A group purchase recommendation method and device based on user preference
By clustering the purchasing preferences of potential users of group buying and making real-time decisions on group buying requests, the problem of rigid transaction conditions in the existing group buying recommendation solutions is solved, the accuracy and flexibility of group buying recommendations is achieved, and user experience and commercial content consumption is improved.
Patent Information
- Application Number
- CN202411173930.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-26
AI Technical Summary
The transaction conditions in the existing group buying recommendation plan are too rigid, resulting in low transaction success rate, fluctuations in commodity sales affect inventory management, resulting in backlog of warehouses or insufficient replenishment.
By clustering the purchase preferences of potential users of group buying into multiple preference vectors, the access probability value and purchase conversion probability value are obtained in real time, and the group buying request is transmitted based on the effective group buying scale decision, a separate decision on the group buying scale of each preference vector is realized. Improve the accuracy and flexibility of group buying recommendations.
It realizes fast and accurate group buying recommendations, improves user experience and commercial content consumption, reduces the overhead caused by frequent group buying, and improves the group buying performance of the target merchant warehouse and the overall performance of the processor system.
Smart Images

Figure CN118691386B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of big data technology, and in particular to a group purchase recommendation method and device based on user preferences. Background Art
[0002] The rapid development of e-commerce platforms has helped merchants increase their sales of goods. The increase in sales of goods has also put forward higher requirements for the management of potential group purchases of goods.
[0003] In the current online group buying scheme, the seller sets the transaction conditions, that is, the seller determines a fixed batch and the price of the product after reaching the batch; after joining the group buying, the buyer pays a deposit in advance. When the transaction deadline arrives, if the transaction conditions set by the seller are met, the transaction can be completed. If not, the transaction will not be established. In this existing scheme, if the transaction conditions are only one transaction unit away from the deadline, the transaction will not be established. Due to the influence of the off-season and peak season of commodity sales, user customer groups and holidays, commodity sales will fluctuate. If there are too few group buying orders for a commodity, it will lead to a backlog in the warehouse, affecting the timely bulk sales of the commodity and increasing the storage cost; if there are too many group buying orders for a commodity, it will lead to insufficient replenishment of the commodity, making it difficult to meet the group buying demand, and the potential group buying sales management pressure will increase.
[0004] The reason why sellers fix the batch size is to ensure that their own interests are not harmed, but this also makes the transaction conditions too rigid and lacks flexibility, resulting in a low transaction success rate. Summary of the invention
[0005] To achieve the above objectives, this application provides the following technical solutions:
[0006] According to a first aspect of the present invention, the present invention claims protection for a group purchase recommendation method based on user preferences, the method comprising:
[0007] Cluster the purchase preferences of potential group buying users into multiple preference vectors;
[0008] Obtain the access probability value and purchase conversion probability value of each preference vector within the recommended time in real time;
[0009] In a scenario where the target merchant warehouse corresponding to the potential group purchase user meets the purchase requirements, determining the effective group purchase scale of the preference vector based on the access probability value and the purchase conversion probability value;
[0010] Within a preset time in the future, the transmission of the group purchase request corresponding to the preference vector is determined based on the effective group purchase scale.
[0011] Furthermore, within the future preset time, before the transmission of the group purchase request corresponding to the preference vector is determined based on the effective group purchase scale, the method further includes:
[0012] Record the access probability value, purchase conversion probability value and effective group purchase scale of the preference vector in the preference vector continuous periodic table;
[0013] The transmission of the group purchase request corresponding to the preference vector is determined based on the effective group purchase scale within a preset time in the future, including:
[0014] In a scenario where a group purchase request transmitted by the target merchant warehouse is obtained, the preference vector continuous periodic table is retrieved based on the group purchase commodity category carried in the group purchase request;
[0015] If a first preference vector associated with the group-buying commodity category is detected in the preference vector persistence periodic table, obtaining an effective group-buying scale and a purchase conversion probability value of the first preference vector;
[0016] In the scenario where the effective group purchase scale is greater than 0 and the purchase conversion probability value is not less than a first critical value, the group purchase request is transmitted to the group purchase linked list, and the value of the effective group purchase scale of the first preference vector in the preference vector continuous periodic table is reduced by m, where m is greater than 0.
[0017] Furthermore, the method further comprises:
[0018] In a scenario that meets the first requirement, interrupting the group purchase request;
[0019] The first requirement includes at least one of the following:
[0020] The first preference vector associated with the group-buying commodity category is not detected in the preference vector continuous periodic table;
[0021] The effective group purchase scale of the first preference vector is equal to 0;
[0022] The purchase conversion probability value of the first preference vector is less than the first critical value.
[0023] Furthermore, clustering the purchase preferences of group purchase potential users into multiple preference vectors includes:
[0024] The product category ID of the current inventory product category is used as a label, and the current inventory product category of the group purchase potential users is grouped to output a plurality of preference vectors; the labels of the current inventory product category contained in the same preference vector are consistent;
[0025] The real-time acquisition of the access probability value and purchase conversion probability value of each preference vector within the recommendation time includes:
[0026] During the group purchase period, obtain the preferred product, the number of orders for the first group purchase, and the number of unreturned products for the first group purchase corresponding to each preference vector;
[0027] determining an access probability value of the preference vector based on the trending product;
[0028] Based on the first group purchase order number and the first group purchase non-return number, a purchase conversion probability value in the preference vector is calculated.
[0029] Furthermore, the method further comprises:
[0030] Obtaining the number of purchase requests from the target merchant warehouse in the purchase requests transmitted by the listener to the manufacturer within the recommended time; the listener is a real-time listener closest to the manufacturer in the processor system;
[0031] Obtain the number of second group purchase orders and the number of second group purchase non-return orders of the target merchant warehouse within the recommended time;
[0032] Determining a second group purchase prediction value of the target merchant warehouse based on the second group purchase order number and the second group purchase non-return number;
[0033] Calculating the group purchase throughput of the target merchant warehouse based on the request quantity and the second group purchase prediction value; the group purchase throughput is used to indicate the additional manufacturer warehouse throughput caused by the frequent group purchases of the target merchant warehouse;
[0034] In a scenario where the group purchase throughput is greater than the second critical value, it is determined that the merchant server meets the purchase requirements.
