E-commerce platform monitoring method based on big data

Abstract

The invention relates to the technical field of intelligent e-commerce, in particular to an e-commerce platform monitoring method based on big data, and the method comprises the steps: carrying out the statistics of regional order returning rates of various types of commodities in different regions; judging a user category, and judging whether behavior monitoring is started or not based on the trading volume of the user; determining the activeness of the user; counting the user order returning rate of the user in a preset time, and comparing the user order returning rate with the regional order returning rate to judge whether the order returning behavior of the user belongs to monitoring target order returning; performing sealing control processing on the users which are judged to be the monitoring target order returning and are low in activity, and performing warning processing on the users which are judged to be the monitoring target order returning and are high in activity; by adopting the method, the regional purchase attribute of the commodity is effectively displayed, the activeness of the user is effectively judged, the accuracy of judging the purchase behavior of the user is effectively improved, the loss of e-commerce caused by order returning of the monitoring target is effectively reduced, and the accuracy and fairness of e-commerce platform monitoring are further improved.

Description

Technical Field

[0001] The present invention relates to the field of smart e-commerce technology, and in particular to an e-commerce platform monitoring method based on big data. Background Art

[0002] E-commerce platforms refer to online markets where goods and services are traded over the Internet. These platforms usually provide a place for buyers and sellers to conduct transactions, and support functions such as product display, shopping carts, payment processing, and order management. Users who trade on e-commerce platforms can place orders online without having to trade face to face. With the popularity of smartphones, more and more consumers are shopping through mobile devices. In combination with social networks, social media platforms are used to promote and sell products. At the same time, based on big data analysis, personalized shopping experiences are provided. E-commerce platforms have developed rapidly around the world, changing the operating model of the traditional retail industry and providing more convenience and choices. However, in actual application, due to competition among peers or malicious consumption, sellers suffer huge losses, so it is necessary to monitor the purchasing behavior of e-commerce platforms.

[0003] The deep fake technology brought by artificial intelligence poses a great risk to authentication and other authentication related to personal information, property information, and data access. The application of authentication and authorization fields such as face recognition, voice control, and fingerprints began before artificial intelligence, and many applications have not yet configured technical preventive measures to deal with artificial intelligence deep fakes, resulting in security risks in authentication, which in turn leads to insecure access to personal data.

[0004] Chinese Patent Publication No.: CN118608229A. A method and system for monitoring and managing e-commerce data and order are disclosed. The invention relates to the field of data management technology, specifically to a method and system for monitoring and managing e-commerce data and order, including: obtaining first data, second data and third data of an e-commerce platform; establishing a user purchase trend of a first commodity according to the first data, and the purchase trend can predict the user's purchase tendency of the commodity; establishing a predicted transaction volume of the first commodity according to the second data, and the predicted transaction volume of the first commodity is conducive to timely replenishment of the e-commerce platform, avoiding out-of-stock problems, and effectively improving user satisfaction; determining an order evaluation level according to the third data, if the order evaluation level is lower than a preset threshold, the e-commerce platform intercepts the order, and the order evaluation level can help the e-commerce platform to timely discover and handle orders with problems, effectively improve user experience, enhance user satisfaction, and thus improve the reputation and competitiveness of the e-commerce platform.

[0005] Chinese Patent Publication Number: CN118379082A. A smart e-commerce system based on 5G and big data is disclosed. The invention discloses a system including a data acquisition module, a recommendation engine module, an augmented reality experience module, a supply chain optimization module and a multimodal interaction module. The data acquisition module collects data from multiple data sources and transmits it to other modules of the system through 5G. The recommendation engine uses machine learning to analyze user behavior and provide personalized product recommendations. The augmented reality module uses three-dimensional technology to display the use effect of the product. The supply chain module analyzes market demand and inventory and optimizes supply chain strategies. The multimodal interaction module supports voice, image search and touch screen operation. By integrating 5G and big data technologies, the invention can provide a faster, more personalized and more interactive e-commerce shopping experience, while optimizing back-end supply chain management, thereby comprehensively improving the competitiveness and user satisfaction of the e-commerce platform.

