and the target address is lower than the poverty index to the number of transactions in which the amount of main currency before each transaction between the target address and all target addresses is lower than the poverty index before each transaction is completed is calculated as the lubrication support.

[0020] In some embodiments of the present invention, in the step of calculating the maintenance degree of the main currency balance based on the time when each transaction occurs, the time when the first transaction occurs at the address to be determined is taken as the first time point, and the time when the last transaction occurs at the address to be determined is taken as the second time point. The main currency balance of the address to be determined between the first time point and the second time point is taken as a function, and the definite integral of the function between the first time point and the second time point is calculated as the maintenance degree of the main currency balance.

[0021] The second aspect of the present invention also provides a system for discovering a fee supply address in a blockchain, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0022] 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 method for discovering a fee supply address in a blockchain.

[0023] 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.

[0024] 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

[0025] 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.

[0026] Figure 1 A schematic diagram of an implementation method of a method for discovering a fee supply address in a blockchain of the present invention. DETAILED DESCRIPTION

[0027] 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.

[0028] 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.

[0029] like Figure 1 As shown, the present invention proposes a method for discovering a fee supply address in a blockchain, the method comprising the following steps:

[0030] Step S100, obtaining addresses that have transactions with the target address and constructing them into an address set;

[0031] In the specific implementation process, multiple addresses that have transactions with the target address can be directly obtained from the system. The obtained addresses are all addresses to be determined, which are constructed into an address set. Subsequently, the addresses to be determined in the address set are determined one by one.

[0032] Step S200, taking the address to be determined as the address to be determined, and obtaining the transaction data of each address to be determined, wherein the transaction data includes the transaction quantity, the transaction value of each transaction, the handling fee value of each transaction, the currency amount before each transaction is completed, and the occurrence time of each transaction;

[0033] In the specific implementation process, the transaction data and the transaction data of the main currency transaction and the transaction data of other currencies, the transaction data of the main currency transaction is the transaction data of the transaction in the currency used to pay the handling fee.

[0034] Step S300, for each address to be determined, the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient are calculated based on the transaction value and transaction quantity of each transaction, the main currency interaction coefficient is calculated based on the transaction quantity, the lubrication support degree is calculated based on the handling fee value of each transaction and the currency quantity before each transaction is completed, and the main currency balance maintenance degree is calculated based on the occurrence time of each transaction;

[0035] By adopting the above scheme, this scheme calculates the features for determining whether the address to be determined is a fee supply address based on the transaction data of the address to be determined, and can make a comprehensive determination through multiple features to ensure the accuracy of the determination.

[0036] Step S400, constructing a data vector corresponding to an address to be determined based on the positive interaction coefficient, the main currency cumulative transfer value coefficient, the main currency interaction coefficient, the lubrication support degree, the main currency balance maintenance degree and the main currency cumulative transfer quantity coefficient;

[0037] In the specific implementation process, this solution generates, for each address to be determined and for the target address, a data vector consisting of each feature as the value of each dimension.

[0038] Step S500, clustering the addresses to be determined based on the data vectors, inputting the data vectors in the same cluster into a preset neural network model, and determining the cluster where the handling fee supply address is located through the neural network.

[0039] In the specific implementation process, in the step of clustering the addresses to be determined based on the data vector, the K-means algorithm can be used for clustering. Specifically, the K-means algorithm has an important hyperparameter, which means that the data need to be clustered into several categories (clusters) in the end. The purpose of this solution is to find a cluster among the clusters, which is mostly the fee supply address.

[0040] This scheme uses grid search and silhouette coefficient to determine the optimal clustering. Grid search is the Cartesian product of hyperparameters K and C, which means that we will generate all possible values ​​of hyperparameter key-value pairs. Generally speaking, the value of K should be controlled within 20 and must be an integer greater than 0, and C∈[0,10], so this scheme will obtain parameter combinations. For each combination, this scheme uses the Calinski-Harabasz index for evaluation. The larger the index value, the clearer the boundary between clusters and the closer the points within the clusters. Therefore, for the 220 pairs of parameters generated by the grid search, this scheme selects a clustering result of the hyperparameter corresponding to the maximum value of the Calinski-Harabasz index.

[0041] After the above steps, this solution obtains the centroid coordinates of each cluster, which will be returned after clustering. The centroid coordinates of each cluster are input into the trained model, and the model returns the probability that the cluster is the fee supply address cluster. This solution selects the address in the cluster with the highest probability as the fee supply address list, which is the output of the patent.

[0042] In some embodiments of the present invention, if the maximum probability of a cluster is less than 70%, an empty list is output.

[0043] In the specific implementation process, the neural network model is a model obtained through supervised learning based on existing data. The data for training the model comes from a labeled data set. To be precise, the data set is based on the existing data and the clustering results are labeled. This solution establishes a regression task and applies a feedforward neural network to complete the task.

