A trading risk control method and system

Abstract

The present invention relates to the technical field of transaction risk control, and specifically to a transaction risk control method and system. The method includes the following steps: obtaining platform transaction information through a transaction risk control system; setting up a transaction data transmission and collation mechanism to collate and detect the platform transaction information, and obtaining a transaction information transmission result; establishing an information feature analysis model based on the platform transaction information, and using the information feature analysis model to analyze the transaction information transmission result to obtain transaction feature information of an online transaction platform; analyzing the platform transaction status based on the transaction feature information and the platform transaction information to ensure the risk control and secure operation of the online transaction platform. The transaction risk control method and system of the present invention utilize a mathematical model to optimize the processes of transaction data transmission, collation, analysis, and application, which can not only improve the user experience and platform operation efficiency, but also effectively ensure the security and stability of the platform.

Description

Technical Field

[0001] The present invention relates to the technical field of transaction risk control, and particularly to a transaction risk control method and system. Background Art

[0002] With the progress and application of cutting-edge mobile Internet technologies such as big data, cloud computing, artificial intelligence, and blockchain, the integration boundary between technology and finance has been continuously broadened, stimulating the innovation and transformation of transaction management models. Facing the challenges of the increasingly complex and diverse transaction market environment, traditional transaction risk management and early warning mechanisms show passivity and lag, posing tests to transaction platforms in terms of operation strategies, technological innovation, and risk prevention and control. Existing transaction data risk monitoring methods mainly rely on business risk supervision systems, with problems such as low automation degree of data processing and incomplete coverage. At the same time, there is a lack of transaction data identification models, detection technologies, and adjustment mechanisms, and it is impossible to achieve real-time acquisition, efficient processing, intelligent analysis, and automatic early warning of online transaction information.

[0003] With the development of online transaction platforms, it is necessary to systematically integrate the massive data resources inside and outside enterprises, and integrate big data and Internet technologies into traditional transaction management methods, aiming to build a transaction risk management method driven by data as the core driving force, strengthen the real-time monitoring and intelligent early warning capabilities of platform transaction risks, build an all-round and multi-level risk prevention and response mechanism, and improve the accuracy of online transaction risk assessment, the timeliness of early warning, and the intelligent level of risk disposal. Summary of the Invention

[0004] Aiming at the deficiencies of existing methods and the needs of practical applications, in order to achieve comprehensive and automated processing of transaction data, sorting, detection, and analysis and identification models are added to the transaction data prevention and control method to achieve real-time acquisition, efficient processing, intelligent analysis, and automatic early warning of online transaction information, thereby improving the accuracy of risk assessment, the timeliness of early warning, and the intelligent level of the online transaction platform. On the one hand, the present invention provides a transaction risk control method, and the method includes the following steps: obtaining platform transaction information through a transaction risk control system; setting up a transaction data transmission and sorting mechanism to sort and detect the platform transaction information, and obtaining a transaction information transmission result; establishing an information feature analysis model based on the platform transaction information, and using the information feature analysis model to analyze the transaction information transmission result to obtain the transaction feature information of the online transaction platform; analyzing the platform transaction status based on the transaction feature information and the platform transaction information to ensure the risk control and safe operation of the online transaction platform. The present invention comprehensively manages and analyzes platform transaction information based on the transaction risk control method and system, improves the risk control and safe operation level of the online transaction platform, and provides a strong guarantee for the stable development of the transaction platform and the safe transactions of users.

[0005] Optionally, the set transaction data transmission and collation mechanism collates and detects the platform transaction information, and obtains a transaction information transmission result, including: setting a transaction data transmission and collation mechanism according to the platform transaction information, where the set transaction data transmission and collation mechanism includes a transmission node transaction information model, a transaction data loss degree analysis model, and a transaction information integration model. The present invention introduces a transmission node transaction information model, a transaction data loss degree analysis model, and a transaction information integration model, which can significantly improve the performance and effect of the transaction data transmission and collation mechanism, and provide a solid support for the effective operation of the transaction risk control method.

[0006] Optionally, the set transaction data transmission and collation mechanism collating and detecting the platform transaction information includes: obtaining a propagation matrix of any node in the transaction information transmission process by using the transmission node transaction information model; obtaining the loss situation of the platform transaction information by using the transaction data loss degree analysis model; constructing a transaction information integration model based on the transmission node transaction information model and the transaction data loss degree analysis model, and obtaining a transmission information set of the online transaction platform by using the transaction information integration model. The present invention sets up a transaction data transmission and collation mechanism, which can significantly improve the actual performance of the transaction risk control method, and is conducive to ensuring the stable development and safe transaction of the online transaction platform.

[0007] Optionally, the transmission node transaction information model satisfies the following relationship:

[0008]

[0009] where, represents the propagation matrix of each node in the transaction information transmission process, represents the Softmax function, represents the matrix of the i-th node, represents the adjacency matrix of the -th node, represents the degree matrix of the -th node matrix, represents the input feature matrix corresponding to the time stamp of the -th node, represents the weight matrix of the -th node, represents the bias vector corresponding to the time stamp of the

[0010] Optionally, the transaction data loss degree analysis model satisfies the following relationship:

[0011]

[0012] Wherein, represents the loss coefficient of transaction information, represents the total number of nodes of transaction information, represents the similarity coefficient between the node propagation matrix and the sample propagation matrix of transaction information, represents the distance between the node propagation matrix and the sample propagation matrix of transaction information, represents the propagation matrix distance threshold. The present invention quantitatively evaluates the loss situation of transaction information during the transmission process through the loss coefficient, provides an intuitive and comparable evaluation standard for the trading platform, and helps to more accurately understand the loss situation and overall impact degree of transaction data.

[0013] Optionally, the transaction information integration model satisfies the following relationship:

[0014]

[0015] Wherein, represents the transmission matrix of transaction information, represents the loss coefficient of transaction information, represents the total number of nodes of transaction information, represents the propagation matrix of each node during the transmission process of transaction information. Based on the loss coefficient, the present invention can accurately reflect the loss situation of transaction information during the transmission process, is beneficial to reflecting the true situation of the information integrity of the online trading platform, and provides more accurate and comprehensive information support for the trading platform.

