Order anti-fraud management system and method

Abstract

The present invention relates to the technical field of order processing, and specifically discloses an order anti-fraud management system and method. The system is provided with a data collection module, a data management module, a user behavior monitoring module and a data alarm prompt module. First, a central processing unit responds to and receives historical order information of each user sent by an edge server, and at the same time, the central processing unit collects monitoring information of an online trading platform, so that a real-time and multi-dimensional data range is applied in order management. The order management degree of each user is obtained according to a comprehensive evaluation of the central processing unit, so as to ensure the evaluation accuracy of the order management threshold, and the order transaction behavior of the user is comprehensively considered. Finally, the order risk level of each user is determined through a risk fraud alarm cloud platform, and an alarm prompt is issued, so as to identify potential order fraud behavior, timely discover loopholes in the order business process, and take corresponding protection measures, which is helpful to improve the business status of the order, thereby improving the management efficiency of the order.

Description

Technical Field

[0001] The present invention relates to the technical field of order processing, and in particular to an order anti-fraud management system and method. Background Art

[0002] Nowadays, with the increasing types and quantities of orders, in order to improve the trust between both parties of the order, it is necessary to strictly manage the orders effectively, so as to identify potential customer fraud, and promptly discover loopholes in the order business process, and take corresponding protection measures to optimize the order business process, which will help improve the operating conditions of the order and thus improve the management efficiency of the order.

[0003] For example, the invention patent with the announcement number CN111523692B announces an order management method, an order management device and an order management system. The method includes: receiving an order; sending the order data of the order to the data storage module so that the data storage module performs a storage operation and stores the order data; sending a resource matching request to the scheduling module so that the scheduling module performs a resource matching operation and selects resources to provide the service requested by the order, wherein the resource matching operation and the storage operation for the same order are performed in parallel; when the resource matching operation for the order has been completed and the storage operation for the order has also been completed, the order is allocated to the resource selected by the resource matching operation. This enables efficient completion of order transactions under multi-platform access.

[0004] For example, the invention patent with announcement number CN106971326B announced the user expectation management system and method for orders, including front-end module, middle-end module and post-end module; in the order generation stage, the front-end module is used to estimate the cost and delivery time; in the order execution stage, the middle-end module is used to track and estimate the new delivery time expectation of the completed order when each step of the order is completed, and delay judgment and reminder are made; after the order is completed, the post-end module is used to summarize the information on the order execution status and convert the delay time into cost compensation. Through the systematic user expectation management of the front, middle and post-end of the order life cycle, the user experience when using this order system is effectively improved, and the user's clear expectations for delivery are established from the three levels of cost, time and operation.

[0005] Combining the above technical solutions, it is found that the existing order management solutions, in most cases, apply a single order management data, and in the process of order management, the management scope is small, which will make the orders completed by subsequent management unable to adapt to the corresponding application scenarios, but will lead to the invalidation of order management, so that the order management efficiency cannot be improved. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides an order anti-fraud management system and method, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides an order anti-fraud management system, including: a data acquisition module, which is used to respond to and receive the historical order information of each user sent by the edge server through a central processor, and the central processor collects the monitoring information of the online trading platform; a data management module, which is used to comprehensively evaluate the historical order information of each user and the monitoring information of the online trading platform through the central processor, and match the order anti-fraud management threshold of each user; a user behavior monitoring module, which is used to monitor the order transaction behavior of each user on the online trading platform, and analyze the order management degree of each user; a data alarm prompt module, which is used to send the order management degree of each user to the risk fraud alarm cloud platform through the central processor, and the risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt.

[0008] As a further solution, the matching obtains the order anti-fraud management threshold of each user, and the specific matching process is as follows:

[0009] The historical order information of each user and the monitoring information of the online trading platform are determined respectively to obtain the historical order management influence of each user and the monitoring influence of the online trading platform, thereby comprehensively evaluating the order comprehensive management index of each user; the order comprehensive management index of each user is matched with the order anti-fraud management threshold value corresponding to each order comprehensive management index interval preset in the order management library, thereby obtaining the order anti-fraud management threshold value of each user.