[0035] According to a second aspect of the present invention, the present invention claims protection for a group purchase recommendation device based on user preferences, the device comprising:
[0036] A segmentation unit, used to cluster the purchase preferences of potential group purchase users into multiple preference vectors;
[0037] A first acquisition unit is used to acquire in real time the access probability value and purchase conversion probability value of each preference vector within the recommendation time;
[0038] A first determining unit is used to determine the effective group purchase scale of the preference vector based on the access probability value and the purchase conversion probability value in a scenario where the target merchant warehouse corresponding to the group purchase potential user meets the purchase requirements;
[0039] A decision-making unit is used to decide the transmission of the group purchase request corresponding to the preference vector based on the effective group purchase scale within a preset time in the future.
[0040] Furthermore, the device also includes:
[0041] A recording unit, used to record the access probability value, purchase conversion probability value and effective group purchase scale of the preference vector in a preference vector continuous period table;
[0042] The decision-making unit comprises:
[0043] A retrieval subunit, configured to retrieve the preference vector continuous periodic table based on the group purchase commodity category carried in the group purchase request, in a scenario where the group purchase request transmitted by the target merchant warehouse is obtained;
[0044] an obtaining subunit, configured to obtain an effective group purchase scale and a purchase conversion probability value of the first preference vector if a first preference vector associated with the group purchase commodity category is detected in the preference vector persistence period table;
[0045] A transmission subunit is used to transmit the group purchase request to the group purchase linked list and reduce the value of the effective group purchase scale of the first preference vector in the preference vector continuous periodic table by m, where m is greater than 0, in a scenario where the effective group purchase scale is greater than 0 and the purchase conversion probability value is not less than a first critical value.
[0046] Furthermore, the decision unit also includes:
[0047] An interruption subunit, configured to interrupt the group purchase request in a scenario that meets the first requirement;
[0048] The first requirement includes at least one of the following:
[0049] The first preference vector associated with the group-buying commodity category is not detected in the preference vector continuous periodic table;
[0050] The effective group purchase scale of the first preference vector is equal to 0;
[0051] The purchase conversion probability value of the first preference vector is less than the first critical value.
[0052] Furthermore, the segmentation unit comprises:
[0053] The segmentation subunit is used to group the current inventory commodity categories of the group purchase potential users by using the commodity category ID of the current inventory commodity category as a label, and output a plurality of preference vectors; the labels of the current inventory commodity categories contained in the same preference vector are consistent;
[0054] The first acquisition unit includes:
[0055] An acquisition subunit is used to obtain the preferred product, the number of first group purchase orders, and the number of unreturned products in the first group purchase corresponding to each preference vector within the group purchase period;
[0056] an access probability value determination subunit, configured to determine an access probability value of the preference vector based on the trend product;
[0057] The group purchase prediction value calculation subunit is used to calculate the purchase conversion probability value in the preference vector based on the first group purchase order number and the first group purchase non-return number.
[0058] Furthermore, the device also includes:
[0059] An acquisition unit, configured to acquire the number of requests from the target merchant warehouse in the purchase requests transmitted by the listener to the manufacturer within the recommended time; the listener is a real-time listener closest to the manufacturer in the processor system;
[0060] A second acquisition unit is used to obtain the number of second group purchase orders and the number of second group purchase non-return orders of the target merchant warehouse within the recommended time;
[0061] A second determining unit, configured to determine a second group purchase prediction value of the target merchant warehouse based on the second group purchase order number and the second group purchase non-return number;
[0062] A throughput calculation unit, configured to calculate the group purchase throughput of the target merchant warehouse based on the request quantity and the second group purchase prediction value; the group purchase throughput is used to indicate the additional manufacturer warehouse throughput caused by the frequent group purchases of the target merchant warehouse;
[0063] The purchase determination unit is used to determine that the merchant server meets the purchase requirements when the group purchase throughput is greater than the second critical value.
[0064] The present application relates to the field of big data technology, and in particular to a group purchase recommendation method and device based on user preferences. In order to solve the problem of low accuracy of group purchase recommendation in the prior art, the present application clusters the purchase preferences of potential group purchase users into multiple preference vectors; obtains the access probability value and purchase conversion probability value of each preference vector in real time within the recommendation time; determines the effective group purchase scale of the preference vector based on the access probability value and the purchase conversion probability value in the scenario where the target merchant warehouse corresponding to the potential group purchase user meets the purchase requirements; and determines the transmission of the group purchase request corresponding to the preference vector based on the effective group purchase scale within a preset time in the future. The present invention can realize fast and accurate group purchase recommendations, and can be applied in data prediction in the commercial field to improve user experience and commercial content consumption. BRIEF DESCRIPTION OF THE DRAWINGS
[0065] Figure 1 A workflow diagram of a group purchase recommendation method based on user preferences as claimed in an embodiment of the present application;
[0066] Figure 2 A second working flow chart of a group purchase recommendation method based on user preferences as claimed in an embodiment of the present application;
[0067] Figure 3 This is a structural module diagram of a group purchase recommendation device based on user preferences as claimed in an embodiment of the present application. DETAILED DESCRIPTION
[0068] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0069] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is multiple, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative position relationship, motion scene, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.
[0070] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to a consistent embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0071] Reference Figure 1 , shows a flowchart of a method for recommending group purchases based on user preferences according to an embodiment of the present invention, wherein the method may specifically include the following steps:
[0072] Step 101: clustering the purchase preferences of potential group purchase users into multiple preference vectors;
[0073] Step 102: Obtain in real time the access probability value and purchase conversion probability value of each preference vector within the recommended time;
[0074] Step 103: Under the scenario that the target merchant warehouse corresponding to the group purchase potential user meets the purchase requirements, determine the effective group purchase scale of the preference vector based on the access probability value and the purchase conversion probability value;
[0075] Step 104: within a preset time in the future, decide on the transmission of the group purchase request corresponding to the preference vector based on the effective group purchase scale.
