A method and apparatus for processing transaction data

Abstract

The present invention provides a transaction data processing method and apparatus. By constructing a transaction directed graph based on online transaction data within a preset time period, determining an initial trader set and an initial target trader set based on the transaction directed graph, and calculating the abnormal behavior scores of each node in the trader set; determining the node with the lowest abnormal behavior score in the trader set, moving it from the trader set to the excluded set and deleting it from the transaction directed graph, and recalculating the abnormal behavior scores of each node in the trader set; if the overall abnormal behavior score of the target trader set is less than the overall abnormal behavior score of the trader set, updating the target trader set to the trader set; repeating the above steps until the trader set is empty, and determining the nodes in the target buyer-seller set as abnormal traders, it is possible to quickly and effectively identify abnormal traders who may conduct market abnormal transactions within a preset time period.

Description

Technical Field

[0001] The present invention relates to the technical field of financial data management, and in particular to a transaction data processing method and device. Background Art

[0002] As a place for buying and selling financial instruments (such as stocks, bonds, currencies, futures, etc.), financial markets provide a channel for capital flow for enterprises, governments and investors, and are a core part of the global economy. With the advancement of technology, online trading platforms have gradually become the mainstream of the market, providing the convenience of real-time trading and data acquisition, allowing investors to easily participate in the global financial market through the Internet. Online trading has the advantages of high liquidity, good transparency, and low cost, but it also increases the risk of market volatility and abnormal trading behavior.

[0003] It can be seen that identifying abnormal trading behaviors and traders with abnormal trading behaviors is an important means to maintain the stability of financial markets. Therefore, a trading data processing solution can be provided to detect abnormal trading behaviors and traders by analyzing online trading data. Summary of the invention

[0004] The present invention provides a transaction data processing method and device, which are used to solve the defect in the prior art that it is difficult to identify abnormal traders with abnormal market behaviors.

[0005] The present invention provides a transaction data processing method, comprising:

[0006] Step 110, constructing a transaction directed graph based on the online transaction data within a preset time period; wherein a node of the transaction directed graph corresponds to a trader, an edge corresponds to a transaction, and edge attributes include transaction submission time, transaction time, submitted transaction volume, transaction volume, submitted transaction price, and transaction price;

[0007] Step 120, based on the transaction directed graph, determining an initial trader set and an initial target trader set, and calculating an abnormal behavior score of each node in the trader set;

[0008] Step 130, determining the node with the lowest abnormal behavior score in the trader set and moving it from the trader set to the excluder set and deleting it from the transaction directed graph, and recalculating the abnormal behavior score of each node in the trader set;

[0009] Step 140: if the overall score of abnormal behavior of the target trader set is less than the overall score of abnormal behavior of the trader set, then the target trader set is updated to the trader set;

[0010] Step 150, repeating steps 130 and 140 until the trader set is empty, and determining that the node in the target trader set is an abnormal trader.

[0011] According to a transaction data processing method provided by the present invention, the abnormal behavior score of each node in the trader set is determined based on the following method:

[0012] Based on the directed transaction graph, determining a suspicious transaction score of each transaction corresponding to an outgoing edge of any node and a suspicious transaction score of each transaction corresponding to an incoming edge of any node;

[0013] The sum of the suspicious transaction scores of each transaction corresponding to the outgoing edge of any node and the suspicious transaction scores of each transaction corresponding to the incoming edge of any node is determined as the abnormal behavior score of any node.

[0014] According to a transaction data processing method provided by the present invention, the transaction suspicion score of a transaction corresponding to any edge in the transaction directed graph is determined based on the following method:

[0015] Determine the sum of the node suspicion degrees of the two nodes connected by any one edge and the transaction suspicion degree of the transaction corresponding to any one edge as the transaction suspicion score of the transaction corresponding to any one edge;

[0016] Among them, the node suspicion degree of any node is determined based on the transaction frequency of any node in a preset time period, the transaction frequency of any node in a trading outbreak period, and the transaction correlation between any node and the nodes in the target trader set; the transaction suspicion degree of any transaction is determined based on the difference between the submission time and the transaction time of any transaction, the difference between the submitted transaction volume and the transaction volume, and the difference between the submitted transaction price and the transaction price.