[0010] As a further solution, the order transaction behavior of each user on the online trading platform is monitored, and the order management degree of each user is analyzed. The specific monitoring process is:

[0011] By monitoring the order transaction behavior of each user on the online trading platform, the order transaction behavior data of each user is obtained, which includes the number of transaction attempts, the network delay duration of the login device, and the network jitter frequency of the login device during the order transaction monitoring period, thereby comprehensively analyzing the order management degree of each user.

[0012] As a further solution, the risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt. The specific determination process is as follows:

[0013] The order management degree of each user is compared with the order anti-fraud management threshold of each user. If the order management degree of a user is higher than the order anti-fraud management threshold of the user, the risk fraud alarm cloud platform does not need to issue an alarm prompt for the user's order; if the order management degree of a user is equal to or lower than the order anti-fraud management threshold of the user, the order management degree of the user is differenced with the order anti-fraud management threshold to obtain the order management deviation value of the user, and the order risk level corresponding to each order management deviation value interval preset by the risk fraud alarm cloud platform is compared to match the order risk level of the user. The risk fraud alarm cloud platform sends an order risk level alarm prompt to the user, thereby completing the order management alarm prompt of the user; by sending the above-mentioned order risk level alarm prompt, the order risk level of each user can be determined according to the risk fraud alarm cloud platform, and an alarm prompt can be issued.

[0014] The second aspect of the present invention provides a method for an order anti-fraud management system, including: S1. The central processor responds to and receives the historical order information of each user sent by the edge server, and at the same time the central processor collects the monitoring information of the online trading platform; S2. The central processor comprehensively evaluates the historical order information of each user and the monitoring information of the online trading platform, and matches to obtain the order anti-fraud management threshold of each user; S3. The order transaction behavior of each user on the online trading platform is monitored, and the order management degree of each user is analyzed; S4. The central processor sends the order management degree of each user to the risk fraud alarm cloud platform, and the risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt.

[0015] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0016] (1) The present invention provides an order anti-fraud management system and method. First, a central processing unit responds to and receives historical order information of each user sent by an edge server. At the same time, the central processing unit collects monitoring information of an online trading platform, so that a real-time, multi-dimensional data range is applied in order management. The central processing unit comprehensively evaluates the historical order information of each user and the monitoring information of the online trading platform to obtain the order management degree of each user, thereby ensuring the matching evaluation accuracy of the order management threshold. Finally, the risk fraud alarm cloud platform is used to determine the order risk level of each user in combination with the order anti-fraud management threshold of each user, and an alarm is issued to identify potential order fraud behaviors, timely discover loopholes in the order business process, and take corresponding protection measures, which is helpful to improve the business status of orders, thereby improving the management efficiency of orders.

[0017] (2) The present invention receives the historical order information of each user sent by the edge server through the central processor, and the central processor simultaneously collects the monitoring information of the online trading platform to ensure strict and effective management operations of the orders. The central processor comprehensively evaluates the historical order information of each user and the monitoring information of the online trading platform to accurately obtain the order management degree of each user, thereby providing a multi-dimensional data basis for subsequent order management optimization.

[0018] (3) The present invention monitors the order transaction behavior of each user on the online trading platform, monitors the number of transaction attempts, the network delay duration of the login device, and the network jitter frequency of the login device during the order transaction monitoring period, and obtains the order management degree of each user through comprehensive processing, thereby clearly monitoring the order management status of the user on the online trading platform, and providing accurate data support for subsequent improvement of order management efforts.

[0019] (4) The present invention determines the order risk level of each user through the risk fraud alarm cloud platform and issues alarm prompts, which can improve the risk determination of orders, enable orders to adapt to various application scenarios, and at the same time improve the trust between the two parties of the order, which is conducive to the efficient management of orders. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0021] Figure 1 It is a schematic diagram of system module connection of the present invention.

[0022] Figure 2 The figure is a schematic flow chart of the method steps of the present invention.

[0023] Figure 3 This is a simplified diagram of the structure involved in the present invention.

[0024] Figure numerals: 1. edge server, 2. wireless network, 3. central processing unit, 4. risk fraud warning cloud platform, 5. online trading platform. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] Reference Figure 1As shown, the first aspect of the present invention provides an order anti-fraud management system, including: a data collection module, a data management module, a user behavior monitoring module and a data alarm prompt module.

[0027] The first aspect of the present invention provides an order anti-fraud management system, which also includes an order management library for storing order anti-fraud management thresholds corresponding to each order comprehensive management index interval, weight factors corresponding to historical order management influence, and weight factors corresponding to monitoring influence, and at the same time storing various data corresponding to the following embodiments.