[0016] Optionally, an information feature analysis model is established according to the platform transaction information, and the information feature analysis model is used to analyze the transaction information transmission result to obtain the transaction feature information of the online trading platform, including: constructing an information feature analysis model by combining the transaction risk control system structure and the platform transaction information; analyzing the transaction information transmission result through the information feature analysis model to obtain the transaction feature information of the online trading platform. The present invention deeply analyzes the transaction information transmission result to reveal the internal laws and data set characteristics of transaction behaviors, helps the trading platform better grasp user needs and market dynamics, thereby providing a more transparent and fair trading environment and enhancing the trust degree of the online trading platform.

[0017] Optionally, the information feature analysis model satisfies the following relationship:

[0018]

[0019] Among them, represents the transaction feature information after analysis, represents the first feature information in the feature label model, represents the weight corresponding to the first feature, represents the first feature information included in the transmission matrix of transaction information, represents the second feature information in the feature label model, represents the weight corresponding to the second feature, represents the second feature information included in the transmission matrix of transaction information, represents the th feature information in the feature label model, represents the th weight corresponding to the feature, represents the th feature information included in the transmission matrix of transaction information. The model of the present invention can comprehensively evaluate the overall characteristics of transactions by integrating multiple feature information, ensuring the influence of important feature information on the results, and can better adapt to the complexity and diversity of transaction information.

[0020] Optionally, analyzing the platform transaction status based on the transaction feature information and the platform transaction information to ensure risk control and secure operation of the online trading platform includes: setting online trading scheduling indicators based on historical transaction information, where the online trading scheduling indicators include the association status, timing situation, and feature label situation of online transactions; analyzing the platform transaction status by combining the transaction feature information, the platform transaction information, and the online trading scheduling indicators, and obtaining the operation status of the online trading platform; adjusting the online trading platform based on the operation status of the online trading platform to achieve risk control and secure operation of the online trading platform. The present invention combines transaction feature information and platform transaction information, can more accurately identify potential risk points in transactions, and the online trading scheduling indicators make risk identification more comprehensive and specific, which helps to promote the platform to provide more convenient, efficient, and secure trading services.

[0021] In a second aspect, to be able to efficiently execute a transaction risk control method provided by the present invention, the present invention also provides a transaction risk control system. The above system includes a data collection module, a data transmission and sorting module, a transaction data analysis module, and an intelligent transaction module. The above data collection module, data transmission and sorting module, transaction data analysis module, and intelligent transaction module are interconnected. The above system executes the transaction risk control method as described in the first aspect of the present invention. The system has a compact structure and stable performance, can stably execute the transaction risk control method provided by the present invention, and improves the overall applicability and practical application ability of the present invention. Description of the Drawings

[0022] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to actual scale.

[0023] Figure 1 It is a flowchart of the transaction risk control method of the present invention;

[0024] Figure 2 It is a schematic diagram of the transaction information integration model process of the transaction risk control method of the present invention;

[0025] Figure 3 It is a schematic diagram of the analysis process of the transaction characteristic information of the transaction risk control method of the present invention;

[0026] Figure 4 It is a structure diagram of the transaction risk control system of the present invention. Specific Embodiments

[0027] The following will describe in detail the specific embodiments of the present invention. It should be noted that the embodiments described here are only for illustrative purposes and do not limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to those of ordinary skill in the art that: the present invention does not have to be practiced with these specific details. In other instances, well-known circuits, software, or methods have not been specifically described in order to avoid obscuring the present invention.

[0028] Throughout the specification, the reference to "one embodiment", "an embodiment", "one example" or "an example" means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "in one embodiment", "in an embodiment", "one example" or "an example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. Additionally, the specific features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0029] Please refer to Figure 1 , the present invention provides a transaction risk control method, and the implementation steps and specific processes of the above transaction risk control method are as follows:

[0030] S1. Obtain the platform transaction information through the transaction risk control system, and its specific steps and implementation content are as follows:

[0031] In the embodiment, a data collection module is set up in the transaction risk control system, and platform transaction information is obtained by using the data collection module. In the embodiment, the information data of the online transaction platform of Shenzhen Xiaofu Technology Co., Ltd. is taken as an example.

[0032] In an optional embodiment, the data sources and data collection processes of the online transaction platform of Shenzhen Xiaofu Technology Co., Ltd. are carefully analyzed and planned, and a comprehensive data collection module is constructed. The above collection module not only covers the core data sources of the internal system of the transaction platform, but also can receive external information sources, such as payment gateway transaction records, market analysis reports provided by third-party data service providers, etc., to ensure the comprehensiveness and multi-dimensional coverage of platform transaction information.

[0033] In order to collect platform transaction information efficiently and accurately, the data collection module is deployed in the corresponding online transaction platform of the company, and corresponding device parameters and collection methods are configured according to the characteristics of each data source. The above collection methods include but are not limited to real-time calling through API interfaces to obtain the latest transaction data, using database direct connection technology to deeply mine historical transaction records, and capturing user behavior details through log parsing technology, etc. The comprehensive application of the above data collection strategies greatly improves the collection efficiency and stability of the data collection module.

[0034] At the same time, in order to ensure the security and maintainability of transaction information, a data storage scheme is also configured. The above scheme not only involves the selection of the database to ensure the high-concurrency read and write capabilities and long-term scalability of the data, but also goes deep into the design level of the data table structure, and strives to improve the efficiency of data query and analysis through reasonable table structure arrangements and index optimizations. In addition, multiple data backup and recovery strategies are also adopted to prevent data loss or damage, providing a solid guarantee for the long-term preservation and reliable use of the data.

[0035] In the embodiment, based on the online transaction platform of Shenzhen Xiaofu Technology Co., Ltd., a series of measures such as clarifying data sources, optimizing data collection processes, and designing a reasonable data storage scheme are taken, and an efficient, stable and secure data collection module is successfully constructed, providing strong support for the stable operation and precise risk control of the online transaction platform.