[0017] According to a transaction data processing method provided by the present invention, the transaction frequency of any node in any time period is calculated based on the following formula:

[0018]

[0019] Where T(A) is the transaction frequency of node A, d is the number of time slices after dividing any time period, and X j is the number of transactions performed by node A in the jth time slice.

[0020] According to a transaction data processing method provided by the present invention, the transaction relevance between any node and the nodes in the target trader set is determined based on the following method:

[0021] Based on the transaction directed graph, determine the number of edges between any node and each node in the target trader set and the number of edges between any node and each node in the excluded trader set;

[0022] The difference between the number of edges between any node and each node in the target trader set and the number of edges between any node and each node in the excluder set is determined as the transaction relevance between any node and the nodes in the target trader set.

[0023] According to a transaction data processing method provided by the present invention, the transaction suspicion of any transaction is determined based on the following method:

[0024] If the difference between the submission time and the transaction time of any transaction is greater than the preset time difference, or the difference between the submission transaction price and the transaction price of any transaction is greater than the preset price difference, then the transaction suspicion degree of any transaction is determined to be the preset value;

[0025] Otherwise, the transaction suspicion of any transaction is determined based on the difference between the submission time and the transaction time of any transaction, the difference between the submission transaction volume and the transaction volume, and the ratio between the submission transaction price and the transaction price.

[0026] According to a transaction data processing method provided by the present invention, the target trader set or the overall abnormal behavior score of the trader set is an average value of the abnormal behavior scores of each node in the corresponding set.

[0027] The present invention also provides a transaction data processing device, comprising:

[0028] A graph construction unit, configured to construct a directed transaction graph based on online transaction data within a preset time period; wherein a node of the directed transaction graph corresponds to a trader, an edge corresponds to a transaction, and edge attributes include a submission time, a transaction time, a submission transaction volume, a transaction volume, a submission transaction price, and a transaction price;

[0029] An initialization unit, used to determine an initial trader set and an initial target trader set based on the transaction directed graph, and calculate an abnormal behavior score of each node in the trader set;

[0030] A first set updating unit, configured to determine the node with the lowest abnormal behavior score in the trader set and move it from the trader set to the excluder set and delete it from the transaction directed graph, and recalculate the abnormal behavior score of each node in the trader set;

[0031] A second set updating unit, configured to update the target trader set to the trader set when the overall score of the abnormal behavior of the target trader set is less than the overall score of the abnormal behavior of the trader set;

[0032] An iteration unit, configured to repeatedly call the first set update unit and the second set update unit until the trader set is empty, and determine that the nodes in the target trader set are abnormal traders.

[0033] The present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the trading data processing method described in any one of the above is implemented.

[0034] The present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the trading data processing method described in any one of the above is implemented.

[0035] The present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, the trading data processing method described in any one of the above is implemented.

[0036] A trading data processing method and apparatus provided by the present invention construct a trading directed graph based on online trading data within a preset time period; determine an initial trader set and an initial target trader set based on the trading directed graph, and calculate the abnormal behavior scores of each node in the trader set; determine the node with the lowest abnormal behavior score in the trader set, move it from the trader set to the excluded set, and delete it from the trading directed graph, and recalculate the abnormal behavior scores of each node in the trader set; if the overall abnormal behavior score of the target trader set is less than the overall abnormal behavior score of the trader set, update the target trader set to the trader set; repeat the above steps until the trader set is empty, and determine that the nodes in the target trader set are abnormal traders, which can quickly and effectively identify abnormal traders who may conduct market abnormal trading within a preset time period, and help improve the stability of financial market trading. Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 It is a schematic flowchart of the trading data processing method provided by the present invention;

[0039] Figure 2It is a schematic flowchart of the method for determining the abnormal behavior score of any node provided by the present invention;

[0040] Figure 3 It is a schematic structural diagram of the transaction data processing device provided by the present invention;

[0041] Figure 4 It is a schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0042] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0043] Figure 1 It is a schematic flowchart of the transaction data processing method provided by the present invention. As Figure 1 shown, the method includes:

[0044] Step 110: Based on the online transaction data within a preset time period, construct a transaction directed graph; wherein, the nodes of the transaction directed graph correspond to traders, an edge corresponds to a transaction, and the edge attributes include the submission time, transaction time, submitted transaction volume, transaction volume, submitted transaction price and transaction price of the transaction;