[0006] It can be seen that the above technical solution has the following problems: analyzing the user's purchasing behavior according to the user's purchasing trend and adjusting the supply chain cannot promptly respond to the losses caused by a large number of returned orders from monitored targets; the method of simply analyzing the problem orders through statistics on the commodity transaction volume cannot comprehensively analyze the causes of the problem orders. Summary of the invention

[0007] To this end, the present invention provides an e-commerce platform monitoring method based on big data, which is used to overcome the problem that the prior art analyzes users' purchasing behavior according to their purchasing trends and adjusts the supply chain, but is unable to promptly respond to the losses caused by a large number of returned orders of monitored targets, and the method of simply analyzing problem orders through statistical analysis of commodity transaction volume cannot comprehensively analyze the causes of problem orders.

[0008] To achieve the above object, the present invention provides an e-commerce platform monitoring method based on big data, comprising:

[0009] Count the number of returned orders for various types of goods in different regions within a preset time, and calculate the regional return rate;

[0010] According to the user's historical browsing situation, determine whether the user is a regular user or a target user, and determine whether to enable behavior monitoring based on the transaction volume of the target user;

[0011] Determine the activity of the target user according to the registration time and browsing time of the target user;

[0012] Counting the transaction volume and order return volume of the target user within the preset time, calculating the user order return rate, comparing the user order return rate with the regional order return rate, determining whether the order return behavior of the target user belongs to the monitored target order return according to the comparison result, and changing the target user who is not determined to be the monitored target order return to the regular user;

[0013] The target user who is determined to have cancelled an order and has low activity is blocked, and the target user who is determined to have cancelled an order and has high activity is warned.

[0014] Furthermore, based on the user's historical browsing situation, the user's transaction time difference is compared with a preset transaction time difference, and the user is determined to be a regular user or a target user based on the comparison result, wherein:

[0015] If the transaction time difference is less than the preset transaction time difference, it is determined that the user belongs to the target user;

[0016] If the transaction time difference is not less than the preset transaction time difference, it is determined that the user is a regular user;

[0017] Among them, the historical browsing situation includes the region where the user account is logged in, the product name retrieved by the user and the transaction time difference; the transaction time difference is the time from the user clicking on the product information to the completion of the product transaction; the preset transaction time difference is positively correlated with the transaction volume of the product in the region.

[0018] Furthermore, the steps of counting the number of returned orders for various types of goods in different regions within a preset time and calculating the regional returned order rate include:

[0019] Divide the overall geographical scope of commodity sales into regions based on transaction volume;

[0020] Counting the transaction volume and order return volume of the products within the preset time in different regions;

[0021] Calculate the regional order return rate corresponding to each region according to the transaction volume and the order return volume;

[0022] Among them, the preset time is positively correlated with the sales time of the product, the transaction volume is the number of products purchased by users; and the return order volume is the number of products returned by users.

[0023] Further, according to the comparison result between the target user's transaction volume and the preset transaction volume, it is determined whether to start behavior monitoring, wherein:

[0024] If the transaction volume of the target user is greater than or equal to the preset transaction volume, determining to start the behavior monitoring;

[0025] Among them, the preset transaction volume is positively correlated with the transaction volume of the product in the region; the behavior monitoring includes judging the activity of the target user and counting the transaction volume and return order volume of the target user within the preset time.

[0026] Furthermore, the step of determining the activity of the target user according to the registration time and browsing time of the target user includes:

[0027] Comparing the browsing time and the registration time of the target user to obtain a browsing time ratio;

[0028] The browsing time ratio is compared with a preset time ratio, and the activity level of the target user is determined according to the comparison result.

[0029] Furthermore, the activity of the target user is determined according to the comparison result of the browsing time ratio and the preset time ratio, wherein:

[0030] If the browsing time ratio is less than the preset time ratio, determining that the target user is a low-activity user;

[0031] If the browsing time ratio is not less than the preset time ratio, determining that the target user is a high-activity user;

[0032] The preset time ratio is negatively correlated with the user registration time.

[0033] Furthermore, the transaction volume and order return volume of the target user within the preset time are counted, and the order return volume is compared with the transaction volume to obtain the user order return rate.