[0036] Furthermore, the setting method of the data collection module in the embodiment is only an optional condition of the present invention. In one or some other embodiments, the system data collection module can be adjusted and optimized according to data collection requirements and the actual situation of the transaction platform. Different transaction platforms have different data types, data volumes and data frequencies. Adjusting the data collection module according to actual needs enables the transaction risk control system to more flexibly adapt to various complex and changeable business scenarios, ensuring the accuracy and timeliness of data collection.

[0037] S2. Set up a transaction data transmission and sorting mechanism to sort and detect the platform transaction information, and obtain the transaction information transmission result. The specific steps and implementation content are as follows:

[0038] First, a data transmission and sorting module is set up in the transaction risk control system. The above data transmission and sorting module sets up a transaction data transmission and sorting mechanism based on the platform transaction information. The transaction data transmission and sorting mechanism set up in the embodiment includes a transmission node transaction information model, a transaction data loss degree analysis model, and a transaction information integration model. The specific content is as follows:

[0039] In an optional embodiment, a propagation matrix of any node in the transaction information transmission process is obtained by using the transmission node transaction information model. The specific content is as follows:

[0040] In the embodiment, the existing graph convolutional neural network is optimized, and a transaction data transmission and sorting mechanism is set up, which means that a transmission node transaction information model, a transaction data loss degree analysis model, and a transaction information integration model are established in the data transmission and sorting module based on the platform transaction information.

[0041] In this embodiment, the convolutional neural network is further optimized. As a deep learning model for structured data, the optimized convolutional neural network can extend the core concept of the original convolutional neural network to more complex and flexible information structures. So that the optimized convolutional neural network can accurately capture and analyze the complex interaction relationships between different information nodes.

[0042] That is to say, the optimized convolutional neural network subverts the simple method of regarding signals as discrete points in Euclidean space in traditional signal technology, and instead regards information signals as attributes or features on nodes. A new node information update mechanism is introduced in the embodiment, that is, by aggregating the information of each node and its neighboring nodes, the information representation of different nodes is dynamically adjusted and optimized, which not only reflects the global topological characteristics of the optimized convolutional neural network, but also deeply reveals the potential interaction and influence relationships between different information nodes.

[0043] Different from traditional neural networks, due to the connection and mutual influence between different nodes, the propagation of gradients between nodes will become more complex and flexible. Therefore, it is necessary to consider the weight matrix, bias term, and matrix information corresponding to the same node. Thus, when updating the model parameters, the above parameters can be uniformly adjusted according to the gradients and situations of different nodes, and information processing and classification of different nodes can be realized on irregular structured data.

[0044] The transmission node transaction information model in the data transmission and sorting module in the embodiment satisfies the following relationship:

[0045]

[0046] Among them, represents the propagation matrix of each node in the process of transaction information transmission, represents the Softmax function, represents the matrix of the i-th node, represents the adjacency matrix of the th node, represents the degree matrix of the matrix of the th node, represents the input feature matrix corresponding to the timestamp of the th node, represents the weight matrix of the th node, represents the bias vector corresponding to the timestamp of the

[0047] The propagation matrix of each node in the process of transaction information transmission can describe a model or framework for the information propagation characteristics of any node, which mainly includes, but is not limited to, information such as the connection relationships between different nodes, the efficiency, direction, and path of information propagation, security, and reliability. Among them, performance indicators such as the speed, weight, and timestamp of information propagation between different nodes will affect the real-time nature and accuracy of transaction information.

[0048] The adjacency matrix of the th node, that is, the matrix corresponding to the th node. For the above adjacency matrix, the elements therein represent the connection situation between nodes. For a transaction information with n nodes, the adjacency matrix is an

[0049] matrix. If there is an edge between node i and node j, the element in the i-th row and j-th column or the j-th row and i-th column of the matrix, depending on whether it is a directed graph or an undirected graph, has a value of 1 or the weight of the edge; if there is no edge, the corresponding value at that position is 0. The above

[0050]

[0051] Among them, represents the adjacency matrix of the th node, represents the preset identity matrix.

[0052] The preset identity matrix can also be called the identity matrix, the identity matrix, or the standard identity matrix, which refers to an A matrix where the elements on the main diagonal are all 1, that is, the element in the i-th row and i-th column is 1, and the remaining elements are all 0. In the embodiment, the identity matrix can be used to represent the starting point of the transformation or the unit state form.

[0053] The degree matrix is a special matrix that can be used to represent the degrees of each node. The above matrix is a square matrix, the number of its rows and columns is equal to the number of nodes in the graph. The degree matrix is a diagonal matrix, that is, all other elements in the matrix are 0 except for the diagonal elements.

[0054] For each diagonal element in the degree matrix, it represents the degree of the corresponding node. In an undirected graph, this degree is the number of edges connected to the node; in a directed graph, the degree can be further divided into the out-degree and in-degree. Since the degree matrix is a diagonal matrix, all other elements in the matrix are 0 except for the diagonal elements, which means that the degrees or the number of edges between nodes do not directly affect the values of the non-diagonal elements.

[0055] In an optional embodiment, the degree matrix of any node matrix is established as follows:

[0056] First, it is necessary to determine the degree of each node in the graph; then, create a square matrix with the same number of nodes as the number of nodes, set the diagonal elements to the degrees of the corresponding nodes, and set the remaining elements to 0.

[0057] If the adjacency matrix of the i-th node matrix satisfies the following relationship:

[0058]

[0059] The degrees of the above nodes are as follows: the degree of node 1 is 1; the degree of node 2 is 3; the degree of node 3 is 1; the degree of node 4 is 1.

[0060] Therefore, the degree matrix of the i-th node matrix can be represented as:

[0061]

[0062] The degree matrix is a diagonal matrix used to represent the degree information of different nodes. It is constructed based on the degree, out-degree, or in-degree of each node in the graph, and the non-diagonal elements are all 0.