[0028] The data acquisition module is connected to the data management module, the data management module and the user behavior monitoring module are both connected to the data alarm prompt module, and the data management module, the user behavior monitoring module and the data alarm prompt module are all connected to the order management library.

[0029] The data collection module is used to receive the historical order information of each user sent by the edge server through the central processor response, and the central processor collects the monitoring information of the online trading platform.

[0030] Reference Figure 3 As shown, it is a simplified structural diagram involved in the present invention, specifically, the central processor 3 synchronously responds to the historical order information of each user sent by the edge server 1 and the monitoring information of the online trading platform 5 through the wireless network 2, and obtains the order anti-fraud management threshold of each user through processing; at the same time, the central processor 3 monitors the order transaction behavior of each user on the online trading platform 5, and analyzes to obtain the order management degree of each user; thus, the central processor 3 sends the order management degree of each user and the order anti-fraud management threshold of each user to the risk fraud alarm cloud platform 4 through the wireless network 2, so as to determine the order risk level of each user and issue an alarm prompt.

[0031] In this example, the central processing unit is the core part of the computer hardware system, responsible for executing instructions, processing data and controlling the operation of the computer. It has multiple data interfaces, so it can synchronously collect data sent by the edge server and data transmitted in real time by multiple sensors through a wireless network. The edge server refers to a server located between the user and the central processing unit, close to the data generation source or the user terminal, which can store multiple data types. For example, the data types that can be stored in this example include but are not limited to structured data, unstructured data, object storage data, and column storage data; the central processing unit and edge server respond to and receive data in a wireless network, which is used to effectively manage fraud-related orders; the online trading platform is also called an online trading platform or an e-commerce platform, which refers to a platform that connects buyers and sellers through a wireless network to provide an electronic environment for trading goods, services or assets.

[0032] It should be explained that this example focuses on the leasing business services, so the users in this example are the recipients of the leasing services, that is, if the order is a house rental order, the user is the housing tenant, and the order can be a bus rental order, a house rental order, a machinery equipment rental order, a container rental service order, a transportation equipment rental service order, etc.

[0033] Specifically, the historical order information of each user includes the average credit score of each user's historical orders, the average daily transaction frequency of each user's historical orders, the number of order cancellations of each user in the historical behavior cycle, and the total number of orders.

[0034] It should be explained that the historical order information of the above-mentioned users is stored in the edge server; the historical behavior period represents the time period for this example to receive data from the edge server, and its specific duration will be set according to factors such as the size of the storage data of the edge server and the number of users. This example does not make any special limitations.

[0035] Furthermore, the monitoring information of the online trading platform specifically includes the average number of order transactions per person, the average number of user logins per day, the average daily memory usage rate and the average daily network traffic.

[0036] It should be explained that the monitoring information of the above-mentioned online trading platforms can be obtained in real time through the built-in data analysis system of the online trading platform. The data analysis system can generate various operational data reports in real time, including user behavior, transaction data, system load, etc. Therefore, by collecting various data generated by the built-in data analysis system of the online trading platform, the above-mentioned average number of order transactions per capita, average daily number of user logins, average daily memory usage and average daily network traffic can be obtained.

[0037] The data management module is used to comprehensively evaluate the historical order information of each user and the monitoring information of the online trading platform through the central processing unit, and match the order anti-fraud management threshold of each user.

[0038] Specifically, the historical order management influence of each user is analyzed in the following process:

[0039] Based on the average credit score of each user's historical orders, the average daily transaction frequency of each user's historical orders, the number of order cancellations and the total number of orders within the historical behavior cycle of each user, the influence factor of the preset credit score unit value, the influence factor of the corresponding unit value of the average daily transaction frequency of orders, and the influence factor of the corresponding unit value of the order cancellation rate are extracted from the order management library at the same time, and the historical order management influence of each user is obtained through data processing.

[0040] In this example, the data processing expression of the historical order management influence of each user is as follows:

[0041]

[0042] is the average credit score of the historical orders of the t-th user, indicating the mean credit score corresponding to the completed historical orders.