[0034] Further, the user return rate is compared with the regional return rate, and it is determined whether the return behavior of the target user belongs to the monitored target return according to the comparison result, wherein:

[0035] If the user order return rate is greater than or equal to the regional order return rate, it is determined that the order return behavior of the target user belongs to the monitored target order return;

[0036] If the user return rate is lower than the regional return rate, the target user is changed to the regular user.

[0037] Furthermore, the target user who is determined to be the monitored target with a refund and low activity is blocked, and the target user who is determined to be the monitored target with a refund and high activity is warned, wherein:

[0038] If the user order return rate of the target user who is determined to be a monitored target order return and has high activity within the preset time is lower than the regional order return rate, the target user is changed to the regular user;

[0039] The blocking process is to block the target user's account.

[0040] Furthermore, the overall geographical scope of commodity sales is divided into regions according to the transaction volume, among which:

[0041] When the overall geographical scope of the sales of the commodities changes, the geographical division shall be re-conducted according to the transaction volume.

[0042] Compared with the prior art, the beneficial effect of the present invention lies in that the order return rate is calculated based on the statistical order return volume of each commodity in different regions, which effectively demonstrates the regional purchasing attributes of the commodity, and effectively improves the accuracy and fairness of e-commerce platform monitoring while accurately analyzing the demand for the commodity.

[0043] Furthermore, by analyzing the user's historical browsing behavior, we can determine whether the user has a tendency to make malicious consumption, and enable behavior monitoring for users with malicious consumption tendencies. This effectively improves the accuracy of judging whether the user has performed the monitored target order return behavior, while further improving the accuracy and fairness of e-commerce platform monitoring.

[0044] Furthermore, the user's activity is determined based on the user's registration time and browsing time, and the user's behavior is analyzed more comprehensively. The judgment of user activity effectively improves the accuracy of judging user purchasing behavior, while further improving the accuracy and fairness of e-commerce platform monitoring.

[0045] Furthermore, the user's return order rate is compared with the return order rate of the same product in the local area to effectively determine whether the user's return order behavior is within the normal range. At the same time, combined with the user's activity level, it is analyzed whether the user belongs to an account used to monitor target return orders by competitors. This effectively reduces the losses to e-commerce companies caused by monitoring target return orders, while further improving the accuracy and fairness of e-commerce platform monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of the e-commerce platform monitoring method based on big data of the present invention;

[0047] Figure 2 A schematic diagram of determining a user category according to an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of determining user activity according to an embodiment of the present invention;

[0049] Figure 4 A schematic diagram of determining a target return order according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0052] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0053] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] See also Figure 1 As shown, it is a flow chart of the e-commerce platform monitoring method based on big data of the present invention, a method for monitoring an e-commerce platform based on big data, comprising:

[0055] Step S1, counting the number of returned orders for various types of goods in different regions within a preset time, and calculating the regional returned order rate;

[0056] Step S2: judging whether the user is a regular user or a target user based on the user's historical browsing behavior, and judging whether to enable behavior monitoring based on the target user's transaction volume;

[0057] Step S3, determining the activity of the target user according to the registration time and browsing time of the target user;

[0058] Step S4, counting the target user's transaction volume and return order volume within a preset time, calculating the user's return order rate, comparing the user's return order rate with the regional return order rate, and determining whether the return order behavior of the target user belongs to the monitored target return order according to the comparison result, and changing the target user who is not determined to be the monitored target return order to a regular user;

[0059] Step S5, blocking the target user who is determined to be a monitored target with a refund and low activity, and warning the target user who is determined to be a monitored target with a refund and high activity.

[0060] See also Figure 2As shown, it is a schematic diagram of determining the user category in an embodiment of the present invention. In step S2, based on the user's historical browsing situation, the user's transaction time difference is compared with the preset transaction time difference, and the user is determined to be a regular user or a target user based on the comparison result, wherein:

[0061] If the transaction time difference is less than the preset transaction time difference, the user is determined to be a target user;

[0062] If the transaction time difference is not less than the preset transaction time difference, the user is determined to be a regular user;

[0063] Embodiment 1: In this embodiment, the preset transaction time difference is 10 seconds. If the transaction time difference is 8 seconds, which is less than the preset transaction time difference of 10 seconds, then the user is determined to be a target user;

[0064] If the transaction time difference is 15 seconds, which is greater than the preset transaction time difference of 10 seconds, the user is determined to be a regular user.