[0076] The group purchase recommendation method based on user preferences provided in the embodiment of the present invention can execute purchase decisions on the hardware merchant server (that is, the target merchant warehouse in the present invention). Exemplarily, the group purchase recommendation method based on user preferences provided in the embodiment of the present invention can be applied to a group purchase recommendation device based on user preferences, which is deployed on the same layer of real-time listeners as the target merchant warehouse, and can obtain listener failure events and listener non-return events that occur in the real-time listeners of this layer, and receive group purchase requests generated by the target merchant warehouse, and decide whether to pass the group purchase request to subsequent purchase components, such as group purchase linked lists. The target merchant warehouse is used to generate group purchase requests based on the purchase information of potential group purchase users. The group purchase recommendation device based on user preferences can prevent access to the next layer of real-time listeners triggered by any group purchase request based on the purchase strategy, thereby achieving the purpose of purchasing group purchases.
[0077] A processor system provided by an embodiment of the present invention includes a processor core, a real-time listener, a manufacturer, a target merchant warehouse, a fault status processing register, a group purchase linked list, and a group purchase recommendation device based on user preferences. Among them, the real-time listener includes a multi-level real-time listener, which includes potential group purchase users. The potential group purchase user is any level of real-time listeners in the multi-level real-time listener. When the potential group purchase user is the real-time listener closest to the processor end, the potential group purchase user is connected to the processor core and the next level of real-time listener respectively; when the potential group purchase user is the real-time listener closest to the manufacturer end, the potential group purchase user is connected to the previous level of real-time listener and the manufacturer respectively. Recording unfinished purchase requests in the listener can merge multiple requests of the same listener row to prevent repeated transmission. The group purchase linked list is used to temporarily store group purchase requests, and transmit the group purchase request to trigger the potential group purchase user to execute data group purchase from the next level of real-time listener or manufacturer.
[0078] The effectiveness and quantity distribution of group purchases in different commodity categories are greatly different. This is due to the spatial locality characteristics of application behavior and group purchase algorithm design. That is, applications tend to access and use data in a centralized manner. Group purchase strategies designed based on application characteristics often contain this characteristic. Based on the regional differences of group purchases, the embodiment of the present invention clusters the purchase preferences of potential group purchase users into multiple preference vectors, and executes a separate group purchase purchase decision for each preference vector.
[0079] Specifically, the embodiment of the present invention performs real-time acquisition of the access probability value and purchase conversion probability value of each preference vector within the recommended time. Among them, the access probability value is used to indicate the frequency of the listener failure of the preference vector, which can be determined based on the tendency products occurring in the preference vector within the recommended time. Exemplarily, the tendency products occurring in the preference vector within the recommended time can be directly used as the value of the access probability value of the preference vector, or the access probability value can be calculated based on the ratio of the number of visits received by the preference vector within the recommended time to the tendency products, and so on. The access probability value can be used to estimate the space where the potential group purchase of the preference vector can play a role. If the access probability value of the preference vector within the recommended time is low, the group purchase scale of the preference vector can be limited to a relatively low range; conversely, if the access probability value of the preference vector within the recommended time is high, it means that the group purchase demand of the preference vector is high, and multiple group purchases need to be performed to meet the data requirements of the received access request. The purchase conversion probability value is used to indicate the proportion of the effective group purchase of the preference vector within the recommended time in all group purchases placed, which can be determined based on the number of group purchases not returned and the number of group purchase orders placed by the preference vector within the recommended time. Among them, group purchase non-return refers to the data block returned from the group purchase being accessed later, and the number of group purchase orders refers to the number of group purchase requests placed by the target merchant warehouse for the preference vector. The purchase conversion probability value can be used to estimate the group purchase quality of the target merchant warehouse for the preference vector. If the purchase conversion probability value of the preference vector within the recommended time is low, it means that the group purchase quality of the target merchant warehouse for the preference vector is low, and the group purchase request order for the preference vector can be reduced to reduce the overhead caused by frequent group purchases and improve the group purchase performance of the target merchant warehouse; if the purchase conversion probability value of the preference vector within the recommended time is high, it means that the group purchase quality of the target merchant warehouse for the preference vector is high, and the group purchase request for the preference vector can be placed normally.
[0080] It should be noted that the recommended time in the embodiment of the present invention can be a preset time period, and the time span corresponding to each time is consistent; the time length of the recommended time can also be defined based on events, and the number of times a specific event occurs within each time is consistent. For example, 20 listener failures of potential group purchasing users can be set as one time, and so on.
[0081] If the target merchant warehouse meets the purchase requirements, the effective group purchase scale of each preference vector can be determined based on the access probability value and purchase conversion probability value of each preference vector, and then based on the effective group purchase scale, a separate decision can be made on the transmission of the group purchase request of each preference vector.
[0082] Among them, the purchase requirements are used to determine whether it is necessary to execute purchases for the target merchant warehouse. Exemplarily, the number of group purchase requests and the number of group purchases that have not been returned can be obtained from the target merchant warehouse, and then the group purchase prediction value of the target merchant warehouse can be determined. In the scenario where the group purchase prediction value of the target merchant warehouse is less than a certain critical value, for example, the group purchase prediction value is less than 20%, it can be determined that the target merchant warehouse meets the purchase requirements, and the number of frequent group purchases can be reduced by executing purchase decisions on the target merchant warehouse, reducing the abnormality and purchase expenses of frequent group purchases triggered by the target merchant warehouse to potential group purchase users, thereby improving the group purchase performance of the target merchant warehouse. In another embodiment, the proportion of group purchase requests placed by the target merchant warehouse in the access requests that cause listener failure in the real-time listener closest to the manufacturer side can also be obtained, and the manufacturer warehouse throughput generated by the target merchant warehouse can be estimated based on this proportion. In a scenario where the manufacturer warehouse throughput generated by the target merchant warehouse is greater than a certain critical value, for example, greater than 50%, it can be determined that the target merchant warehouse meets the purchase requirements, and the manufacturer warehouse throughput generated by the target merchant warehouse can be reduced by executing purchase decisions on the target merchant warehouse, thereby improving the overall performance of the processor system.