[0063] In the embodiment, parameters such as the constructed propagation matrix, degree matrix, and feature matrix, each row of which represents the observation at a time point, each column represents a specific attribute or feature, and at the same time, the matrix can include static features such as the inherent attributes of nodes and dynamic features that change over time according to needs.

[0064] Analyze the transaction information matrix based on a time window. To capture the temporal dependencies and short-term trends in the time series, a time window analysis can be performed on the information matrix, including calculating statistics such as the mean, median, standard deviation, maximum, minimum, etc. within a given time window. These statistics can reflect the overall characteristics of the data within a specific time window. Additionally, a sliding window technique can be applied to gradually move the time window to analyze the dynamic changes in the entire time series.

[0065] In this embodiment, a time series model is introduced. To gain a deeper understanding of the complexity of time series data and predict future trends, a time series analysis model is used in the embodiment, including but not limited to ARIMA, seasonal decomposition, exponential smoothing, etc. These models not only consider the statistics within the time window but also utilize the patterns and periodicity in historical data to predict future values.

[0066] Then perform a sequence-to-sequence conversion based on the time series model. For scenarios that require considering both past and future information simultaneously, the time series data can be converted into a sequence-to-sequence format and processed using deep learning models such as recurrent neural networks, long short-term memory networks, or gated recurrent units, which can learn the long-term dependencies in the time series and generate predicted or transformed sequences.

[0067] Furthermore, multi-dimensional time series analysis can be carried out. If the node information contains multiple related time series, then multi-dimensional time series analysis can be performed. It is necessary to consider both the synchrony and asynchrony between different sequences, as well as the interactions between different multi-dimensional time series. Methods such as covariance analysis, principal component analysis (PCA), or tensor decomposition can be used to analyze the complex relationships between different time series.

[0068] When calculating the weight matrix for different nodes, it is first necessary to clarify the meaning and purpose of the weight matrix in a specific context or application. Since the definition of the weight matrix can vary depending on the application, the number of interactions or frequencies between different nodes can be combined. The elements of the weight matrix can represent the weight from node i to node j at time t, which refers to the number of interactions between nodes i and j before time t.

[0069] The bias vector corresponding to different nodes at a time stamp can adjust the function output or the result of a linear transformation in the model, allowing the model to have a non-zero output even without input. In the data transmission and arrangement module, the bias term can be regarded as a threshold adjustment for the function for the node, allowing the node to be activated even when the input is zero, if the bias term is large enough and the function permits.

[0070] In this embodiment, a neural network framework is used and the bias vector for initializing the nodes is designed. The specific calculation content is as follows:

[0071] import tensorflow as tf

[0072] # Assume there are n transaction data nodes in the embodiment

[0073] num_neurons = n

[0074] # Initialize the bias vector with zeros

[0075] bias = tf.Variable(tf.zeros([num_neurons]), name='bias')

[0076] # Combine the bias vector with the weights of any node

[0077] # output = tf.matmul(input, weights) + bias, output = ( )

[0078] In another alternative embodiment, the loss situation of the platform transaction information is obtained by using the transaction data loss degree analysis model, and the specific content is as follows:

[0079] In the embodiment, the sample matrix and the actual matrix are compared and analyzed. The transaction data loss degree analysis function is an effective similarity measurement technique that can accurately reflect the internal relationship between different information. Through the model, it can automatically distinguish the similarity degree of transaction behaviors, patterns or features, which helps to identify information such as transaction fraud detection and market trend prediction.

[0080] The transaction data loss degree analysis function trains the network by minimizing the distance between similar samples and maximizing the distance between dissimilar samples. Based on historical information and rules, a threshold is defined. When the distance between two similar samples is less than the preset threshold, they are considered the same; when the distance between two dissimilar samples is greater than the preset threshold, they are considered different. The above transaction data loss degree analysis model satisfies the following relationship:

[0081]

[0082] Wherein, represents the loss coefficient of the transaction information, represents the total number of nodes of the transaction information, represents the similarity coefficient between the node propagation matrix and the sample propagation matrix, represents the distance between the node propagation matrix and the sample propagation matrix, Represents the propagation matrix distance threshold.

[0083] The similarity coefficient between the propagation matrices of different nodes and the sample propagation matrix refers to a quantitative index that measures the degree of similarity between the above two matrices in terms of structure, element distribution, or a certain specific property. In addition, for the similarity coefficient between the propagation matrices of different nodes and the sample propagation matrix, if they have similar structures or can be transformed into similar representation forms such as vectors or sets, any one or more of the above similarity measurement methods can be used for calculation. However, if their structures are very different or cannot be directly compared, they need to be preprocessed or transformed first so that appropriate similarity measurement methods can be applied.

[0084] The similarity coefficient between the above-mentioned propagation matrices of different nodes and the sample propagation matrix satisfies the following relationship:

[0085]

[0086] Wherein, Represents the similarity coefficient between the propagation matrix of the th node and the sample propagation matrix, Represents the scaling parameter of the eigenvector, Represents the th node propagation matrix mapped eigenvector, Represents the eigenvector mapped by the sample propagation matrix.

[0087] The scaling parameter of the eigenvector refers to the eigenvalue that can describe the way a linear transformation such as matrix multiplication affects a vector. When a linear transformation such as matrix A acts on a non-zero vector B, if the resulting vector AB is collinear with B, that is, they are on the same straight line but may have opposite directions or different lengths, then B is called an eigenvector of A, and the proportionality factor is the corresponding eigenvalue, and the above proportionality factor is actually the scaling parameter of the eigenvector B under the transformation.

[0088] The eigenvector mapped by the matrix refers to a non-zero vector whose direction remains unchanged or only undergoes a scaling transformation without rotation under the linear transformation of the matrix. The eigenvector remains unchanged in direction or only undergoes a direction reversal under the transformation of the matrix, making the relevant vector the key to understanding the sample propagation vector.