[0065] Among them, historical browsing information includes the region where the user account is logged in, the product name searched by the user and the transaction time difference; the transaction time difference is the time from when the user clicks on the product information to when the product transaction is completed; the preset transaction time difference is positively correlated with the transaction volume of the product in the region.

[0066] It is understandable that the greater the transaction volume of a product in a region, the longer the users in the region browse the product.

[0067] Optionally, the transaction volume of the product in the region is 5 orders, and the preset transaction time difference is 10 seconds;

[0068] The transaction volume of the product in this region is 10 orders, and the preset transaction time difference is 13 seconds;

[0069] The transaction volume of the product in this area is 20 orders, and the preset transaction time difference is 16 seconds.

[0070] Specifically, in step S1, the steps of counting the number of returned orders for various types of goods in different regions within a preset time and calculating the regional returned order rate include:

[0071] Step S11, dividing the overall geographical scope of commodity sales into regions according to the transaction volume;

[0072] Step S12, counting the transaction volume and order return volume of the goods within a preset time in different regions;

[0073] Step S13, calculating the regional return order rate corresponding to each region according to the transaction volume and the return order volume;

[0074] Among them, the preset time is positively correlated with the sales time of the product, the transaction volume is the number of products purchased by users; and the return volume is the number of products returned by users.

[0075] It is understandable that the longer the product starts to be sold, the longer the preset time is, the better it can reflect the long-term stable transaction volume and order return data.

[0076] In one embodiment, the preset time is 1 day, the transaction volume of the product within 1 day is 20 orders, and the number of returned orders is 5 orders, then the regional returned order rate is 5 / 20=25%.

[0077] Specifically, the order return rate is calculated based on the statistical return volume of each product in different regions, which effectively demonstrates the regional purchasing attributes of the products. While accurately analyzing the demand for the products, it effectively improves the accuracy and fairness of e-commerce platform monitoring.

[0078] Specifically, by analyzing the user's historical browsing behavior, we can determine whether the user has a tendency to make malicious consumption, and enable behavior monitoring for users with malicious consumption tendencies. This effectively improves the accuracy of judging whether the user has performed the monitored target order return behavior, while further improving the accuracy and fairness of e-commerce platform monitoring.

[0079] Specifically, in step S2, based on the comparison result between the target user's transaction volume and the preset transaction volume, it is determined whether to enable behavior monitoring, wherein:

[0080] If the target user's transaction volume is greater than or equal to the preset transaction volume, it is determined to start behavior monitoring;

[0081] Embodiment 2: Based on Embodiment 1, this embodiment is different from the embodiment 1 in that the preset transaction volume is 10 orders. If the transaction volume of the target user is 50 orders, which is greater than the preset transaction volume of 10 orders, it is determined to start behavior monitoring;

[0082] Among them, the preset transaction volume is positively correlated with the transaction volume of the product in the region; behavior monitoring includes judging the activity of the target user and counting the transaction volume and return order volume of the target user within the preset time.

[0083] It is understandable that the greater the transaction volume of the product in the region, the more orders will be placed by users. When the orders exceed the normal range, behavior monitoring will be enabled.

[0084] Optionally, the transaction volume of the product in the region is 5 orders, and the preset transaction volume is 10 orders;

[0085] The transaction volume of the product in this area is 50 orders, and the default transaction volume is 60 orders;

[0086] The transaction volume of the product in this area is 100 orders, and the preset transaction volume is 120 orders.

[0087] Specifically, in step S3, the step of determining the activity of the target user according to the registration time and browsing time of the target user includes:

[0088] Step S31, comparing the browsing time and registration time of the target user to obtain a browsing time ratio;

[0089] Step S32, comparing the browsing time ratio with a preset time ratio, and determining the activity of the target user according to the comparison result.

[0090] Specifically, the user's activity is determined based on the user's registration time and browsing time, and the user's behavior is analyzed more comprehensively. The judgment of user activity effectively improves the accuracy of judging user purchasing behavior, while further improving the accuracy and fairness of e-commerce platform monitoring.