[0045] Step 120: Based on the transaction directed graph, determine an initial trader set and an initial target trader set, and calculate the abnormal behavior scores of each node in the trader set;

[0046] Step 130: Determine the node with the lowest abnormal behavior score in the trader set, move it from the trader set to the excluded set and delete it from the transaction directed graph, and recalculate the abnormal behavior scores of each node in the trader set;

[0047] Step 140: If the overall abnormal behavior score of the target trader set is less than the overall abnormal behavior score of the trader set, update the target trader set to the trader set;

[0048] Step 150: Repeat Step 130 and Step 140 until the trader set is empty, and determine the nodes in the target buyer and seller set as abnormal traders.

[0049] Here, the preset time period may include one or more trading days. After obtaining the online trading data within the preset time period, a trading directed graph can be constructed based on the trader, submission time (i.e., the time when the seller submits the trade), transaction time, submitted trading volume (i.e., the trading volume desired by the seller when submitting the trade), trading volume, submitted trading price (i.e., the trading price desired by the seller when submitting the trade), and transaction trading price included in each trade in the online trading data. Among them, each node of the trading directed graph corresponds to a trader, and this trader may be the seller or the buyer in different trades. Between two nodes, if there is a trade between the traders corresponding to these two nodes, then these two nodes are connected by a directed edge, and the direction of the directed edge is from the seller to the buyer. The edge attributes of each edge include information such as the submission time, transaction time, submitted trading volume, trading volume, submitted trading price, and transaction trading price of the corresponding trade.

[0050] According to this trading directed graph, an initial trader set and an initial target trader set can be constructed. Among them, the initial trader set and the initial target trader set are the same, and both contain all the nodes in the trading directed graph. Subsequently, based on this trading directed graph, the abnormal behavior scores of each node in the trader set can be calculated, and the overall abnormal behavior score of the current trader set can be calculated. It should be noted that since the initial trader set and the initial target trader set are the same, the overall abnormal behavior score of the current target trader set is also equal to the overall abnormal behavior score of the current trader set. Here, the higher the abnormal behavior score of a node, the higher the possibility that the trader corresponding to this node has conducted abnormal market trading.

[0051] In some embodiments, as Figure 2 shown, the abnormal behavior scores of each node in the trader set can be determined based on the following method:

[0052] Step 210, based on the trading directed graph, determine the trading suspicion scores of each trade corresponding to the out-edges of the any node and the trading suspicion scores of each trade corresponding to the in-edges of the any node;

[0053] Step 220, determine the sum of the trading suspicion scores of each trade corresponding to the out-edges of the any node and the trading suspicion scores of each trade corresponding to the in-edges of the any node, and use it as the abnormal behavior score of the any node.

[0054] Specifically, the trading suspicion scores of the trades corresponding to each edge in the trading directed graph can be calculated. For any node, obtain the trading suspicion scores of each trade corresponding to all the out-edges of this node and the trading suspicion scores of each trade corresponding to all the in-edges of this node, and use the sum obtained by accumulating them as the abnormal behavior score of this node.

[0055] Among them, the transaction suspicion score of the transaction corresponding to any edge is the sum of the node suspicion of the two nodes connected by the edge and the transaction suspicion of the transaction corresponding to the edge. In some embodiments, the node suspicion of any node is determined based on the transaction frequency of the node in a preset time period, the transaction frequency of the node during the transaction outbreak period, and the transaction correlation between the node and the nodes in the target trader set. Among them, the transaction correlation between any node and the nodes in the target trader set characterizes the difference in the number of transactions between the trader corresponding to the node and the suspicious trader relative to the number of transactions between the trader and the ordinary trader. The transaction suspicion of any transaction is determined based on the difference between the submission time and the transaction time of the transaction, the difference between the submitted transaction volume and the transaction volume, and the difference between the submitted transaction price and the transaction transaction price.

[0056] In other embodiments, the transaction frequency of any node in any time period is calculated based on the following formula:

[0057]

[0058] Among them, T(A) is the transaction frequency of node A in the time period, d is the number of time slices after the time period is divided, and X j is the number of transactions performed by node A in the jth time slice.