[0043] The influencing factor of the credit score unit value preset for the order management library is constructed based on the relationship between the historical credit score and the historical order management influence, and a mapping set of credit scores and their corresponding weight factors is constructed. The real-time credit score is input into the mapping set to obtain the corresponding influencing factor of the credit score unit value. At the same time, the value range in this example is (0, 1).

[0044] is the average daily transaction frequency of historical orders of the t-th user, indicating the frequency of the user's order transactions.

[0045] The impact factor of the unit value corresponding to the average daily transaction frequency of orders preset for the order management library is constructed based on the relationship between the historical average daily transaction frequency of orders and the historical order management influence. A mapping set of the average daily transaction frequency of orders and its corresponding weight factor is constructed, and the real-time average daily transaction frequency of orders is input into the mapping set to obtain the impact factor of the unit value corresponding to the average daily transaction frequency of orders. At the same time, the value range in this example is (0, 1).

[0046] is the number of order cancellations of the t-th user in the historical behavior period, indicating the number of orders canceled by the user in this historical behavior period.

[0047] is the total number of orders placed by the t-th user in the historical behavior period, indicating the total number of orders placed by the user in the historical behavior period.

[0048] The impact factor of the unit value corresponding to the order cancellation rate preset for the order management library is constructed based on the relationship between the historical order cancellation rate and the historical order management influence. A mapping set of the order cancellation rate and its corresponding weight factor is constructed, and the real-time order cancellation rate is input into the mapping set to obtain the impact factor of the unit value corresponding to the order cancellation rate. At the same time, the value range in this example is (0, 1).

[0049] t is the ID of each user, , y is the total number of users.

[0050] In this example embodiment, the above historical order management influence is numerically calculated, and this example only analyzes a certain user. At the same time, the value of the influence factor of the unit value of the credit score is set to 0.1, the value of the influence factor of the unit value corresponding to the average daily transaction frequency of the order is set to 0.5, and the value of the influence factor of the unit value corresponding to the order cancellation rate is set to 0.8. If the total number of orders is set to 50, then through the changes in the credit score, the average daily transaction frequency of the order, and the number of order cancellations, the specific changes in the historical order management influence of the user are shown in Table 1:

[0051] Table 1 The impact of historical order management and corresponding parameter changes

[0052]

[0053] From Table 1 above, it can be found that in this example, the highest credit score is set to 5 points, and it can be known that the credit score in the third column is the highest, indicating that the management of this order is good. At the same time, the order transaction frequency of this order is always kept within a reasonable transaction frequency range (the reasonable range of transaction frequency is set according to factors such as the user's historical payment amount and the number of historical successful transactions. In this example, the reasonable range of transaction frequency of this user is set to be between 15 and 30). However, since the ratio of the number of order cancellations to the total number in this column is the smallest, it can be seen from the value changes in the third column that the order management efficiency of this user is relatively high. Although it shows that the impact of the order is small, the value of its historical order management impact is not the minimum value. Therefore, it can be obtained that the historical order management impact is related to multidimensional factors. Only when all factors are always in the best and reasonable state can the historical order management impact value be minimized.

[0054] In the formula, is the historical order management influence of the t-th user. In this example, the order management situation is not only related to the order itself, but also if the user corresponding to the order has a high level of fraud, it also means that the order management efficiency is not high. Therefore, by evaluating the management status of the user's historical orders, it can provide a historical reference for the subsequent judgment of the order management risk. If the order credit score in this expression is low, it means that the corresponding user's order management credibility is not high, indicating that the user's fraud risk is high, so that the user's order cancellation rate is relatively low, and the user's average daily transaction frequency is relatively abnormal, so that the subsequent order management situation is more risky, which is not conducive to the effective management of the user's order. In summary, by analyzing the user's historical order management situation, the fraud risk of the order can be evaluated, providing a more powerful data basis for subsequent risk warnings.

[0055] Furthermore, the monitoring impact of the online trading platform is analyzed in the following specific process:

[0056] Based on the average number of order transactions per capita, the average number of daily user logins, the average daily memory usage and the average daily network traffic of the online trading platform, the monitoring impact of the online trading platform is finally determined.

[0057] In this example, the monitoring impact of the above online trading platform is expressed as follows:

[0058]

[0059] The average number of order transactions per capita on the online trading platform refers to the average number of order transactions performed by a single user on the online trading platform.

[0060] The average daily number of user logins to the online trading platform refers to the average number of times users log into the online trading platform in a single day.