[0091] See also Figure 3 As shown, it is a schematic diagram of determining user activity in an embodiment of the present invention. In step S32, the activity of the target user is determined according to the comparison result of the browsing time ratio and the preset time ratio, wherein:

[0092] If the browsing time ratio is less than the preset time ratio, the target user is determined to be a low-activity user;

[0093] If the browsing time ratio is not less than the preset time ratio, the target user is determined to be a highly active user;

[0094] Embodiment 3: Based on Embodiment 2, this embodiment is different from it in that the preset time ratio is 30%. If the browsing time ratio is 20% which is less than the preset time ratio 30%, the target user is determined to be a low-activity user.

[0095] If the browsing time ratio is 50% and is greater than the preset time ratio of 30%, the target user is determined to be a highly active user.

[0096] Among them, the preset time ratio is negatively correlated with the user registration time.

[0097] It is understandable that users start browsing products after registering an account. Their registration time is longer than their browsing time. Their activity level can be inferred by the ratio of their browsing time to their registration time. As the registration time increases, the corresponding browsing time will decrease.

[0098] Optionally, the user registration period is 5 days and the preset time ratio is 30%;

[0099] The user registration period is 20 days, and the preset time ratio is 20%;

[0100] The user registration period is 50 days and the preset time ratio is 10%.

[0101] Specifically, in step S4, the transaction volume and return volume of the target user within a preset time are counted, and the return volume is compared with the transaction volume to obtain the user return rate.

[0102] In one embodiment, the preset time is 1 day, the target user's transaction volume within 1 day is 50 orders, and the return order volume is 45 orders, then the user return order rate is 45 / 50=90%.

[0103] See also Figure 4 As shown, it is a schematic diagram of determining the monitoring target return order according to an embodiment of the present invention. In step S4, the user return order rate is compared with the regional return order rate, and it is determined whether the return order behavior of the target user belongs to the monitoring target return order according to the comparison result, wherein:

[0104] If the user return rate is greater than or equal to the regional return rate, the return behavior of the target user is determined to be a monitored target return;

[0105] If the user return rate is lower than the regional return rate, the target user will be changed to a regular user.

[0106] Embodiment 4: Based on Embodiment 3, this embodiment is different from it in that if the user return rate is 80% and is greater than the regional return rate of 30%, it is determined that the return behavior of the target user belongs to the monitoring target return;

[0107] If the user return rate is 10% and is less than the regional return rate of 30%, the target user will be changed to a regular user.

[0108] Specifically, the user's return order rate is compared with the return order rate of the same product in the local domain to effectively determine whether the user's return order behavior is within the normal range. At the same time, combined with the user's activity level, it is analyzed whether the user belongs to an account used to monitor target return orders by competitors. This effectively reduces the losses to e-commerce companies caused by monitoring target return orders, while further improving the accuracy and fairness of e-commerce platform monitoring.

[0109] Specifically, in step S5, the target user determined to be a monitored target with a cancelled order and low activity is blocked, and the target user determined to be a monitored target with a cancelled order and high activity is warned, wherein:

[0110] If the target user who is determined to be the target of the monitoring return order and has high activity has a return order rate lower than the regional return order rate within the preset time, the target user will be changed to a regular user;

[0111] It is understandable that target users who are determined to be subject to order return monitoring and have high activity will be converted into regular users if they change their bad purchasing habits in a timely manner after receiving warnings and reduce their order return rate to below the regional order return rate.

[0112] The blocking process is to ban the target user's account.

[0113] Specifically, in step S11, the overall geographical scope of commodity sales is divided into regions according to the transaction volume, where:

[0114] When the overall geographical scope of commodity sales changes, the regions are redivided according to the transaction volume.

[0115] It is understandable that the sales areas of goods will change over time, with new and reduced sales areas. The regions will be redivided based on changes in each region and transaction volume.

[0116] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0117] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for monitoring an e-commerce platform based on big data, characterized in that: include: Count the number of returned orders for various types of goods in different regions within a preset time, and calculate the regional return rate; According to the user's historical browsing situation, determine whether the user is a regular user or a target user, and determine whether to enable behavior monitoring based on the transaction volume of the target user; Determine the activity of the target user according to the registration time and browsing time of the target user; Counting the transaction volume and order return volume of the target user within the preset time, calculating the user order return rate, comparing the user order return rate with the regional order return rate, determining whether the order return behavior of the target user belongs to the monitored target order return according to the comparison result, and changing the target user who is not determined to be the monitored target order return to the regular user; The target user who is determined to have cancelled an order and has low activity is blocked, and the target user who is determined to have cancelled an order and has high activity is warned.