[0083] The effective group purchase scale of the preference vector can be calculated and output based on the access probability value and purchase conversion probability value of the preference vector. As an example, the effective group purchase scale = w × access probability value × purchase conversion probability value, where w is a preset coefficient, and the value of w can be set based on actual needs.
[0084] After determining the effective group purchase scale of each preference vector, the transmission of group purchase requests corresponding to each preference vector can be determined based on the effective group purchase scale within a preset time in the future. Within a preset time in the future, the number of group purchase requests corresponding to each preference vector transmitted to subsequent purchase parts is less than or equal to the effective group purchase scale of the preference vector.
[0085] Taking the processor system as an example, after receiving the access request (including the group purchase request of the previous level real-time listener), the potential group purchase user will feedback the listener non-return scenario to the target merchant warehouse. The target merchant warehouse predicts the data that may be accessed in the future based on the listener non-return scenario of the potential group purchase user, and generates a group purchase request so as to group purchase these data to the potential group purchase user in advance. The potential group purchase user group purchases data from the next level real-time listener or manufacturer based on the group purchase request, and fills it back into the real-time listener of this level to perform a merge on the requests of the same listener row in the potential group purchase user, so as to avoid repeating the transmission of the same request to the next level real-time listener or manufacturer. The potential group purchase user feeds back the non-return scenario (i.e., group purchase non-return) and the listener non-return scenario of the data returned from the group purchase in subsequent visits to the group purchase recommendation device based on user preferences. The group purchase recommendation device based on user preferences determines the purchase conversion probability value of each preference vector in the potential group purchase user based on the group purchase non-return scenario of the potential group purchase user, and determines the access probability value of the potential group purchase user based on the listener non-return scenario of the potential group purchase user.
[0086] In the processor system, the group purchase decision unit will execute acquisition of the group purchase request placed by the target merchant warehouse. In the scenario where the target merchant warehouse meets the purchase requirements, the group purchase decision unit can determine the preference vector corresponding to the group purchase request based on the group purchase commodity category carried in each group purchase request placed by the target merchant warehouse. If the effective group purchase scale of the preference vector corresponding to the group purchase request is not 0, the transmission of the group purchase request can be performed without intervention, and the group purchase request will be normally transmitted to the group purchase linked list, waiting to be transmitted in the group purchase linked list to execute the subsequent group purchase process. In addition, after the group purchase request corresponding to a certain preference vector is normally ordered, the group purchase decision unit can reduce the effective group purchase scale of the preference vector by 1. If the effective group purchase scale of the preference vector corresponding to the group purchase request is equal to 0, the group purchase request will be interrupted, and the group purchase request interrupted by the group purchase decision unit will no longer be transmitted to the group purchase linked list, and will no longer trigger the subsequent group purchase process.
[0087] The group purchase recommendation method based on user preferences provided by the embodiment of the present invention performs clustering on the purchase preferences of group purchase potential users, and obtains the access probability value and purchase conversion probability value in each preference vector in a timely manner. In the scenario where the target merchant warehouse meets the purchase requirements, the access probability value and purchase conversion probability value of the preference vector are used to determine how many group purchase requests are placed for the preference vector in the future preset time, thereby realizing a separate decision on the group purchase scale of each preference vector. Purchasing for a certain preference vector will not affect the normal group purchase process of other preference vectors among the group purchase potential users, thereby avoiding the blindness of executing global purchase for the group purchase potential users, and improving the accuracy of group purchase decision. In addition, the embodiment of the present invention triggers the purchase decision only in the scenario where the target merchant warehouse meets the purchase requirements, and can ensure that the group purchase requests generated by the target merchant warehouse are retained as much as possible when the target merchant warehouse does not detect a throughput problem, thereby reducing the throughput overhead caused by group purchase while ensuring the group purchase performance of the target merchant warehouse, and is conducive to improving the overall performance of the processor system.
[0088] It should be noted that many active group purchase procurement technologies in related technologies decide the aggressiveness and group purchase distance of merchant servers based on indicators such as group purchase accuracy, coverage, last-level listener anomalies, and real-time warehouses. For each merchant server, it is necessary to propose a targeted solution for the aggressiveness and group purchase distance, which is usually manifested in targeted adjustment of the critical value. These procurement technologies mainly detect the following problems:
[0089] (1) Aggressive purchasing may result in too many valid group purchases being blocked, causing the performance of the merchant server to deteriorate.
[0090] (2) Purchasing conservatively may result in invalid group purchases being placed, which will not help alleviate problems such as real-time monitor anomalies.
[0091] The group purchase recommendation method based on user preference provided by the embodiment of the present invention first determines whether the target merchant warehouse meets the purchase requirements before executing the purchase of the target merchant warehouse. If the target merchant warehouse meets the purchase requirements, the purchase mechanism is triggered, and the transmission of the group purchase request is determined based on the effective group purchase scale of each preference vector in the group purchase potential users; if the target merchant warehouse does not meet the purchase requirements, the group purchase is directly triggered based on the group purchase request. Compared with the active purchase technology in the related art, the embodiment of the present invention can retain the group purchase request as much as possible when the target merchant warehouse does not detect the throughput problem, avoids the excessive effective group purchases being blocked due to aggressive purchases, and ensures the group purchase performance of the target merchant warehouse. In addition, the embodiment of the present invention performs regional clustering on the potential users of group purchase, calculates the effective group purchase scale by the access probability value of the preference vector and the group purchase prediction value, rather than directly disabling or enabling the group purchase in the area, avoiding the blindness of global purchases and improving the accuracy of purchase decisions.
