A Flow Regulation Method, System, Smart Terminal and Storage Medium

Abstract

This application relates to the field of computer technology, and in particular, to a traffic regulation method, system, intelligent terminal, and storage medium, aiming to solve the problem that the order volume of different commodities traded is affected by different exposure positions in the prior art, and a single rule is used to regulate the exposure positions of all stores, and the expected regulation effect cannot be accurately achieved in all cases. The technical solution is a traffic regulation method, including the following steps: obtaining a user's search request, obtaining an initial commodity list based on the search request, and sorting the commodities in the initial commodity list based on a preset sorting rule; obtaining the regulation requirements of the target commodity, and obtaining a regulation plan for the target commodity under the search request based on the regulation requirements; performing a secondary sorting on the initial commodity list based on the regulation plan to obtain a regulated commodity list. This application has the effect of improving the accuracy of traffic regulation.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a flow control method, system, intelligent terminal and storage medium. Background Art

[0002] E-commerce refers to the efficient online trading activities between buyers and sellers in the open network environment of the Internet based on the client / server application mode in a wide range of commercial trade activities around the world, which can realize online shopping for consumers, online transactions between merchants, online electronic payments and various business activities. On this basis, the rapid development of mobile applications has spawned a large number of application platforms for realizing e-commerce services, allowing users to select and trade merchants and their products based on the merchant information placed in mobile applications.

[0003] Application platforms that provide e-commerce services can help stores gain a huge customer base, attracting a large number of stores to settle in, leading to fierce competition for goods. In a competitive environment, the order in which merchants are displayed on the application platform, that is, the exposure position of the merchants, has a great impact on the number of clicks and orders of the merchants. Stores with high exposure positions can obtain higher user traffic and thus close more orders.

[0004] Currently, the platform can adjust the exposure position to achieve the control of store traffic. The platform usually uses fixed rules to control the store exposure position, such as top, bottom, and control to a certain specified position.

[0005] In the process of implementing this application, the inventors found that the above technology has at least the following problems:

[0006] The order volumes of different products are affected differently by exposure positions. Using a single rule to regulate the exposure positions of all stores cannot accurately achieve the desired regulation effect. Summary of the invention

[0007] In order to improve the accuracy of traffic control, the present application provides a traffic control method, system, intelligent terminal and storage medium.

[0008] In the first aspect, the present application provides a flow control method, which adopts the following technical solution:

[0009] A flow control method, the method comprising the following steps:

[0010] Obtaining a user's search request, obtaining an initial product list based on the search request, and sorting the products in the initial product list based on a preset sorting rule;

[0011] Obtain the regulation requirements of the target commodity, and based on the regulation requirements, obtain the regulation plan of the target commodity under the search request;

[0012] Based on the regulation plan, perform a secondary sorting on the initial commodity list to obtain the regulated commodity list.

[0013] By adopting the above technical solution, after obtaining the user's search request, an initial commodity list is obtained, which facilitates formulating and implementing corresponding regulation plans based on the current situation of the commodity list, replacing the adjustment according to fixed rules, helping to improve the pertinence and accuracy of the traffic regulation plan. In addition, the setting of the regulation plan is based on the regulation requirements of the target commodity, which helps to intuitively meet the regulation requirements of the commodity and reduces the possibility that the regulation plan fails to achieve the effect.

[0014] Optionally, before obtaining the regulation requirements of the target commodity and obtaining the regulation plan of the target commodity under the search request based on the regulation requirements, it further includes:

[0015] Obtain the historical order data of the target commodity, and based on the historical order data, obtain an order prediction model;

[0016] Obtain the exposure-to-order data of the target commodity, where the exposure-to-order data at least includes the historical exposure positions of the target commodity and the order conversion data corresponding to the historical exposure positions;

[0017] Generate a conversion rate prediction model based on the exposure-to-order data.

[0018] By adopting the above technical solution, training with historical order data to obtain an order prediction model and training with exposure-to-order data to obtain a conversion rate prediction model helps the terminal to analyze the order volume of different commodities and the order volume of the same commodity at different exposure positions through data models, thereby helping to improve the output efficiency and accuracy of the regulation plan.

[0019] Optionally, the obtaining the historical order data of the target commodity and obtaining the order prediction model based on the historical order data includes:

[0020] Obtain the historical order data of the target commodity and at least one supplementary reference feature, where the supplementary reference feature at least includes holiday features and commodity quality;

[0021] Based on the historical order data and the supplementary reference features, obtain an order prediction model.

[0022] By adopting the above technical solution, when training and generating the order prediction model, adding supplementary reference features helps to incorporate factors related to the sales volume of commodities such as commodity quality and holidays into the analysis of order prediction, which helps to improve the accuracy of the results output by the order prediction model.