[0089] In another alternative embodiment, a transaction information integration model is constructed based on the delivery node transaction information model and the transaction data loss degree analysis model, and the delivery information set of the online transaction platform is obtained by using the transaction information integration model. The specific content is as follows:

[0090] During the process of transmitting transaction information, the propagation matrix describes the way and efficiency of transaction information spreading from one node to other nodes, and includes parameters such as the connection strength, information spreading speed, reliability, etc. between different nodes. At the same time, during the process of transmitting transaction information, due to factors such as network failures, node failures, malicious attacks, etc., the transaction data may be lost or damaged. The data loss result can be quantified as the amount of lost data, the value of the lost data, the degree of impact on the transaction process, etc.

[0091] The transaction information transmission matrix combines the propagation matrix and the transaction data loss result, and is used to comprehensively describe the state, efficiency and risk of transaction information during the transmission process. It not only considers the way and efficiency of transaction information spreading in the data transmission and sorting module, but also considers the possible losses that transaction information may suffer during the transmission process.

[0092] The above transaction information integration model satisfies the following relationship:

[0093]

[0094] Among them, represents the transmission matrix of transaction information, represents the loss coefficient of transaction information, represents the total number of nodes of transaction information, represents the propagation matrix of each node during the transmission process of transaction information.

[0095] In an optional embodiment, for the process of obtaining the transmission matrix of transaction information by the transaction information integration model, please refer to Figure 2 , where H1, H2, H3, H4, H5, H6, H7, Hi respectively represent the propagation matrices corresponding to different nodes during the transmission process of transaction information.

[0096] Based on Figure 2It can be seen that the transaction data transmission and sorting mechanism established by the above data transmission and sorting module mainly analyzes the connection relationships and information flow conditions of different nodes through the delivery node transaction information model, and obtains the propagation matrix of different nodes during the transaction information delivery process. The above matrix includes parameters such as the connection strength, information propagation speed, and reliability between different nodes. Then, the risk assessment and loss identification of the system's transaction information are carried out using the transaction data loss degree analysis model, and the possible loss situations of the transaction information during the delivery process are analyzed, such as data loss or damage caused by network failures, node failures, malicious attacks, etc. Furthermore, the probability of transaction information loss, the amount of lost data, the value of the lost data, and the impact degree on the transaction process can be quantified. Finally, the transaction information propagation matrix and the data loss risk assessment results are combined to comprehensively construct a transaction information integration model and obtain a transaction information set, deeply analyze the system's transaction information, identify the information delivery information and optimization space. Based on the transaction information integration results, the reliability and timeliness of the transaction information can be more accurately evaluated, so as to formulate more reasonable transaction decisions, which helps to reduce transaction risks and improve the transaction success rate.

[0097] In the embodiment, incorporating the loss coefficient into the transaction information integration model can more comprehensively evaluate the risks that the transaction information may suffer during the delivery process, help better understand potential data loss or damage situations, and thus formulate more effective risk management strategies.

[0098] Furthermore, the way to obtain the transaction information set in this embodiment is only an optional condition of this embodiment. In one or some other embodiments, the way to obtain the transaction information set can be optimized according to the transaction information requirements and the transaction risk control system situation. Different transaction scenarios and risk control systems have different requirements for transaction information. Optimizing the acquisition method can make the model meet the information acquisition requirements in different scenarios and improve the versatility and scalability of the model.

[0099] S3. Establish an information feature analysis model based on the platform transaction information, and use the information feature analysis model to analyze the transaction information delivery result to obtain the transaction feature information of the online trading platform. The specific steps and implementation contents are as follows:

[0100] Construct an information feature analysis model by combining the transaction risk control system structure and the platform transaction information, and analyze the transaction information delivery result through the information feature analysis model to obtain the transaction feature information of the online trading platform. The specific content is as follows:

[0101] The transaction data analysis module first aggregates and absorbs the transaction information set from the data transmission and collation module, and then uses the advanced algorithms and models in the analysis module to deeply analyze and deconstruct the transaction information set to extract key transaction characteristics, trends, and potential risk points, which helps to finally form a detailed and effective transaction information analysis report.

[0102] To more accurately grasp the transaction needs and behavior patterns, the transaction data analysis module is further used to sort out and analyze the relationships among customer information, capital flow trajectories, transaction attributes, etc. in the transaction information set. By constructing a multi-dimensional and three-dimensional customer transaction information portrait, not only can the basic information such as the financial status and credit rating of transaction participants be clearly depicted, but also the psychological characteristics such as their transaction habits and risk preferences can be deeply understood, providing a solid data foundation for personalized services and risk prevention and control.

[0103] In the embodiment, the transaction data has characteristics such as large scale, diversity, and high turnover. The system deploys an efficient data transmission and collation module, which can quickly capture and aggregate the transaction data information from each business system, and can also convert it into a transaction information set with clear structure and complete content through a series of operations such as cleaning, transformation, and integration. The above process not only realizes the seamless docking and information sharing between internal information systems, but also lays a foundation for subsequent transaction information analysis.

[0104] On this basis, the transaction data analysis module is used to integrate and analyze the transaction information. On the other hand, external data sources are introduced. The above external data has a certain degree of accuracy, reliability, and stability, and can become an important way to supplement internal transaction information. While making up for the lack of transaction data, it improves the integrity of transaction information. The transaction data analysis module integrates and complements internal and external data, effectively solving information quality problems such as information asymmetry, and providing a more comprehensive and accurate information foundation for transaction risk control methods.

[0105] The information feature analysis model in the transaction data analysis module needs to satisfy the following relationship:

[0106]

[0107] Among them, represents the transaction feature information after analysis, represents the first feature information in the feature label model, represents the weight corresponding to the first feature, represents the first feature information included in the transmission matrix of transaction information, represents the second feature information in the feature label model, represents the weight corresponding to the second feature, The second characteristic information contained in the delivery matrix representing the transaction information, Represents the first Feature information, Indicates The weights corresponding to the features, The delivery matrix of transaction information contains Feature information.

[0108] In an optional embodiment, the transaction information set processed by the transaction data analysis module is not limited to the direct transaction data of the transaction risk control system, but also covers the management data recorded in the system, which reflects the operation status and decision-making trajectory of the enterprise. In addition, the key indicator data of operation management is also included in the transaction data analysis module, thereby providing an important basis for the evaluation of business performance and monitoring operation efficiency.