[0059] Secondly, in order to calculate the transaction correlation between any node and the nodes in the target trader set, the number of edges (including incoming edges and outgoing edges) between the node and each node in the target trader set and the number of edges (including incoming edges and outgoing edges) between the node and each node in the excluder set (the nodes in the excluder set are traders with less suspicious levels screened out in the cyclic process, which will be described in detail later) can be determined based on the transaction directed graph, and then the difference between the number of edges between the node and each node in the target trader set and the number of edges between the node and each node in the excluder set is determined as the transaction correlation between the node and the nodes in the target trader set.

[0060] Regarding the suspicion degree of any transaction, if the difference between the submission time and the transaction time of the transaction is greater than the preset time difference, or the difference between the submitted transaction price and the transaction price of the transaction is greater than the preset price difference, then determine that the suspicion degree of the transaction is the preset value (a relatively low value, for example, it can be 0); otherwise, based on the difference between the submission time and the transaction time of the transaction, the difference between the submitted trading volume and the trading volume, and the ratio of the submitted transaction price to the transaction price of the transaction, determine the suspicion degree of the transaction. In some embodiments, when the difference between the submission time and the transaction time of the transaction is not greater than the preset time difference, and the difference between the submitted transaction price and the transaction price of the transaction is not greater than the preset price difference, the suspicion degree of the transaction can be calculated based on the following formula:

[0061]

[0062] where C is the suspicion degree of the transaction, ti and tj are the submission time and the transaction time of the transaction, pi and pj are the submitted transaction price and the transaction price of the transaction, and vi and vj are the submitted trading volume and the trading volume of the transaction, is the preset time difference, is the preset price difference.

[0063] After obtaining the abnormal behavior scores of each node in the initial trader set, determine the node with the lowest abnormal behavior score in the trader set (i.e., the node with the lowest suspicion degree in the current trader set), move it from the trader set to the excluder set and delete it from the transaction directed graph to obtain a new transaction directed graph. Subsequently, based on the method provided in the above embodiments, recalculate the abnormal behavior scores of each node in the trader set based on the updated transaction directed graph, and recalculate the overall abnormal behavior score of the current trader set. If the overall abnormal behavior score of the current target trader set is less than the overall abnormal behavior score of the current trader set, then update the current target trader set to the current trader set, and update the overall abnormal behavior score of the current target trader set to the overall abnormal behavior score of the current trader set. Among them, the overall abnormal behavior score of the target trader set or the trader set is the average value of the abnormal behavior scores of each node in the corresponding set. Repeat the above steps 130 and 140 until the trader set is empty. At this time, the traders corresponding to the nodes in the target buyer-seller set are abnormal traders, and they can be monitored closely to ensure the trading stability of the financial market.

[0064] In summary, the method provided by the embodiment of the present invention constructs a transaction directed graph based on the online transaction data within a preset time period; determines an initial trader set and an initial target trader set based on the transaction directed graph, and calculates the abnormal behavior scores of each node in the trader set; determines the node with the lowest abnormal behavior score in the trader set, moves it from the trader set to the excluded set, deletes it from the transaction directed graph, and recalculates the abnormal behavior scores of each node in the trader set; if the overall abnormal behavior score of the target trader set is less than the overall abnormal behavior score of the trader set, updates the target trader set to the trader set; repeats the above steps until the trader set is empty, and determines the nodes in the target buyer-seller set as abnormal traders, which can quickly and effectively identify abnormal traders who may conduct market abnormal transactions within a preset time period, and helps to improve the stability of financial market transactions.

[0065] The transaction data processing device provided by the present invention will be described below. The transaction data processing device described below can be correspondingly referred to the transaction data processing method described above.