[0061] The influence factor of the unit value corresponding to the user behavior activity indicator preset for the order management library is constructed based on the relationship between the historical user behavior activity indicator and the monitoring influence, and a mapping set of the user behavior activity indicator and its corresponding weight factor is constructed. The real-time user behavior activity indicator is input into the mapping set to obtain the influence factor of the unit value corresponding to the user behavior activity indicator. At the same time, the value range in this example is (0, 1); the user behavior activity indicator is the sum of the average number of order transactions per capita and the average number of daily user logins.

[0062] It is the average daily memory usage rate of the online trading platform, which means the ratio of the memory used by the online trading platform in a single day to its total memory capacity.

[0063] The impact factor of the unit value corresponding to the daily average memory usage preset for the order management library is constructed based on the relationship between the historical daily average memory usage and the monitoring impact. A mapping set of the daily average memory usage and its corresponding weight factor is constructed, and the real-time daily average memory usage is input into the mapping set to obtain the impact factor of the unit value corresponding to the daily average memory usage. At the same time, the value range in this example is (0, 1).

[0064] It is the average daily network traffic of the online trading platform, which means the network speed of the online trading platform transmitted through a specific network (such as the Internet, local area network, etc.) in a single day.

[0065] The impact factor of the unit value of the daily average network traffic preset for the order management library is constructed based on the relationship between the historical daily average network traffic and the monitoring impact. A mapping set of the daily average network traffic and its corresponding weight factor is constructed, and the real-time daily average network traffic is input into the mapping set to obtain the impact factor of the unit value of the daily average network traffic. At the same time, the value range in this example is (0, 1).

[0066] in, is the monitoring influence of the online trading platform. In this example, the management of orders is closely related to the transaction information of the corresponding online trading platform. If the average number of order transactions per capita and the average daily number of user logins on the online trading platform are both increasing, it means that the online trading platform has more orders, which increases the difficulty of order management. As a result, the memory usage of the online trading platform is higher, which will lead to a decrease in the network speed of the online trading platform, that is, the network traffic is slower, thus affecting the efficient management of orders. In summary, if the average number of order transactions per capita, the average daily number of user logins and the memory usage rate of the online trading platform are all on the rise, and the network traffic of the online trading platform is low, it will comprehensively lead to insufficient management of the platform's orders, ultimately affecting the order management efficiency.

[0067] Specifically, the matching obtains the order anti-fraud management threshold of each user, and the specific matching process is as follows:

[0068] The historical order information of each user and the monitoring information of the online trading platform are determined respectively, and the historical order management influence of each user and the monitoring influence of the online trading platform are obtained, thereby comprehensively evaluating the comprehensive order management index of each user.

[0069] The order comprehensive management index of each user is matched with the order anti-fraud management threshold value corresponding to each order comprehensive management index interval preset in the order management library, thereby obtaining the order anti-fraud management threshold value of each user, and the matching process is as follows:

[0070] Each order comprehensive management index interval corresponds to an order anti-fraud management threshold. When querying the order comprehensive management index interval to which a user's order comprehensive management index belongs, the order anti-fraud management threshold corresponding to the order comprehensive management index interval is the user's order anti-fraud management threshold.

[0071] Furthermore, the order comprehensive management index of each user is specifically expressed as follows:

[0072]

[0073] In the formula, is the comprehensive order management index of the t-th user. In this example, through the multi-factor analysis of the above expression, it can be obtained that the historical order management influence and the monitoring influence will affect the order management degree of this expression, indicating that the greater the historical order management influence and the monitoring influence, the lower the efficiency of order management, that is, the smaller the user's order management degree, the more management measures are needed to improve the order management behavior.

[0074] is the historical order management influence of the t-th user, which is a value obtained by comprehensively evaluating the average credit score of historical orders, the average daily transaction frequency of historical orders, the number of order cancellations, and the total number of orders.

[0075] The weight factor corresponding to the historical order management influence preset for the order management library is constructed based on the relationship between the previous historical order management influence and the order comprehensive management index. A mapping set of the historical order management influence and its corresponding weight factor is constructed, and the real-time historical order management influence is input into the mapping set to obtain the weight factor corresponding to the historical order management influence. At the same time, the value range in this example is (0, 1).