[0044] The above scheme is adopted. This scheme calculates the data vector corresponding to each address to be determined based on the transaction data of each address to be determined. The values ​​of each dimension in the data vector are used as the transaction features of the address. All addresses to be determined are clustered through transaction features, and further combined into a data matrix through clustered data vectors. The addresses to be determined in the entire cluster are determined based on the pre-trained neural network model to improve the determination efficiency and accurately determine the fee supply address in the address to be determined.

[0045] In some embodiments of the present invention, in the step of inputting data vectors in the same cluster into a preset neural network model, the data vectors in the same cluster are organized into a data matrix, and the data matrix is ​​input into the preset neural network model.

[0046] In a specific implementation process, each data vector is regarded as a row of a data matrix, and the data matrix is ​​composed of a plurality of rows.

[0047] In some embodiments of the present invention, in the step of determining the cluster where the handling fee supply address is located through a neural network, the pre-trained neural network model outputs the determination probability of the cluster for the handling fee supply address cluster, and compares the determination probability with a preset determination threshold to determine whether the cluster belongs to the handling fee supply address cluster. If so, the address to be determined in the cluster is determined to be the handling fee supply address.

[0048] In some embodiments of the present invention, after completing the determination of all clusters, if there are multiple clusters whose corresponding determination probabilities are greater than the determination threshold, the address to be determined in the cluster with the largest determination probability is selected as the handling fee supply address; if after completing the determination of all clusters, if there is no cluster whose corresponding determination probability is greater than the determination threshold, it is determined that there is no handling fee supply address for the target address.

[0049] By adopting the above scheme, after clustering the addresses to be determined into clusters, this scheme further determines each cluster through a pre-trained neural network model. Then, this scheme can complete the determination of the addresses to be determined in a cluster at one time, and the addresses to be determined clustered into the same cluster are of the same category. This scheme can improve the determination efficiency while ensuring the determination accuracy.

[0050] In some embodiments of the present invention, in the step of calculating the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient based on the transaction value and transaction quantity of each transaction, the number of positive transactions from the address to be determined to the target address is determined based on the transaction value of each transaction, and the ratio of the number of positive transactions to the number of transactions of the two addresses is calculated as the positive interaction coefficient.

[0051] The above scheme is adopted, and the positive interaction coefficient of this scheme is used as the transaction feature for determining the positive transaction of transferring money from the address to be determined to the target address.

[0052] In some embodiments of the present invention, in the step of calculating the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient based on the transaction value and transaction quantity of each transaction, the positive transactions with the main currency as the transaction currency in the positive transactions between the address to be determined and the target address are screened, and the total amount of the main currency transferred cumulatively in the positive transactions with the main currency as the transaction currency is calculated, and the ratio of the total amount of the main currency transferred cumulatively in the positive transactions with the main currency as the transaction currency for a single address to be determined to the total amount of the main currency received cumulatively by the target address is calculated as the main currency cumulative transfer value coefficient.

[0053] Using the above scheme, the main currency cumulative transfer value coefficient of this scheme is used as a transaction feature to determine the positive transaction value of the main currency transferred from the address to be determined to the target address.

[0054] In some embodiments of the present invention, in the step of calculating the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient based on the transaction value and transaction quantity of each transaction, the ratio of the cumulative number of transactions of the main currency transferred with the main currency as the transaction currency in the forward transaction between the address to be determined and the target address to the cumulative number of transactions of the main currency received by the target address is calculated as the main currency cumulative transfer quantity coefficient.

[0055] The above scheme is adopted, and the main currency cumulative transfer quantity coefficient of this scheme is used as a transaction feature for determining the transaction quantity of positive transactions of transferring the main currency from the address to be determined to the target address.

[0056] In some embodiments of the present invention, in the step of calculating the primary currency interaction coefficient based on the transaction quantity, the ratio of the transaction quantity between the address to be determined and the target address using the primary currency as the transaction currency to the transaction quantity between the address to be determined and the target address is calculated as the primary currency interaction coefficient.

[0057] The above scheme is adopted, and the main currency interaction coefficient of this scheme is used as a transaction feature to determine the proportion of the transaction quantity of the main currency between the address to be determined and the target address.

[0058] In some embodiments of the present invention, in the step of calculating the lubrication support based on the handling fee value of each transaction and the amount of currency before each transaction is completed, the average of the handling fee values ​​is calculated based on the handling fee value of each transaction between the address to be determined and the target address, the poverty index is calculated based on the average of the handling fee values, and the poverty index is compared with the amount of main currency before each transaction is completed. The ratio of the number of transactions in which the amount of main currency before each transaction between the address to be determined and the target address is lower than the poverty index to the number of transactions in which the amount of main currency before each transaction between the target address and all target addresses is lower than the poverty index before each transaction is completed is calculated as the lubrication support.