[0066] Based on any of the above embodiments, Figure 3 is a schematic structural diagram of the transaction data processing device provided by the present invention. As Figure 3 shown, the device includes:

[0067] A graph construction unit 310, configured to construct a transaction directed graph based on the online transaction data within a preset time period; wherein, the nodes of the transaction directed graph correspond to traders, an edge corresponds to a transaction, and the edge attributes include the submission time, transaction time, submitted trading volume, trading volume, submitted trading price, and transaction trading price of the transaction;

[0068] An initialization unit 320, configured to determine an initial trader set and an initial target trader set based on the transaction directed graph, and calculate the abnormal behavior scores of each node in the trader set;

[0069] A first set update unit 330, configured to determine the node with the lowest abnormal behavior score in the trader set, move it from the trader set to the excluded set, delete it from the transaction directed graph, and recalculate the abnormal behavior scores of each node in the trader set;

[0070] A second set update unit 340, configured to update the target trader set to the trader set when the overall abnormal behavior score of the target trader set is less than the overall abnormal behavior score of the trader set;

[0071] The iteration unit 350 is used to repeatedly call the first set updating unit and the second set updating unit until the trader set is empty, and determine that the node in the target trader set is an abnormal trader.

[0072] The device provided by the embodiment of the present invention constructs a transaction directed graph based on online transaction data within a preset time period; determines an initial trader set and an initial target trader set based on the transaction directed graph, and calculates the abnormal behavior score of each node in the trader set; determines the node with the lowest abnormal behavior score in the trader set and moves it from the trader set to the excluder set and deletes it from the transaction directed graph, and recalculates the abnormal behavior score of each node in the trader set; if the overall abnormal behavior score of the target trader set is less than the overall abnormal behavior score of the trader set, the target trader set is updated to the trader set; repeats the above steps until the trader set is empty, and determines that the nodes in the target buyer and seller set are abnormal traders, so that abnormal traders who may conduct abnormal market transactions within the preset time period can be quickly and effectively identified, which helps to improve the stability of financial market transactions.

[0073] Based on any of the above embodiments, the abnormal behavior score of each node in the trader set is determined based on the following method:

[0074] Based on the directed transaction graph, determining a suspicious transaction score of each transaction corresponding to an outgoing edge of any node and a suspicious transaction score of each transaction corresponding to an incoming edge of any node;

[0075] The sum of the suspicious transaction scores of each transaction corresponding to the outgoing edge of any node and the suspicious transaction scores of each transaction corresponding to the incoming edge of any node is determined as the abnormal behavior score of any node.

[0076] Based on any of the above embodiments, the transaction suspicion score of a transaction corresponding to any edge in the transaction directed graph is determined based on the following method:

[0077] Determine the sum of the node suspicion degrees of the two nodes connected by any one edge and the transaction suspicion degree of the transaction corresponding to any one edge as the transaction suspicion score of the transaction corresponding to any one edge;

[0078] Among them, the node suspicion degree of any node is determined based on the transaction frequency of any node in a preset time period, the transaction frequency of any node in a trading outbreak period, and the transaction correlation between any node and the nodes in the target trader set; the transaction suspicion degree of any transaction is determined based on the difference between the submission time and the transaction time of any transaction, the difference between the submitted transaction volume and the transaction volume, and the difference between the submitted transaction price and the transaction price.

[0079] Based on any of the above embodiments, the transaction frequency of any node in any time period is calculated based on the following formula:

[0080]

[0081] Where T(A) is the transaction frequency of node A, d is the number of time slices after dividing any time period, and X j is the number of transactions performed by node A in the jth time slice.

[0082] Based on any of the above embodiments, the transaction relevance between any node and the nodes in the target trader set is determined based on the following method:

[0083] Based on the transaction directed graph, determine the number of edges between any node and each node in the target trader set and the number of edges between any node and each node in the excluded trader set;

[0084] The difference between the number of edges between any node and each node in the target trader set and the number of edges between any node and each node in the excluder set is determined as the transaction relevance between any node and the nodes in the target trader set.

[0085] Based on any of the above embodiments, the transaction suspicion of any transaction is determined based on the following method:

[0086] If the difference between the submission time and the transaction time of any transaction is greater than the preset time difference, or the difference between the submission transaction price and the transaction price of any transaction is greater than the preset price difference, then the transaction suspicion degree of any transaction is determined to be the preset value;

[0087] Otherwise, the transaction suspicion of any transaction is determined based on the difference between the submission time and the transaction time of any transaction, the difference between the submission transaction volume and the transaction volume, and the ratio between the submission transaction price and the transaction price.

[0088] Based on any of the above embodiments, the target trader set or the overall abnormal behavior score of the trader set is an average value of the abnormal behavior scores of each node in the corresponding set.