[0076] The monitoring impact of the online trading platform is obtained by evaluating multiple factors such as the number of order transactions per capita, the average number of user logins per day, the average daily memory usage rate and the average daily network traffic.

[0077] The weight factor corresponding to the monitoring influence preset for the order management library is constructed based on the relationship between the historical monitoring influence and the order comprehensive management index. A mapping set of the monitoring influence and its corresponding weight factor is constructed, and the real-time monitoring influence is input into the mapping set to obtain the weight factor corresponding to the monitoring influence. At the same time, the value range in this example is (0, 1).

[0078] t is the ID of each user, , y is the total number of users.

[0079] In a specific embodiment, the present invention receives historical order information of each user sent by the edge server in response to the central processor, and the central processor simultaneously collects monitoring information of the online trading platform to ensure strict and effective management operations of the orders. The central processor comprehensively evaluates the historical order information of each user and the monitoring information of the online trading platform to accurately obtain the order management degree of each user, providing a multi-dimensional data basis for subsequent order management optimization.

[0080] The user behavior monitoring module is used to monitor the order transaction behavior of each user on the online trading platform and analyze the order management degree of each user.

[0081] Specifically, the order transaction behavior of each user on the online trading platform is monitored, and the order management degree of each user is obtained by analysis. The specific monitoring process is:

[0082] By monitoring the order transaction behavior of each user on the online trading platform, the order transaction behavior data of each user is monitored, and the order transaction behavior data includes the number of transaction attempts during the order transaction monitoring period, the network delay duration of the login device, and the network jitter frequency of the login device. The specific acquisition method is real-time monitoring through the data analysis system built into the online trading platform, that is, the acquisition method is the same as the monitoring information acquisition method of the above-mentioned online trading platform, and finally the number of transaction attempts during the order transaction monitoring period, the network delay duration of the login device, and the network jitter frequency of the login device can be obtained; wherein the order transaction monitoring period refers to the time period corresponding to the central processing unit monitoring the multi-dimensional data of the online trading platform, which can be monitored through the task manager of the central processing unit.

[0083] The order management degree of each user is obtained through comprehensive analysis. The specific expression is as follows:

[0084]

[0085] In the formula, is the order management degree of the t-th user. In this example, if the user manages the order improperly during the order management process, it will also affect the management strength. Therefore, if the number of transaction attempts of the user is too high, it means that the user cannot effectively trade the order. This factor will be affected by the network of the device corresponding to the user's login to the online trading platform. That is, if the network circulation speed corresponding to the user's login device is slow, it means that the network delay time is long and a large degree of jitter will occur, which will affect the user's online transaction and ultimately make the user's order management efficiency low. In summary, if the number of transaction attempts of the user, the device network delay is long, and the device network jitter is too large, the order management degree of this expression will be low, resulting in a low management strength.

[0086] It is the number of transaction attempts of the t-th user during the order transaction monitoring period, indicating the number of successful transaction attempts made by the user when conducting order transactions.

[0087] The impact factor corresponding to a single transaction attempt preset for the order management library is constructed based on the relationship between the number of historical transaction attempts and the order management degree. A mapping set of the number of transaction attempts and their corresponding weight factors is constructed, and the real-time number of transaction attempts is input into the mapping set to obtain the impact factor corresponding to a single transaction attempt. At the same time, the value range in this example is (0, 1).

[0088] It is the network delay duration of the login device of the tth user during the order transaction monitoring period, indicating the time period during which the network of the user's login device is delayed when the user is conducting an order transaction.

[0089] The impact factor of the unit value corresponding to the network delay time preset for the order management library is constructed based on the relationship between the historical network delay time and the order management degree. A mapping set of network delay time and its corresponding weight factor is constructed, and the real-time network delay time is input into the mapping set to obtain the impact factor of the unit value corresponding to the network delay time. At the same time, the value range in this example is (0, 1).

[0090] is the network jitter frequency of the login device of the tth user during the order transaction monitoring period, indicating the frequency of network jitter of the login device of the user when performing order transactions.

[0091] The impact factor of the unit value of the network jitter frequency preset for the order management library is constructed based on the relationship between the historical network jitter frequency and the order management degree. A mapping set of the network jitter frequency and its corresponding weight factor is constructed, and the real-time network jitter frequency is input into the mapping set to obtain the impact factor of the unit value of the network jitter frequency. At the same time, the value range in this example is (0, 1).