[0092] In addition, the embodiment of the present invention can determine whether the preference vector needs to be stored through group purchase based on the access probability value of the preference vector, and can avoid placing group purchase orders for invalid targets; based on the purchase conversion probability value of the preference vector, it can be evaluated whether the group purchase effectively solves the storage problem of the preference vector. Combining these two pieces of information to determine the effective group purchase scale of the preference vector can reduce invalid group purchase orders, alleviate the abnormality of frequent group purchases on real-time monitors, reduce purchase costs, and thus improve the overall performance of the processor system.
[0093] Optionally, step 101 clusters the purchase preferences of potential group purchase users into multiple preference vectors, including: grouping the current inventory product categories among the potential group purchase users using the product category ID of the current inventory product category as a label, and outputting multiple preference vectors; the labels of the current inventory product categories contained in the same preference vector are consistent.
[0094] In an embodiment of the present invention, the current inventory commodity categories can be grouped according to the commodity category IDs of the current inventory commodity categories among the group purchase potential users, thereby directly segmenting the purchase preferences of the group purchase potential users into multiple preference vectors. For example, the commodity category IDs of the current inventory commodity categories can be used as labels to group the current inventory commodity categories.
[0095] It is understandable that the number of bits corresponding to the label can be set based on actual needs, so that the size of the preference vector to be segmented can be adjusted by adjusting the number of bits of the label.
[0096] Optionally, the step 102 of acquiring the access probability value and purchase conversion probability value of each preference vector within the recommendation time in real time includes:
[0097] Step S11: during the group purchase period, obtain the preferred product, the number of first group purchase orders, and the number of unreturned products in the first group purchase corresponding to each preference vector;
[0098] Step S12: determining the access probability value of the preference vector based on the trend product;
[0099] Step S13: Calculate the purchase conversion probability value in the preference vector based on the number of orders for the first group purchase and the number of non-returns for the first group purchase.
[0100] In an embodiment of the present invention, the tendency product occurring in the preference vector within the recommendation time can be directly used as the access probability value of the preference vector, or the access probability value can be calculated based on the ratio of the number of visits received by the preference vector within the recommendation time to the tendency product, and so on.
[0101] The number of times the first group purchase was not returned refers to the number of times the data block returned by the group purchase in the preference vector was subsequently accessed. The number of first group purchase orders refers to the number of group purchase requests for the preference vector placed by the target merchant warehouse. The purchase conversion probability value of the preference vector can be determined based on the number of first group purchase orders and the number of times the first group purchase was not returned of the preference vector, and the purchase conversion probability value = the number of first group purchase not returned / the number of first group purchase orders.
[0102] In an optional embodiment of the present invention, in step 103, before the transmission of the group purchase request corresponding to the preference vector is determined based on the effective group purchase scale within the future preset group purchase time, the method further includes:
[0103] Step S21, recording the access probability value, purchase conversion probability value and effective group purchase scale of the preference vector in the preference vector continuous period table;
[0104] The step 103 of transmitting the group purchase request corresponding to the preference vector based on the effective group purchase scale within a preset group purchase time in the future includes:
[0105] Step S22: in a scenario where a group purchase request transmitted by the target merchant warehouse is obtained, the preference vector continuous periodic table is retrieved based on the group purchase commodity category carried in the group purchase request;
[0106] Step S23: if a first preference vector associated with the group-buying commodity category is detected in the preference vector persistence period table, then obtaining an effective group-buying scale and a purchase conversion probability value of the first preference vector;
[0107] Step S24: when the effective group purchase scale is greater than 0 and the purchase conversion probability value is not less than a first critical value, the group purchase request is transmitted to a group purchase linked list, and the value of the effective group purchase scale of the first preference vector in the preference vector continuous periodic table is reduced by m, where m is greater than 0.
[0108] In the embodiment of the present invention, the access probability value (or preferred product) of each preference vector, the number of unreturned products in the first group purchase, the number of orders placed in the first group purchase, and the effective group purchase scale can be recorded through a preference vector continuous periodic table.
[0109] In an embodiment of the present invention, if a group purchase request for placing an order at a target merchant warehouse is obtained, and the target merchant warehouse meets the purchase requirements, the preference vector continuous periodic table can be retrieved based on the group purchase commodity category carried in the group purchase request. If a first preference vector Ri associated with the group purchase commodity category is detected in the preference vector continuous periodic table, the effective group purchase scale and purchase conversion probability value of the first preference vector Ri can be obtained from the preference vector continuous periodic table to determine whether to place an order for the group purchase request. If the current effective group purchase scale of the first preference vector Ri is greater than 0, and the purchase conversion probability value is not less than the first critical value, the group purchase request can be normally transmitted to the group purchase chain table to trigger the subsequent group purchase process. Then, the value of the effective group purchase scale of the first preference vector Ri in the preference vector continuous periodic table is reduced by m, where m is greater than 0. Among them, the value of m can be determined based on the initial value of the effective group purchase scale. For example, when the calculated effective group purchase scale = w × access probability value × purchase conversion probability value, in the scenario where the coefficient w takes a large value, m can be an integer greater than 1, such as 2 or 3, so as to perform correction on the coefficient w to avoid the situation where the number of group purchase requests actually placed is large and the purchase effect cannot be achieved in the scenario where the value of w takes a large value. When the coefficient w takes a small value, m can be equal to 1.
[0110] The first critical value may be set based on actual needs, for example, the first critical value may be 20%.
[0111] Optionally, the method further includes: in a scenario that meets the first requirement, interrupting the group purchase request.
[0112] The first requirement includes at least one of the following:
[0113] W1: the first preference vector associated with the group-buying commodity category is not detected in the preference vector persistence periodic table;
[0114] W2, the effective group purchase scale of the first preference vector is equal to 0;
[0115] W3. The purchase conversion probability value of the first preference vector is less than the first critical value.