2. The e-commerce platform monitoring method based on big data according to claim 1 is characterized in that: According to the user's historical browsing situation, the user's transaction time difference is compared with the preset transaction time difference, and the user is determined to be the regular user or the target user according to the comparison result, wherein: If the transaction time difference is less than the preset transaction time difference, it is determined that the user belongs to the target user; If the transaction time difference is not less than the preset transaction time difference, it is determined that the user is a regular user; Among them, the historical browsing situation includes the region where the user account is logged in, the product name retrieved by the user and the transaction time difference; the transaction time difference is the time from the user clicking on the product information to the completion of the product transaction; the preset transaction time difference is positively correlated with the transaction volume of the product in the region.

3. The e-commerce platform monitoring method based on big data according to claim 2 is characterized in that: The steps of counting the number of returned orders for various types of goods in different regions within a preset time and calculating the regional return rate include: Divide the overall geographical scope of commodity sales into regions based on transaction volume; Counting the transaction volume and order return volume of the products within the preset time in different regions; Calculate the regional order return rate corresponding to each region according to the transaction volume and the order return volume; Among them, the preset time is positively correlated with the sales time of the product, the transaction volume is the number of products purchased by users; and the return order volume is the number of products returned by users.

4. The e-commerce platform monitoring method based on big data according to claim 3 is characterized in that: According to the comparison result between the target user's transaction volume and the preset transaction volume, it is determined whether to start behavior monitoring, wherein: If the transaction volume of the target user is greater than or equal to the preset transaction volume, determining to start the behavior monitoring; Among them, the preset transaction volume is positively correlated with the transaction volume of the product in the region; the behavior monitoring includes judging the activity of the target user and counting the transaction volume and return order volume of the target user within the preset time.

5. The e-commerce platform monitoring method based on big data according to claim 4 is characterized in that: The step of determining the activity of the target user according to the registration time and browsing time of the target user comprises: Comparing the browsing time and the registration time of the target user to obtain a browsing time ratio; The browsing time ratio is compared with a preset time ratio, and the activity level of the target user is determined according to the comparison result.

6. The e-commerce platform monitoring method based on big data according to claim 5 is characterized in that: The activity of the target user is determined according to the comparison result between the browsing time ratio and the preset time ratio, wherein: If the browsing time ratio is less than the preset time ratio, determining that the target user is a low-activity user; If the browsing time ratio is not less than the preset time ratio, determining that the target user is a high-activity user; The preset time ratio is negatively correlated with the user registration time.

7. The e-commerce platform monitoring method based on big data according to claim 6 is characterized in that: The transaction volume and order return volume of the target user within the preset time are counted, and the order return volume is compared with the transaction volume to obtain the user order return rate.

8. The e-commerce platform monitoring method based on big data according to claim 7 is characterized in that: The user return rate is compared with the regional return rate, and whether the return behavior of the target user belongs to the monitored target return is determined according to the comparison result, wherein: If the user order return rate is greater than or equal to the regional order return rate, it is determined that the order return behavior of the target user belongs to the monitored target order return; If the user return rate is lower than the regional return rate, the target user is changed to the regular user.

9. The e-commerce platform monitoring method based on big data according to claim 8 is characterized in that: The target user who is determined to be the target of the monitoring target order cancellation and has low activity is blocked, and the target user who is determined to be the target of the monitoring target order cancellation and has high activity is warned, wherein: If the user order return rate of the target user who is determined to be a monitored target order return and has high activity within the preset time is lower than the regional order return rate, the target user is changed to the regular user; The blocking process is to block the target user's account.

10. The e-commerce platform monitoring method based on big data according to claim 9, characterized in that: The overall geographical scope of commodity sales is divided into regions according to the transaction volume, among which: When the overall geographical scope of the sales of the commodities changes, the geographical division shall be re-conducted according to the transaction volume.

Images