[0092] t is the ID of each user, , y is the total number of users.

[0093] In a specific embodiment, the present invention monitors the order transaction behavior of each user on the online trading platform, monitors the number of transaction attempts, the login device network delay duration, and the login device network jitter frequency during the order transaction monitoring period, and obtains the order management degree of each user through comprehensive processing, thereby clearly monitoring the user's order management status on the online trading platform, and providing accurate data support for subsequent improvement of order management efforts.

[0094] The data alarm prompt module is used to send the order management level of each user to the risk fraud alarm cloud platform through the central processor. The risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt.

[0095] In this example, the risk fraud warning cloud platform is used to determine the risk level of an order and issue warnings for the order, and is connected to the central processor via a wireless network.

[0096] Specifically, the risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt. The specific determination process is as follows:

[0097] The order management degree of each user is compared with the corresponding order anti-fraud management threshold of each user. The comparison is one-to-one, that is, the order management degree of a user is only compared with the order anti-fraud management threshold of the user. If the order management degree of a user is higher than the order anti-fraud management threshold of the user, it means that the order management degree of the user is within a reasonable management range, and the risk fraud alarm cloud platform does not need to issue an alarm prompt for the user's order.

[0098] If a user's order management degree is equal to or lower than the user's order anti-fraud management threshold, it means that the user's order management status has certain management risks. Then the user's order management degree and the order anti-fraud management threshold are processed by difference to obtain the user's order management deviation value. The order risk level corresponding to each order management deviation value interval preset by the risk fraud alarm cloud platform is compared to match the user's order risk level. The specific matching process is as follows:

[0099] Each order management deviation value interval corresponds to an order risk level. The risk fraud alarm cloud platform queries the order management deviation value interval to which the order management deviation value belongs. The order risk level corresponding to the order management deviation interval is the order risk level of the user. This example sets the above order management deviation value interval to three intervals, which correspond to three order risk levels, namely, the first order management deviation value interval, the corresponding value range is [0, 5], and the matched order risk level is a low risk level; the second order management deviation value interval, the corresponding value range is (5, 10), and the matched order risk level is a medium risk level; the remaining values ​​are the third order management deviation value interval, and the matched order risk level is a high risk level.

[0100] The risk fraud alarm cloud platform will send an order risk level alarm to the user to complete the user's order management alarm. For example, if the order management deviation value in this example is 5, the matched order risk level of the user is a low risk level, indicating that the management efficiency of the user's corresponding order has a low risk and needs further management optimization. Specifically, the risk fraud alarm cloud platform will transmit the obtained low risk level to the user's order management software through the wireless network, prompting the user that the order management risk is low and there may be some potential problems that need further optimization, such as further performance optimization of the order's associated hardware equipment, real-time monitoring of abnormal conditions in the environmental area to which the order belongs and timely response measures, etc., so as to obtain order management with a lower risk level and improve order management efficiency.

[0101] By sending the above-mentioned warning prompts of order risk levels, the order risk level of each user can be determined according to the risk fraud warning cloud platform, and warning prompts can be issued.

[0102] In a specific embodiment, the present invention determines the order risk level of each user through a risk fraud alarm cloud platform and issues alarm prompts, which can improve the risk determination of orders, enable orders to adapt to a variety of application scenarios, and at the same time improve the trust between the two parties to the order, which helps to efficiently manage orders.

[0103] Reference Figure 2 As shown, the second aspect of the present invention provides a method for an order anti-fraud management system, including: S1. The central processor responds to and receives the historical order information of each user sent by the edge server, and at the same time the central processor collects the monitoring information of the online trading platform; S2. The central processor comprehensively evaluates the historical order information of each user and the monitoring information of the online trading platform, and matches to obtain the order anti-fraud management threshold of each user; S3. The order transaction behavior of each user on the online trading platform is monitored, and the order management degree of each user is analyzed; S4. The central processor sends the order management degree of each user to the risk fraud alarm cloud platform, and the risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt.