[0109] Based on the above transaction data analysis module, it can be seen that this module also integrates professional data resources from third parties and relevant transaction information on the Internet. Third-party data is professional and targeted, and can provide a unique perspective and in-depth insights for transaction analysis; while Internet data is real-time, extensive and diverse, providing rich information resources for capturing transaction market dynamics and consumer behavior analysis.

[0110] In the embodiment, the transaction data analysis module can fully integrate business system transaction data, management system management data, operation management indicator data, third-party professional data and Internet transaction information, thereby constructing a multi-dimensional and multi-level data analysis framework. The above framework not only enhances the breadth and depth of data analysis, but also improves the accuracy and timeliness of analysis, and provides strong data support for risk management, business decision-making and strategic planning of the transaction risk control system.

[0111] When analyzing the data characteristics of transaction information sets, the transaction data analysis module adopts a series of technical means and strategies to explore the potential information and interrelationships of transaction data. In view of the diversity and complexity of transaction data, a flexible data extraction and conversion process is designed to ensure that the data can be processed and analyzed efficiently and accurately.

[0112] First, advanced data analysis tools are used to extract structured data targets from transaction information sets. For non-standard log-type and library table data, special scripts are written to ensure that the above information can be smoothly extracted and stored in the Hadoop distributed file system, laying the foundation for subsequent transaction data analysis.

[0113] For the acquired structured data, it is directly converted into the Hive table format, and a series of preprocessing tasks such as data cleaning, fusion, and transformation are completed relying on the powerful data processing capabilities of Hive. At the same time, a knowledge graph is constructed to graphically display the complex relationships between data, providing strong support for subsequent in-depth analysis. Throughout the entire process of data processing, the parallel computing capabilities of Spark are fully utilized, significantly improving the analysis efficiency and effect of the system's transaction data.

[0114] In the transaction data analysis module, a transaction data feature label model is constructed. In the embodiment, statistical principles and methods are used to conduct in-depth statistical analysis on the transaction information set of the trading platform. Key features of different data items can be refined by calculating statistics such as variance and standard deviation to form basic data element items. The above basic data element items, as the cornerstone of modeling analysis, are substituted into the iterative calculation process to continuously optimize and improve the feature label model.

[0115] In an optional embodiment, the construction of the customer multi-dimensional label library is completed, that is, the classification extraction and processing of different feature information in the transaction information are completed. Taking Shenzhen Xiaofu Technology Co., Ltd. as the center, integrating various internal and external data resources of the enterprise, through retrieving and analyzing multi-dimensional information such as the basic information, equity structure, personnel changes, business conditions, industrial and commercial registration, legal cases, credit records, guarantee situations, administrative penalties, and social public opinions of the enterprise, a rich and detailed transaction information set is formed. The above transaction information set not only covers the static attributes of the enterprise but also includes dynamic change indicators such as the number of overdue times, and thus can provide a comprehensive and multi-angle enterprise portrait.

[0116] In the process of establishing the feature label model, a variety of unsupervised learning algorithms such as clustering analysis, association rule mining, and collaborative filtering can be adopted to achieve in-depth insight and accurate classification of online transaction behaviors. The above model not only helps to identify value groups in the transaction process but also can effectively predict potential risks, providing strong support for enterprise operation decisions.

[0117] In addition, advanced machine learning algorithms such as GDBT, SVM, RF, LR, ARIMA, and XGBoost are fully utilized, combined with big data technology, to analyze the transaction customers in the transaction information set, including but not limited to in-depth analysis and mining of data such as the basic attributes and behavioral characteristics of transaction participants. Based on this, a group portrait of transaction customers, a product preference model, and an honesty prediction model can be successfully constructed, which helps to provide a scientific basis for the goals of precision marketing and risk management of the online trading platform.

[0118] This embodiment also introduces the Support Vector Machine (SVM) into the model library. By continuously optimizing the model parameters and algorithm design, it helps to continuously improve the performance of the Support Vector Machine (SVM) and other models to meet the business requirements and risk prevention and control of the enterprise's online trading platform.

[0119] The analyzed transaction feature information satisfies the following relationship:

[0120]

[0121] Among them, the feature information in the feature label model includes but is not limited to: basic transaction information such as transaction time, amount, type, and status; transaction user information including transaction user ID, account information, browsing history, purchase history, click behavior, etc.; commodity or service information such as commodity or service ID, name, category, price, and inventory; abnormal transaction identifiers such as abnormal transaction amount and abnormal transaction time, etc., which are used to identify potential fraud behaviors; features in transaction time series analysis, such as transaction frequency, transaction interval, transaction trend, etc., which are used to analyze users' transaction habits and patterns. The transaction feature information in the embodiment plays an important role in online transaction data analysis, helps to understand transaction requirements, optimize commodity recommendations, improve user experience, identify potential risks, etc. At the same time, through in-depth mining and analysis of relevant feature information, it can also provide more accurate marketing decision support for enterprises.

[0122] Please refer to Figure 3 , the analyzed transaction feature information satisfies the following schematic diagram, where 1, 2, m respectively represent the first, second, and the m-th feature information in the feature label model, and among them respectively represent the weights corresponding to different feature information, H1*, H2*, Hm* respectively represent different feature information, and t1, t2, tm respectively represent different feature information in the feature label model after analysis.

[0123] Based on the schematic diagram, it can be seen that the analyzed transaction feature information contains all the feature information in the feature label model, and combines the weights corresponding to different feature information for the analysis and processing of the system's transaction feature information. The above feature information can be replaced and supplemented according to the key parameters of the platform transaction information and the structural characteristics of the platform trading system. The embodiment comprehensively covers all the feature information in the feature label model and conducts analysis in combination with the corresponding weights, which can more accurately capture the essence and trend of transaction behaviors, helps to identify potential transaction patterns, abnormal behaviors or market trends, thereby improving the accuracy of transaction decisions.