[0023] Optionally, obtaining the regulation demand of the target commodity and obtaining the regulation plan of the target commodity under the search request based on the regulation demand includes:

[0024] Obtain the regulation demand of the target commodity;

[0025] Obtain a regulation plan that meets the regulation demand based on the order prediction model and the conversion rate prediction model;

[0026] The regulation plan is used to perform sorting adjustment on the commodity list output under the same search request for the target commodity.

[0027] By adopting the above technical solution, using the order prediction model and the conversion rate prediction model in the process of generating the regulation plan helps to generate the regulation plan by using the data model, and helps to improve the generation efficiency and accuracy of the regulation plan.

[0028] Optionally, before generating the conversion rate prediction model based on the exposure and order data, it further includes:

[0029] If the sample size of the exposure and order data of the target commodity is lower than the preset sample threshold, then fit the exposure and order data to obtain the fitted exponential curve of the exposure and order data;

[0030] Obtain the simulated conversion data corresponding to the exposure position lacking exposure and order data based on the fitted exponential curve.

[0031] By adopting the above technical solution, when the amount of data generated by the model is insufficient, by fitting the exponential curve, the data that may be generated at the positions with data gaps is simulated and filled, which helps to supplement sufficient data for analysis, and then ensures that the data model can be supported by sufficient data volume, and further helps to improve the accuracy of the output result of the data model.

[0032] Optionally, after performing secondary sorting on the initial commodity list based on the regulation plan to obtain the regulated commodity list, it further includes:

[0033] Periodically obtain the actual order data of the commodity according to the preset time window.

[0034] By adopting the above technical solution, obtaining the actual order data after regulation according to the time window helps to analyze the actual order data, and further helps to analyze the effect of traffic regulation through the actual order data.

[0035] Optionally, after periodically obtaining the actual order data of the target commodity according to the preset time window, it further includes:

[0036] Obtain the regulation deviation data based on the actual order completion data of the target commodity and the regulation requirements;

[0037] Obtain the regulation compensation plan based on the regulation deviation data.

[0038] By adopting the above technical solution, obtaining the deviation data through the analysis of the actual order completion data helps to adjust the exposure position of the commodity within the next time window based on the deviation data, so that the traffic regulation of the commodity reaches the target specified in the regulation requirements, and further helps to improve the regulation effect of the regulation plan.

[0039] In a second aspect, the present application provides a traffic regulation system, adopting the following technical solution:

[0040] A traffic regulation system, the system includes:

[0041] An initial sorting module, configured to obtain a search request of a user, and obtain an initial commodity list based on the search request, and the initial commodity list sorts commodities based on a preset sorting rule;

[0042] A regulation plan module, configured to obtain the regulation requirements of a target commodity, and obtain a regulation plan of the target commodity under the search request based on the regulation requirements;

[0043] A regulation output module, configured to perform a secondary sorting on the initial commodity list based on the regulation plan to obtain a regulated commodity list.

[0044] By adopting the above technical solution, after obtaining the search request of the user, an initial commodity list is obtained, which is convenient for formulating and executing a corresponding regulation plan based on the current situation of the commodity list, replacing the adjustment according to a fixed rule, helping to improve the pertinence and accuracy of the traffic regulation plan. In addition, the setting of the regulation plan is based on the regulation requirements of the target commodity, which helps to intuitively meet the regulation requirements of the commodity and reduces the possibility that the regulation plan cannot achieve the effect.

[0045] In a third aspect, the present application provides an intelligent terminal, adopting the following technical solution:

[0046] An intelligent terminal, the intelligent terminal includes a processor and a memory, and at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement a traffic regulation method as described in any one of the first aspects.

[0047] By adopting the above technical solution, the processor in the intelligent terminal can implement the above traffic regulation method according to the relevant computer programs stored in the memory, so as to improve the accuracy of traffic regulation.

[0048] Fourthly, the present application provides a computer-readable storage medium, adopting the following technical solutions:

[0049] A computer-readable storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement a traffic regulation method as described in any one of the first aspects.

[0050] By adopting the above technical solutions, corresponding programs can be stored, thereby improving the accuracy of traffic regulation.

[0051] In summary, the present application includes at least one of the following beneficial technical effects:

[0052] After obtaining the user's search request, an initial product list is obtained, which facilitates formulating and executing corresponding regulation plans based on the current product list situation, replacing the adjustment according to fixed rules, helping to improve the pertinence and accuracy of the traffic regulation plan. In addition, the setting of the regulation plan is based on the regulation requirements of the target product, which helps to intuitively meet the regulation requirements of the product and reduces the possibility that the regulation plan cannot achieve the desired effect;

[0053] Using historical order data to train and obtain an order prediction model, and using exposure and conversion data to train and obtain a conversion rate prediction model helps the terminal to analyze the order volume of different products and the order volume of the same product at different exposure positions through the data model, thereby helping to improve the output efficiency and accuracy of the regulation plan;

[0054] By analyzing the actual order data to obtain deviation data, it helps to adjust the product exposure position within the next time window based on the deviation data, so that the traffic regulation of the product reaches the target specified in the regulation requirements, thereby helping to improve the regulation effect of the regulation plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0056] Figure 1 It is a method flowchart of a traffic regulation method shown in an embodiment of the present application;

[0057] Figure 2 It is a flowchart block diagram of a traffic regulation method shown in an embodiment of the present application;

[0058] Figure 3 is a system block diagram of a traffic regulation system shown in an embodiment of the present application;

[0059] Figure 4 is a schematic structural diagram of an intelligent terminal shown in an embodiment of the present application.