[0104] In a specific embodiment, the present invention provides an order anti-fraud management system and method. First, the central processor responds to the historical order information of each user sent by the edge server. At the same time, the central processor collects the monitoring information of the online trading platform, so that the order management aspect applies a real-time, multi-dimensional data range. The central processor comprehensively evaluates the historical order information of each user and the monitoring information of the online trading platform to obtain the order management degree of each user, thereby ensuring the matching evaluation accuracy of the order management threshold. Finally, the risk fraud alarm cloud platform is combined with the order anti-fraud management threshold of each user to determine the order risk level of each user, and an alarm is issued to identify potential order fraud behaviors, timely discover loopholes in the order business process, and take corresponding protection measures, which is helpful to improve the operating status of the order, thereby improving the order management efficiency.

[0105] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. An order anti-fraud management system, characterized in that: include: The data collection module is used to receive the historical order information of each user sent by the edge server through the central processor response, and the central processor collects the monitoring information of the online trading platform; The data management module is used to comprehensively evaluate the historical order information of each user and the monitoring information of the online trading platform through the central processor, and match the order anti-fraud management threshold of each user; User behavior monitoring module is used to monitor the order transaction behavior of each user on the online trading platform and analyze the order management degree of each user; The data alarm prompt module is used to send the order management level of each user to the risk fraud alarm cloud platform through the central processor. The risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt; The matching obtains the order anti-fraud management threshold of each user, and the specific matching process is as follows: Determine the historical order information of each user and the monitoring information of the online trading platform respectively, obtain the historical order management influence of each user and the monitoring influence of the online trading platform, and thus comprehensively evaluate the comprehensive order management index of each user; Matching the order comprehensive management index of each user with the order anti-fraud management threshold corresponding to each order comprehensive management index interval preset in the order management library, thereby obtaining the order anti-fraud management threshold of each user; The order transaction behavior of each user on the online trading platform is monitored, and the order management degree of each user is obtained by analysis. The specific monitoring process is as follows: By monitoring the order transaction behavior of each user on the online trading platform, the order transaction behavior data of each user is obtained, and the order transaction behavior data includes the number of transaction attempts, the network delay time of the login device, and the network jitter frequency of the login device during the order transaction monitoring period, thereby comprehensively analyzing and obtaining the order management degree of each user; The historical order information of each user specifically includes the average credit score of each user's historical orders, the average daily transaction frequency of each user's historical orders, the number of order cancellations of each user within the historical behavior period, and the total number of orders; The monitoring information of the online trading platform specifically includes the average number of order transactions per person, the average number of user logins per day, the average daily memory usage rate and the average daily network traffic.

2. According to claim 1, an order anti-fraud management system is characterized by: The specific expression of the comprehensive order management index of each user is as follows: ； In the formula, is the comprehensive order management index of the t-th user, is the historical order management influence of the t-th user, The weight factor corresponding to the historical order management influence preset in the order management library, To monitor the impact of online trading platforms, is the weight factor corresponding to the monitoring influence preset by the order management library, t is the number of each user, , y is the total number of users.

3. According to claim 1, an order anti-fraud management system is characterized by: The risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt. The specific determination process is as follows: Compare the order management degree of each user with the order anti-fraud management threshold of each user. If the order management degree of a user is higher than the order anti-fraud management threshold of the user, the risk fraud alarm cloud platform does not need to issue an alarm for the user's order; If a user's order management degree is equal to or lower than the user's order anti-fraud management threshold, the user's order management degree and the order anti-fraud management threshold are processed by difference to obtain the user's order management deviation value, and the order risk level corresponding to each order management deviation value interval preset by the risk fraud alarm cloud platform is compared to match the user's order risk level. The risk fraud alarm cloud platform then sends an order risk level warning to the user, thereby completing the user's order management warning prompt; By sending the above-mentioned warning prompts of order risk levels, the order risk level of each user can be determined according to the risk fraud warning cloud platform, and warning prompts can be issued.

4. A method for applying the order anti-fraud management system according to any one of claims 1 to 3, characterized in that: include: S1. The central processor responds to the historical order information of each user sent by the edge server, and the central processor collects monitoring information of the online trading platform; S2. The central processor comprehensively evaluates the historical order information of each user and the monitoring information of the online trading platform, and matches the order anti-fraud management threshold of each user; S3. Monitor the order trading behavior of each user on the online trading platform and analyze the order management degree of each user; S4. The central processor sends the order management level of each user to the risk fraud alarm cloud platform. The risk fraud alarm cloud platform combines the order anti-fraud management threshold of each user to determine the order risk level of each user and issue an alarm prompt.

Images