[0124] The transaction data analysis module analyzes transaction feature information based on big data and machine learning technologies, which can provide strong information support for the intelligent transaction module. By automatically analyzing and processing a large amount of transaction data, it helps the intelligent transaction module to quickly generate decision-making suggestions or execute transaction instructions, thus effectively ensuring the risk control and safe operation of the online trading platform.

[0125] Furthermore, the analysis technology and specific steps of the transaction information in this embodiment are only an optional condition of this embodiment. In one or some other embodiments, the transaction information analysis technology can be adjusted according to the actual operation situation of the system and the analysis requirements of the transaction information. Adjusting the transaction information analysis technology can continuously optimize the analysis process, reduce unnecessary computing overhead, improve the analysis speed and accuracy, and thus enhance the overall performance and analysis efficiency of the system.

[0126] S4. Analyze the platform transaction status based on the transaction feature information and the platform transaction information to ensure the risk control and safe operation of the online trading platform. The specific steps and implementation contents are as follows:

[0127] First, set the online transaction scheduling indicators based on historical transaction information. In the embodiment, the online transaction scheduling mainly includes the association status, time sequence situation, and feature label situation of the online transaction. Furthermore, in this embodiment, a transaction strategy scheduling device, an intelligent display device, and a data storage device are set in the intelligent transaction module. The above transaction strategy scheduling device, intelligent display device, and data storage device realize transaction risk control according to the transaction data analysis result.

[0128] As the risk prevention and control analysis center of the online trading platform, the transaction strategy scheduling device aggregates diversified data information from the data collection module, data transmission and sorting module, and transaction data analysis module, including but not limited to the structural relationship of transaction information, external third-party information, company internal materials, and extensive external data such as industrial and commercial registration, judicial records, real estate information, provident fund payment, and social security status. By using advanced machine learning algorithms such as support vector machines, carefully constructing and continuously optimizing the risk control and credit granting models, the above process not only realizes the real-time monitoring of risks in the entire chain of online trading business, but also ensures the accuracy and fairness of credit ratings, building a solid defense line for the security of online trading.

[0129] First, conduct correlation analysis to obtain the association status of the online transaction information.

[0130] In the intelligent trading module, trading data association rules are preset. By applying unsupervised learning techniques, the trading strategy scheduling device can automatically and deeply explore the complex relationships and internal laws hidden in trading data. The above-mentioned association rules not only have high practicality and intuitiveness, but also can reveal the connections between various relevant factors, thus laying a solid information foundation for the early prediction and effective prevention and control of trading risks. The above process not only enhances the intelligence level of trading decisions, but also significantly improves the accuracy and efficiency of risk management.

[0131] Second, perform time series analysis to obtain the time series situation of online trading information.

[0132] Next is time series analysis. Time series analysis focuses on the changes and differences in trading data over time series. It can adopt various statistical means such as autocorrelation analysis and spectral analysis, and combine the construction and verification of statistical models to deeply analyze the trends and periodic laws contained in historical trading data. The above process not only increases the prediction ability of the online trading platform for future market dynamics, but also shows inestimable practical value in optimizing prediction models, formulating effective control strategies, and implementing efficient data filtering. The time series analysis provides a solid data foundation for the trading decision-making process, ensuring the scientificity and forward-looking of trading risk decisions.

[0133] Third, perform label analysis to obtain the feature label situation of online trading information.

[0134] Then perform feature label analysis. This link aims to deeply analyze the feature label situation of online trading information through label aggregation technology. The core of label analysis is to use advanced clustering and statistical analysis methods to refine specific feature data or identification information involved in transactions. Especially for high-risk feature information, the system can quickly identify customer groups with similar risk characteristics and accurately evaluate their potential risk probabilities.

[0135] The above process not only greatly simplifies the risk management and analysis process, but also significantly improves the response speed and accuracy of risk prediction. Through the real-time generated risk labels and prediction reports, enterprise risk managers and operation decision-makers can quickly obtain key information, so as to formulate more accurate and efficient risk response strategies. Label analysis not only provides strong technical support for the enterprise's risk management, but also provides a solid guarantee for the enterprise to cope with the ever-changing market environment and ensure the safety and stability of transactions.

[0136] Then, analyze the platform trading status by combining trading feature information, platform trading information, and online trading scheduling indicators, and obtain the operation situation of the online trading platform.

[0137] After completing the correlation analysis, time-series analysis, and label analysis, the intelligent trading module will further integrate transaction feature information, platform trading information, and online trading scheduling metrics to achieve a comprehensive and multi-dimensional analysis of the platform's trading status. The above process combines the in-depth mining and real-time monitoring of transaction data, which can reveal the internal logic and external manifestations of online trading activities, and thus gain a comprehensive insight into the operation of the online trading platform.

[0138] Furthermore, the trading risk control system of this embodiment will conduct a comprehensive evaluation and comparative analysis based on the key elements in the transaction feature information, such as trading frequency, amount distribution, user behavior patterns, etc., combined with the key indicators in the platform trading information, such as order processing efficiency, payment success rate, user satisfaction, etc., and the real-time data in the online trading scheduling metrics, such as trading volume, system load, response time, etc.

[0139] Through the above series of complex analysis steps, the intelligent trading module can accurately judge the operational health status of the platform, identify potential trading bottlenecks, risk points, or optimization spaces. At the same time, the system can also predict future trading trends, provide forward-looking decision-making support for platform managers, help them flexibly adjust operation strategies, optimize resource allocation, and thus ensure the continuous and stable operation and business growth of the online trading platform.

[0140] Finally, based on the operation of the online trading platform, the online trading platform is adjusted to achieve risk control and secure operation of the online trading platform.

[0141] Ultimately, based on the in-depth analysis and comprehensive evaluation of the operation of the online trading platform above, the intelligent trading module takes a series of targeted adjustment measures, which helps to achieve risk control and secure operation of the online trading platform.

[0142] The adjustment measures in the embodiment include but are not limited to: optimizing trading strategies. According to transaction feature information and market dynamics, adjust trading rules, fee structures, or preferential strategies to balance user experience and platform revenue, while reducing the occurrence probability of fraud and risky transactions.