[0116] It should be noted that if the group purchase commodity category of the group purchase request belongs to the purchase preference of a certain preference vector, the group purchase request can be considered to be associated with the preference vector. Exemplarily, the commodity category ID of the group purchase commodity category can be compared with the label of the preference vector. If the commodity category ID of the group purchase commodity category is consistent with the label of the preference vector, the group purchase request can be considered to be associated with the preference vector.
[0117] In the embodiment of the present invention, if the first preference vector associated with the group purchase commodity category carried in the group purchase request is not detected in the preference vector continuous period table, the group purchase request can be interrupted. Alternatively, if the first preference vector associated with the group purchase commodity category carried in the group purchase request is detected in the preference vector continuous period table, but the current effective group purchase scale of the first preference vector is 0, or the purchase conversion probability value is less than the first critical value, the group purchase request is interrupted.
[0118] Exemplarily, in the processor system, the group purchase decision unit obtains the group purchase request for placing an order at the target merchant warehouse, and in the scenario where it is determined that interruption is required, the group purchase request is not transmitted to the group purchase linked list, and the subsequent group purchase process is no longer triggered.
[0119] The embodiment of the present invention determines whether to place a group purchase request based on the effective group purchase scale and the purchase conversion probability value of the preference vector, which can reduce the number of orders for frequent group purchases while reducing the group purchase throughput, thereby reducing the purchase expenses caused by frequent group purchases and improving the group purchase performance of the target merchant warehouse.
[0120] Optionally, refer to Figure 2 , the method further comprises:
[0121] Step S31, obtaining the number of purchase requests from the target merchant warehouse in the purchase requests transmitted by the listener to the manufacturer within the recommended time; the listener is a real-time listener closest to the manufacturer in the processor system;
[0122] Step S32, obtaining the number of second group purchase orders and the number of second group purchase non-return orders of the target merchant warehouse within the recommended time;
[0123] Step S33: determining a second group purchase prediction value of the target merchant warehouse based on the second group purchase order number and the second group purchase non-return number;
[0124] Step S34, calculating the group purchase throughput of the target merchant warehouse based on the request quantity and the second group purchase prediction value; the group purchase throughput is used to indicate the additional manufacturer warehouse throughput caused by the frequent group purchases of the target merchant warehouse;
[0125] Step S35: in a scenario where the group purchase throughput is greater than a second critical value, determining that the merchant server meets the purchase requirements.
[0126] In an embodiment of the present invention, the number of second group purchase orders and the number of second group purchase non-returns of the target merchant warehouse within the recommended time can be obtained, and the second group purchase prediction value can be calculated. The number of second group purchase orders refers to the number of group purchase requests transmitted by the target merchant warehouse to the subsequent purchase component (such as the group purchase chain list). The number of second group purchase non-returns refers to the number of times the data of the group purchase request placed by the target merchant warehouse to the group purchase potential user is accessed in the subsequent purchase. The second group purchase prediction value = the number of second group purchase non-returns / the number of second group purchase orders.
[0127] The listener refers to the real-time listener closest to the manufacturer in the processor system. The proportion of group purchase requests that belong to the target merchant warehouse order in the purchase requests transmitted by the listener to the manufacturer is counted, that is, the number of requests from the target merchant warehouse in the purchase requests transmitted by the listener to the manufacturer. Then, based on this number of requests and the second group purchase prediction value of the target merchant warehouse, the additional manufacturer warehouse throughput caused by the frequent group purchases triggered by the target merchant warehouse is estimated. Exemplarily, for example, when the second group purchase prediction value of the target merchant warehouse is 20%, and the number of requests from the target merchant warehouse in the requests that cause the listener failure of the listener is 50%, it can be estimated that the frequent group purchases at this time cause about 50%×(1-20%)=40% of the group purchase throughput. It should be noted that the correct group purchase replaces the role of normal access, so it will not cause additional manufacturer warehouse throughput.
[0128] Based on the group purchase throughput of the target merchant warehouse, it can be determined whether it is necessary to execute a purchase decision for the target merchant warehouse. For example, if the group purchase throughput is greater than the second critical value, it can be determined that the target merchant warehouse meets the purchase requirements, and the purchase decision for the target merchant warehouse can be triggered. The second critical value can be set based on actual decision requirements, for example, the second critical value can be 30%.
[0129] In summary, the embodiment of the present invention provides a group purchase recommendation method based on user preferences, performs clustering on the purchase preferences of group purchase potential users, and obtains the access probability value and purchase conversion probability value in each preference vector in a timely manner. In the scenario where the target merchant warehouse meets the purchase requirements, the access probability value and purchase conversion probability value of the preference vector are used to determine how many group purchase requests are placed for the preference vector in the future preset time, thereby realizing a separate decision on the group purchase scale of each preference vector. Purchasing for a certain preference vector will not affect the normal group purchase process of other preference vectors among the group purchase potential users, thereby avoiding the blindness of executing global purchase for group purchase potential users, and improving the accuracy of group purchase decision. In addition, the embodiment of the present invention triggers the purchase decision only in the scenario where the target merchant warehouse meets the purchase requirements, and can ensure that the group purchase requests generated by the target merchant warehouse are retained as much as possible when the target merchant warehouse does not detect a throughput problem, thereby reducing the throughput overhead caused by group purchase while ensuring the group purchase performance of the target merchant warehouse, and is conducive to improving the overall performance of the processor system.
[0130] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.
[0131] Device Embodiment
[0132] Reference Figure 3 , shows a structural block diagram of a group purchase recommendation device based on user preferences of the present invention, and the device may specifically include:
[0133] A segmentation unit 301 is used to cluster the purchase preferences of potential group purchase users into multiple preference vectors;
[0134] The first acquisition unit 302 is used to acquire the access probability value and purchase conversion probability value of each preference vector within the recommendation time in real time;
[0135] A first determining unit 303 is configured to determine an effective group purchase scale of the preference vector based on the access probability value and the purchase conversion probability value in a scenario where the target merchant warehouse corresponding to the group purchase potential user meets the purchase requirements;
[0136] The decision unit 304 is configured to decide the transmission of the group purchase request corresponding to the preference vector based on the effective group purchase scale within a preset time in the future.