[0059] Using the above scheme, the lubrication support of this scheme refers to the tendency of the main currency to be transferred from the address to be determined to the target address whenever the main currency of the target address is insufficient. If the address is a fee supply address, the tendency of the main currency to be transferred to the target address needs to be guaranteed.

[0060] In some embodiments of the present invention, in the step of calculating the maintenance degree of the main currency balance based on the time when each transaction occurs, the time when the first transaction occurs at the address to be determined is taken as the first time point, and the time when the last transaction occurs at the address to be determined is taken as the second time point. The main currency balance of the address to be determined between the first time point and the second time point is taken as a function, and the definite integral of the function between the first time point and the second time point is calculated as the maintenance degree of the main currency balance.

[0061] Using the above scheme, the lubrication support of this scheme is used to determine the tendency of the address to be determined to maintain a certain main currency balance. If the address is a fee supply address, it is necessary to ensure that a certain main currency balance is maintained.

[0062] An embodiment of the present invention also provides a system for discovering a fee supply address in a blockchain, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0063] 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 method for discovering the fee supply address in the aforementioned blockchain. 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.

[0064] 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.

[0065] 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.

[0066] 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.

[0067] 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 a fee supply address in a blockchain, characterized in that: The method comprises the following steps: Get the addresses that have transactions with the target address and construct them into an address set; The address that has transactions with the target address is used as the address to be determined, and the transaction data of each address to be determined is obtained, wherein the transaction data includes the transaction quantity, the transaction value of each transaction, the handling fee value of each transaction, the currency quantity before each transaction is completed, and the occurrence time of each transaction; For each address to be determined, the positive interaction coefficient, the main currency cumulative transfer value coefficient and the main currency cumulative transfer quantity coefficient are calculated based on the transaction value and transaction quantity of each transaction, the number of positive transactions from the address to be determined to the target address is determined based on the transaction value of each transaction, and the ratio of the number of positive transactions to the number of transactions of the two addresses is calculated as the positive interaction coefficient; the positive transactions with the main currency as the transaction currency in the positive transactions between the address to be determined and the target address are screened, and the total amount of the main currency transferred in the positive transactions with the main currency as the transaction currency is calculated, and the ratio of the total amount of the main currency transferred in the positive transactions with the main currency as the transaction currency for a single address to be determined to the main currency as the transaction currency to the total amount of the main currency received by the target address is calculated as the main currency cumulative transfer value coefficient; the ratio of the number of transactions with the main currency as the transaction currency in the positive transactions between the address to be determined and the target address to the number of transactions with the main currency as the transaction currency to the total amount of the main currency received by the target address is calculated as the main currency cumulative transfer quantity coefficient; The main currency interaction coefficient is calculated based on the number of transactions. The ratio of the number of transactions between the address to be determined and the target address using the main currency as the transaction currency to the number of transactions between the address to be determined and the target address is calculated as the main currency interaction coefficient. The lubrication support is calculated based on the handling fee value of each transaction and the amount of currency before each transaction is completed. The average of the handling fee values ​​is calculated based on the handling fee value of each transaction between the address to be determined and the target address. The average of the handling fee values ​​is used as the poverty index. Based on the poverty index and the amount of main currency before each transaction is completed, the ratio of the number of transactions between the address to be determined and the target address in which the amount of main currency before each transaction is completed is lower than the poverty index and the number of transactions between the target address and all target addresses in which the amount of main currency before each transaction is completed is lower than the poverty index is calculated as the lubrication support; The main currency balance maintenance degree is calculated based on the time when each transaction occurs. The time when the first transaction occurs at the address to be determined is taken as the first time point, and the time when the last transaction occurs at the address to be determined is taken as the second time point. The definite integral of the main currency balance between the first time point and the second time point is calculated as the main currency balance maintenance degree. Based on the positive interaction coefficient, the main currency cumulative transfer value coefficient, the main currency interaction coefficient, the lubrication support degree, the main currency balance maintenance degree and the main currency cumulative transfer quantity coefficient, a data vector corresponding to an address to be determined is constructed; The addresses to be determined are clustered based on the data vectors, and the data vectors in the same cluster are input into the preset neural network model. The cluster where the fee supply address is located is determined by the neural network.

2. The method for discovering a fee supply address in a blockchain according to claim 1, characterized in that: In the step of inputting data vectors in the same cluster into a preset neural network model, the data vectors in the same cluster are organized into a data matrix, and the data matrix is ​​input into the preset neural network model.

3. The method for discovering a fee supply address in a blockchain according to claim 1 or 2, characterized in that: In the step of determining the cluster where the handling fee supply address is located through a neural network, the pre-trained neural network model outputs the determination probability of the cluster for the handling fee supply address cluster, and compares the determination probability with a preset determination threshold to determine whether the cluster belongs to the handling fee supply address cluster. If so, the address to be determined in the cluster is determined to be the handling fee supply address.

4. A system for discovering a fee supply address in a blockchain, 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 3.

Images