[0089] Figure 4 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4As shown in the figure, the electronic device may include: a processor 410, a memory 420, a communications interface 430, and a communication bus 440. Among them, the processor 410, the memory 420, and the communication interface 430 complete communication with each other through the communication bus 440. The processor 410 may call logic instructions in the memory 420 to execute a transaction data processing method, which includes: Step 110, constructing a transaction directed graph based on online transaction data within a preset time period; wherein, the nodes of the transaction directed graph correspond to traders, one edge corresponds to a transaction, and the edge attributes include the submission time, transaction time, submitted trading volume, trading volume, submitted trading price, and transaction trading price of the transaction; Step 120, determining an initial set of traders and an initial set of target traders based on the transaction directed graph, and calculating the abnormal behavior scores of each node in the set of traders; Step 130, determining the node with the lowest abnormal behavior score in the set of traders, moving it from the set of traders to the set of excluded traders, and deleting it from the transaction directed graph, and recalculating the abnormal behavior scores of each node in the set of traders; Step 140, if the overall abnormal behavior score of the set of target traders is less than the overall abnormal behavior score of the set of traders, updating the set of target traders to the set of traders; Step 150, repeating Step 130 and Step 140 until the set of traders is empty, and determining the nodes in the set of target buyers and sellers as abnormal traders.

[0090] In addition, when the logic instructions in the above-mentioned memory 420 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0091] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the transaction data processing method provided by each of the above methods. The method includes: Step 110, constructing a transaction directed graph based on the online transaction data within a preset time period; wherein, the nodes of the transaction directed graph correspond to traders, one edge corresponds to one transaction, and the edge attributes include the submission time, transaction time, submitted trading volume, trading volume, submitted trading price, and transaction trading price of the transaction; Step 120, based on the transaction directed graph, determining an initial set of traders and an initial set of target traders, and calculating the abnormal behavior scores of each node in the set of traders; Step 130, determining the node with the lowest abnormal behavior score in the set of traders, moving it from the set of traders to the set of excluded traders, and deleting it from the transaction directed graph, and recalculating the abnormal behavior scores of each node in the set of traders; Step 140, if the overall abnormal behavior score of the set of target traders is less than the overall abnormal behavior score of the set of traders, then updating the set of target traders to the set of traders; Step 150, repeating Step 130 and Step 140 until the set of traders is empty, and determining the nodes in the set of target buyers and sellers as abnormal traders.

[0092] On the other hand, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the transaction data processing method provided by each of the above. The method includes: Step 110, constructing a transaction directed graph based on the online transaction data within a preset time period; wherein, the nodes of the transaction directed graph correspond to traders, one edge corresponds to one transaction, and the edge attributes include the submission time, transaction time, submitted trading volume, trading volume, submitted trading price, and transaction trading price of the transaction; Step 120, based on the transaction directed graph, determining an initial set of traders and an initial set of target traders, and calculating the abnormal behavior scores of each node in the set of traders; Step 130, determining the node with the lowest abnormal behavior score in the set of traders, moving it from the set of traders to the set of excluded traders, and deleting it from the transaction directed graph, and recalculating the abnormal behavior scores of each node in the set of traders; Step 140, if the overall abnormal behavior score of the set of target traders is less than the overall abnormal behavior score of the set of traders, then updating the set of target traders to the set of traders; Step 150, repeating Step 130 and Step 140 until the set of traders is empty, and determining the nodes in the set of target buyers and sellers as abnormal traders.