[0137] Optionally, the device further comprises:
[0138] A recording unit, used to record the access probability value, purchase conversion probability value and effective group purchase scale of the preference vector in a preference vector continuous period table;
[0139] The decision-making unit comprises:
[0140] A retrieval subunit, configured to retrieve the preference vector continuous periodic table based on the group purchase commodity category carried in the group purchase request, in a scenario where the group purchase request transmitted by the target merchant warehouse is obtained;
[0141] an obtaining subunit, configured to obtain an effective group purchase scale and a purchase conversion probability value of the first preference vector if a first preference vector associated with the group purchase commodity category is detected in the preference vector persistence period table;
[0142] A transmission subunit is used to transmit the group purchase request to the group purchase linked list and reduce the value of the effective group purchase scale of the first preference vector in the preference vector continuous periodic table by m, where m is greater than 0, in a scenario where the effective group purchase scale is greater than 0 and the purchase conversion probability value is not less than a first critical value.
[0143] Optionally, the decision unit further includes:
[0144] An interruption subunit, configured to interrupt the group purchase request in a scenario that meets the first requirement;
[0145] The first requirement includes at least one of the following:
[0146] The first preference vector associated with the group-buying commodity category is not detected in the preference vector continuous periodic table;
[0147] The effective group purchase scale of the first preference vector is equal to 0;
[0148] The purchase conversion probability value of the first preference vector is less than the first critical value.
[0149] Optionally, the segmentation unit includes:
[0150] The segmentation subunit is used to group the current inventory commodity categories of the group purchase potential users by using the commodity category ID of the current inventory commodity category as a label, and output a plurality of preference vectors; the labels of the current inventory commodity categories contained in the same preference vector are consistent.
[0151] Optionally, the first acquiring unit includes:
[0152] An acquisition subunit is used to obtain the preferred product, the number of first group purchase orders, and the number of unreturned products in the first group purchase corresponding to each preference vector within the group purchase period;
[0153] an access probability value determination subunit, configured to determine an access probability value of the preference vector based on the trend product;
[0154] The group purchase prediction value calculation subunit is used to calculate the purchase conversion probability value in the preference vector based on the first group purchase order number and the first group purchase non-return number.
[0155] Optionally, the device further comprises:
[0156] An acquisition unit, configured to acquire the number of requests from the target merchant warehouse in the purchase requests transmitted by the listener to the manufacturer within the recommended time; the listener is a real-time listener closest to the manufacturer in the processor system;
[0157] A second acquisition unit is used to obtain the number of second group purchase orders and the number of second group purchase non-return orders of the target merchant warehouse within the recommended time;
[0158] A second determining unit, configured to determine a second group purchase prediction value of the target merchant warehouse based on the second group purchase order number and the second group purchase non-return number;
[0159] A throughput calculation unit, configured to calculate the group purchase throughput of the target merchant warehouse based on the request quantity and the second group purchase prediction value; the group purchase throughput is used to indicate the additional manufacturer warehouse throughput caused by the frequent group purchases of the target merchant warehouse;
[0160] The purchase determination unit is used to determine that the merchant server meets the purchase requirements when the group purchase throughput is greater than the second critical value.
[0161] In summary, the embodiment of the present invention provides a group purchase recommendation device based on user preferences, which performs clustering on the purchase preferences of group purchase potential users, and obtains the access probability value and purchase conversion probability value in each preference vector in a timely manner. In the scenario where the target merchant warehouse meets the purchase requirements, the access probability value and purchase conversion probability value of the preference vector are used to determine how many group purchase requests are placed for the preference vector in the future preset time, thereby realizing a separate decision on the group purchase scale of each preference vector. Purchasing for a certain preference vector will not affect the normal group purchase process of other preference vectors among group purchase potential users, thereby avoiding the blindness of executing global purchase for group purchase potential users, and improving the accuracy of group purchase decision. In addition, the embodiment of the present invention triggers the purchase decision only in the scenario where the target merchant warehouse meets the purchase requirements, which can ensure that the group purchase requests generated by the target merchant warehouse are retained as much as possible when the target merchant warehouse does not detect a throughput problem, thereby reducing the throughput overhead caused by group purchase while ensuring the group purchase performance of the target merchant warehouse, and is conducive to improving the overall performance of the processor system.
[0162] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0163] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The similar parts between the various embodiments can be referenced to each other.
[0164] Regarding the processor in the above embodiment, the specific manner in which each unit performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0165] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the clustering of units is only a logical function clustering. There may be other clustering methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0166] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be physically detected separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the content of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.
[0167] The above detailed description of the specific implementation of the invention is only used as an example, and the present application is not limited to the specific implementation described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application. Therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the present application should be included in the scope of the present application.