[0143] Enhancing risk control. For high-risk customers or behavior patterns identified in label analysis, implement more stringent review processes, limit trading amounts, or take other risk control measures to effectively control credit risk and operational risk.

[0144] Improving system performance. According to the system load and response time reflected in the online trading scheduling metrics, optimize server configuration, upgrade software versions, or introduce more efficient algorithms to improve trading processing speed and stability, and reduce the risk of system failures and data loss.

[0145] In addition, it is necessary to improve supervision and compliance to ensure that the platform operation complies with relevant laws, regulations and regulatory requirements, strengthen management in aspects such as data protection, privacy policies and anti-money laundering, and enhance the compliance and credibility of the platform; through user feedback and market research, continuously optimize the platform interface, transaction process and customer service to improve user satisfaction and loyalty, laying a solid foundation for the long-term development of the platform.

[0146] Based on the trading risk control system of the present invention, the operation of the online trading platform is adjusted and optimized. The intelligent trading module can effectively achieve the goals of risk control and secure operation, ensuring the stable operation and sustainable development of the online trading platform.

[0147] Please refer to Figure 4 , in an optional embodiment, in order to efficiently execute the trading risk control method provided by the present invention, the present invention also provides a trading risk control system. The above-mentioned trading risk control system includes a data collection module, a data transmission and sorting module, a trading data analysis module and an intelligent trading module. The data collection module, the data transmission and sorting module, the trading data analysis module and the intelligent trading module are interconnected. The above-mentioned system executes the specific steps of the relevant embodiments of the trading risk control method provided by the present invention. The trading risk control system of the present invention has a complete structure, is objective and stable, can efficiently execute the trading risk control method of the present invention, and improves the overall applicability and practical application ability of the present invention.

[0148] 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 described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

[0149] 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 described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A transaction risk control method, characterized in that, It includes the following steps: Obtain the platform transaction information through the transaction risk control system; Set up a transaction data transmission and sorting mechanism to sort and detect the platform transaction information, and obtain the transaction information transmission result; Establish an information feature analysis model based on the platform transaction information, and use the information feature analysis model to analyze the transaction information transmission result to obtain the transaction feature information of the online trading platform; Analyze the platform transaction status based on the transaction feature information and the platform transaction information to ensure the risk control and secure operation of the online trading platform; The step of setting up a transaction data transmission and sorting mechanism to sort and detect the platform transaction information and obtain the transaction information transmission result includes: Set up a transaction data transmission and sorting mechanism according to the platform transaction information. The set transaction data transmission and sorting mechanism includes a transmission node transaction information model, a transaction data loss degree analysis model, and a transaction information integration model; The step of setting up a transaction data transmission and sorting mechanism to sort and detect the platform transaction information includes: Use the transmission node transaction information model to obtain the propagation matrix of any node during the transaction information transmission process; Use the transaction data loss degree analysis model to obtain the loss situation of the platform transaction information; Construct a transaction information integration model based on the transmission node transaction information model and the transaction data loss degree analysis model, and use the transaction information integration model to obtain the transmission information set of the online trading platform; The transmission node transaction information model satisfies the following relationship: ， Among them, represents the propagation matrix of each node in the process of transaction information transmission, represents the Softmax function, represents the matrix of the i-th node, represents the adjacency matrix of the j-th node, represents the degree matrix of the j-th node matrix, represents the input feature matrix corresponding to the time stamp of the j-th node, represents the weight matrix of the j-th node, represents the bias vector corresponding to the time stamp of the j-th node; The transaction data loss degree analysis model satisfies the following relationship: ， Among them, represents the loss coefficient of transaction information, represents the total number of nodes of transaction information, represents the similarity coefficient between the node propagation matrix and the sample propagation matrix, represents the distance between the node propagation matrix and the sample propagation matrix, represents the propagation matrix distance threshold; The transaction information integration model satisfies the following relationship: ， Among them, represents the transmission matrix of transaction information, represents the loss coefficient of transaction information, represents the total number of nodes of transaction information, represents the propagation matrix of each node in the process of transaction information transmission.

2. The transaction risk control method according to claim 1, wherein, The step of establishing an information feature analysis model based on the platform transaction information and using the information feature analysis model to analyze the transaction information transmission result to obtain the transaction feature information of the online trading platform includes: Construct an information feature analysis model by combining the transaction risk control system structure and the platform transaction information; Analyze the transaction information transmission result through the information feature analysis model to obtain the transaction feature information of the online trading platform.

3. The transaction risk control method according to claim 2, wherein The information feature analysis model includes: The information feature analysis model satisfies the following relationship: ， Among them, represents the transaction feature information after analysis, represents the first feature information in the feature label model, represents the weight corresponding to the first feature, represents the first feature information included in the transmission matrix of transaction information, represents the second feature information in the feature label model, represents the weight corresponding to the second feature, represents the second feature information included in the transmission matrix of transaction information, represents the feature information in the feature label model, represents the weight corresponding to the feature, represents the feature information included in the transmission matrix of transaction information.

4. The transaction risk control method according to claim 1, wherein The step of analyzing the platform transaction status based on the transaction feature information and the platform transaction information to ensure the risk control and secure operation of the online trading platform includes: Set the online trading scheduling indicators based on the historical transaction information. The online trading scheduling indicators include the association status, time sequence situation, and feature label situation of the online trading; Analyze the platform transaction status by combining the transaction feature information, the platform transaction information, and the online trading scheduling indicators, and obtain the operation situation of the online trading platform; Adjust the online trading platform based on the operation situation of the online trading platform to achieve the risk control and secure operation of the online trading platform.

5. A transaction risk control system, characterized in that, The system includes a data collection module, a data transmission and sorting module, a transaction data analysis module, and an intelligent transaction module. The data collection module, the data transmission and sorting module, the transaction data analysis module, and the intelligent transaction module are interconnected and execute the transaction risk control method according to any one of claims 1-4.

Images