[0093] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0094] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A transaction data processing method, characterized in that: include: Step 110, constructing a transaction directed graph based on the online transaction data within a preset time period; wherein a node of the transaction directed graph corresponds to a trader, an edge corresponds to a transaction, and edge attributes include transaction submission time, transaction time, submitted transaction volume, transaction volume, submitted transaction price, and transaction price; Step 120, based on the transaction directed graph, determining an initial trader set and an initial target trader set, and calculating an abnormal behavior score of each node in the trader set; Step 130, determining the node with the lowest abnormal behavior score in the trader set and moving it from the trader set to the excluder set and deleting it from the transaction directed graph, and recalculating the abnormal behavior score of each node in the trader set; Step 140: if the overall score of abnormal behavior of the target trader set is less than the overall score of abnormal behavior of the trader set, the target trader set is updated to the trader set; wherein the overall score of abnormal behavior of the target trader set or the trader set is the average of the abnormal behavior scores of each node in the corresponding set; Step 150, repeating steps 130 and 140 until the trader set is empty, and determining that the node in the target trader set is an abnormal trader; The abnormal behavior score of any node is determined based on the following method: If the difference between the submission time and the transaction time of any transaction is greater than the preset time difference, or the difference between the submission transaction price and the transaction price of any transaction is greater than the preset price difference, then the transaction suspicion degree of any transaction is determined to be the preset value; Otherwise, determining the transaction suspicion of any transaction based on the difference between the submission time and the transaction time, the difference between the submission transaction volume and the transaction volume, and the ratio between the submission transaction price and the transaction price of any transaction; Based on the transaction directed graph, determining the difference between the number of edges between any node and each node in the target trader set and the number of edges between any node and each node in the excluded set as the transaction correlation between any node and the nodes in the target trader set; Determine the node suspicion of any node based on the transaction frequency of any node in a preset time period, the transaction frequency of any node in a transaction outbreak period, and the transaction correlation between any node and nodes in the target trader set; Determine the sum of the node suspicion degree of two nodes connected by any edge and the transaction suspicion degree of the transaction corresponding to any edge as the transaction suspicion score of the transaction corresponding to any edge; Based on the transaction directed graph, the transaction suspicion score of each transaction corresponding to the outgoing edge of any node and the sum of the transaction suspicion score of each transaction corresponding to the incoming edge of any node are determined as the abnormal behavior score of any node.

2. A transaction data processing device, characterized in that: include: A graph construction unit, configured to construct a directed transaction graph based on online transaction data within a preset time period; wherein a node of the directed transaction graph corresponds to a trader, an edge corresponds to a transaction, and edge attributes include a submission time, a transaction time, a submission transaction volume, a transaction volume, a submission transaction price, and a transaction price; An initialization unit, used to determine an initial trader set and an initial target trader set based on the transaction directed graph, and calculate an abnormal behavior score of each node in the trader set; A first set updating unit, configured to determine the node with the lowest abnormal behavior score in the trader set and move it from the trader set to the excluder set and delete it from the transaction directed graph, and recalculate the abnormal behavior score of each node in the trader set; A second set updating unit, configured to update the target trader set to the trader set when the overall score of the abnormal behavior of the target trader set is less than the overall score of the abnormal behavior of the trader set; wherein the overall score of the abnormal behavior of the target trader set or the trader set is the average value of the abnormal behavior scores of each node in the corresponding set; an iteration unit, configured to repeatedly enable the first set updating unit and the second set updating unit to implement corresponding functions until the trader set is empty, and determine that a node in the target trader set is an abnormal trader; The abnormal behavior score of any node is determined based on the following method: If the difference between the submission time and the transaction time of any transaction is greater than the preset time difference, or the difference between the submission transaction price and the transaction price of any transaction is greater than the preset price difference, then the transaction suspicion degree of any transaction is determined to be the preset value; Otherwise, determining the transaction suspicion of any transaction based on the difference between the submission time and the transaction time, the difference between the submission transaction volume and the transaction volume, and the ratio between the submission transaction price and the transaction price of any transaction; Based on the transaction directed graph, determining the difference between the number of edges between any node and each node in the target trader set and the number of edges between any node and each node in the excluded set as the transaction correlation between any node and the nodes in the target trader set; Determine the node suspicion of any node based on the transaction frequency of any node in a preset time period, the transaction frequency of any node in a transaction outbreak period, and the transaction correlation between any node and nodes in the target trader set; Determine the sum of the node suspicion degree of two nodes connected by any edge and the transaction suspicion degree of the transaction corresponding to any edge as the transaction suspicion score of the transaction corresponding to any edge; Based on the transaction directed graph, the transaction suspicion score of each transaction corresponding to the outgoing edge of any node and the sum of the transaction suspicion score of each transaction corresponding to the incoming edge of any node are determined as the abnormal behavior score of any node.

3. 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 program, a transaction data processing method as claimed in claim 1 is implemented.

4. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a transaction data processing method as claimed in claim 1 is implemented.

Images