Claims
1. A group purchase recommendation method based on user preferences, characterized in that: The method comprises: Cluster the purchase preferences of potential group buying users into multiple preference vectors; Obtain the access probability value and purchase conversion probability value of each preference vector within the recommended time in real time; In a scenario where the target merchant warehouse corresponding to the potential group purchase user meets the purchase requirements, determining the effective group purchase scale of the preference vector based on the access probability value and the purchase conversion probability value; Within a preset time in the future, determining the transmission of the group purchase request corresponding to the preference vector based on the effective group purchase scale; Before the transmission of the group purchase request corresponding to the preference vector is determined based on the effective group purchase scale within a preset future time, the method further includes: Record the access probability value, purchase conversion probability value and effective group purchase scale of the preference vector in the preference vector continuous periodic table; The transmission of the group purchase request corresponding to the preference vector is determined based on the effective group purchase scale within a preset time in the future, including: In a scenario where a group purchase request transmitted by the target merchant warehouse is obtained, the preference vector continuous periodic table is retrieved based on the group purchase commodity category carried in the group purchase request; If a first preference vector associated with the group-buying commodity category is detected in the preference vector persistence periodic table, obtaining an effective group-buying scale and a purchase conversion probability value of the first preference vector; In a scenario where the effective group purchase scale is greater than 0 and the purchase conversion probability value is not less than a first critical value, the group purchase request is transmitted to a group purchase linked list, and the value of the effective group purchase scale of the first preference vector in the preference vector continuous periodic table is reduced by m, where m is greater than 0; The purchasing preferences of potential group purchase users are clustered into multiple preference vectors, including: The product category ID of the current inventory product category is used as a label, and the current inventory product category of the group purchase potential users is grouped to output a plurality of preference vectors; the labels of the current inventory product category contained in the same preference vector are consistent; The real-time acquisition of the access probability value and purchase conversion probability value of each preference vector within the recommendation time includes: During the group purchase period, obtain the preferred product, the number of orders for the first group purchase, and the number of unreturned products for the first group purchase corresponding to each preference vector; determining an access probability value of the preference vector based on the trending product; Calculating a purchase conversion probability value in the preference vector based on the first group purchase order number and the first group purchase non-return number; The method further comprises: Obtaining the number of purchase requests from the target merchant warehouse in the purchase requests transmitted by the listener to the manufacturer within the recommended time; the listener is a real-time listener closest to the manufacturer in the processor system; Obtain the number of second group purchase orders and the number of second group purchase non-return orders of the target merchant warehouse within the recommended time; Determining a second group purchase prediction value of the target merchant warehouse based on the second group purchase order number and the second group purchase non-return number; Calculating the group purchase throughput of the target merchant warehouse based on the request quantity and the second group purchase prediction value; the group purchase throughput is used to indicate the additional manufacturer warehouse throughput caused by the frequent group purchases of the target merchant warehouse; In a scenario where the group purchase throughput is greater than the second critical value, it is determined that the merchant server meets the purchase requirements.
2. The method according to claim 1, characterized in that The method further comprises: In a scenario that meets the first requirement, interrupting the group purchase request; The first requirement includes at least one of the following: The first preference vector associated with the group-buying commodity category is not detected in the preference vector continuous periodic table; The effective group purchase scale of the first preference vector is equal to 0; The purchase conversion probability value of the first preference vector is less than the first critical value.
3. A group purchase recommendation device based on user preferences, characterized in that: The device comprises: A segmentation unit, used to cluster the purchase preferences of potential group purchase users into multiple preference vectors; A first acquisition unit is used to acquire in real time the access probability value and purchase conversion probability value of each preference vector within the recommendation time; A first determining unit is used to determine the effective group purchase scale of the preference vector based on the access probability value and the purchase conversion probability value in a scenario where the target merchant warehouse corresponding to the group purchase potential user meets the purchase requirements; A decision unit, configured to decide, within a preset time in the future, the transmission of the group purchase request corresponding to the preference vector based on the effective group purchase scale; A recording unit, used to record the access probability value, purchase conversion probability value and effective group purchase scale of the preference vector in a preference vector continuous period table; The decision-making unit comprises: A retrieval subunit, configured to retrieve the preference vector continuous periodic table based on the group purchase commodity category carried in the group purchase request, in a scenario where the group purchase request transmitted by the target merchant warehouse is obtained; an obtaining subunit, configured to obtain an effective group purchase scale and a purchase conversion probability value of the first preference vector if a first preference vector associated with the group purchase commodity category is detected in the preference vector persistence period table; a transmission subunit, configured to transmit the group purchase request to a group purchase linked list and reduce the value of the effective group purchase scale of the first preference vector in the preference vector continuous periodic table by m, where m is greater than 0, in a scenario where the effective group purchase scale is greater than 0 and the purchase conversion probability value is not less than a first critical value; The segmentation unit comprises: The segmentation subunit is used to group the current inventory commodity categories of the group purchase potential users by using the commodity category ID of the current inventory commodity category as a label, and output a plurality of preference vectors; the labels of the current inventory commodity categories contained in the same preference vector are consistent; The first acquisition unit includes: An acquisition subunit is used to obtain the preferred product, the number of first group purchase orders, and the number of unreturned products in the first group purchase corresponding to each preference vector within the group purchase period; an access probability value determination subunit, configured to determine an access probability value of the preference vector based on the trend product; a group purchase prediction value calculation subunit, configured to calculate a purchase conversion probability value in the preference vector based on the first group purchase order number and the first group purchase non-return number; The device also includes: An acquisition unit, configured to acquire the number of requests from the target merchant warehouse in the purchase requests transmitted by the listener to the manufacturer within the recommended time; the listener is a real-time listener closest to the manufacturer in the processor system; A second acquisition unit is used to obtain the number of second group purchase orders and the number of second group purchase non-return orders of the target merchant warehouse within the recommended time; A second determining unit, configured to determine a second group purchase prediction value of the target merchant warehouse based on the second group purchase order number and the second group purchase non-return number; A throughput calculation unit, configured to calculate the group purchase throughput of the target merchant warehouse based on the request quantity and the second group purchase prediction value; the group purchase throughput is used to indicate the additional manufacturer warehouse throughput caused by the frequent group purchases of the target merchant warehouse; The purchase determination unit is used to determine that the merchant server meets the purchase requirements when the group purchase throughput is greater than the second critical value.
4. The device according to claim 3, characterized in that The decision making unit also includes: An interruption subunit, configured to interrupt the group purchase request in a scenario that meets the first requirement; The first requirement includes at least one of the following: The first preference vector associated with the group-buying commodity category is not detected in the preference vector continuous periodic table; The effective group purchase scale of the first preference vector is equal to 0; The purchase conversion probability value of the first preference vector is less than the first critical value.
Citation Information
Patent Citations
Internet group buying method and system
CN105654364A
Big data-based grouping method and system
CN112419016A
E-commerce big data logistics supply chain control system based on artificial intelligence and block chain
CN113139690A
Flow limiting processing method and device, equipment and storage medium
CN115051952A