[0060] Explanation of reference numerals: 1. Initial sorting module; 2. Regulation scheme module; 3. Regulation output module. Detailed implementation manners

[0061] This specific embodiment is only an explanation of the present application, and it does not limit the present application. After reading this specification, those skilled in the art can make modifications without creative contributions to this embodiment as needed, but as long as it is within the scope of the claims of the present application, it is protected by the patent law. To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying Figures 1-4 drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0062] The following will be combined with the specific implementation manners to Figure 1 explain the shown processing flow in detail, and the content can be as follows:

[0063] The embodiment of the present application provides a traffic regulation method, which can be applied to an intelligent terminal. Taking the intelligent terminal as the execution subject, it is used to realize the regulation of the exposure position of a product on the search result list page in an online search scenario. In addition, since the exposure position of a product on the search result list page is usually associated with multiple factors, for example, it is associated with the matching degree of search conditions. Specifically, under the same traffic regulation scheme, the higher the matching degree with the search conditions, the higher the exposure position. For the convenience of understanding the solution of the present application, the search result list pages including the target product described in the embodiments of the present application are all generated based on the same search conditions. On this premise, the present application provides a traffic regulation method, including the following steps:

[0064] Step 101, obtain the search request of the user, and obtain an initial product list based on the search request. The initial product list sorts products based on a preset sorting rule.

[0065] In implementation, before performing traffic regulation on a commodity, it is first necessary to obtain the current traffic status of the target commodity, and the current traffic status of the commodity can be obtained through the current exposure position of the commodity. The intelligent terminal obtains the user's search request. Based on the user's search request, the intelligent terminal can obtain an initial commodity list that matches the search request. At this time, the initial commodity list includes the target commodity, and the target commodity is displayed in the initial commodity list according to a preset sorting rule. Specifically, the preset sorting rule can be based on the relevance between the target commodity and the search request.

[0066] In this way, before implementing traffic regulation, the intelligent terminal can master the current exposure position of the target commodity by obtaining the initial commodity list, which helps to implement a corresponding traffic regulation plan for the current situation of the target commodity.

[0067] Step 102: Obtain the regulation requirement of the target commodity, and based on the regulation requirement, obtain the regulation plan of the target commodity under the search request.

[0068] Specifically, there can be multiple demand dimensions for the regulation requirement of the target commodity. For example, the increment of orders, the increment of fans of the store where the commodity is located, or the increment of collections of the commodity, etc. In this embodiment, the increment of orders is taken as an example for illustration, and other situations are similar and will not be elaborated.

[0069] In implementation, after the intelligent terminal obtains the regulation requirement for the target commodity to generate a certain increment of orders for the target commodity, it obtains a preset regulation plan that matches the target commodity. The regulation plan corresponds to the target commodity and can be designed according to the commodity characteristics of the target commodity itself. In this embodiment, the regulation plan can be achieved by adjusting the exposure position of the target commodity to increase the exposure volume of the target commodity, and then realizing the growth of orders to meet the regulation requirement of the target commodity.

[0070] In one embodiment, since the order volume of a commodity is affected by multiple factors and it is difficult to analyze through a single data, accordingly, the following processing can be done before step 102: Obtain the historical order data of the target commodity, and obtain an order prediction model based on the historical order data; obtain the exposure-to-order data of the target commodity, and the exposure-to-order data at least includes the historical exposure position of the target commodity and the order conversion data corresponding to the historical exposure position; generate a conversion rate prediction model based on the exposure-to-order data.

[0071] Among them, the historical order data refers to the order data of the target commodity on different historical dates. Taking the change amount of the date as the baseline, it reflects the change of the order volume of the target commodity on different dates;

[0072] The exposure-to-order data at least includes the historical exposure positions of the target commodity and the order conversion data corresponding to the historical exposure positions. Taking the change of the exposure position of the commodity as the baseline, it reflects the order conversion volume of the target commodity at different exposure positions.

[0073] In implementation, the conversion rate refers to the probability of generating an actual order after a user clicks on a commodity. The intelligent terminal can use the exposure-to-order data as a training data set to train an ESMM (Entire Space Multi Task) two-tower model to achieve this. The data used in the ESMM two-tower model can include the user's search and click logs, the user's click data, and the corresponding order placement situations. In addition, it can also include the basic information of the target commodity, including the commodity price, commodity usage, store address, etc.; the user's behavior data, including data in dimensions such as the order placement volume, collection volume, or forwarding volume after the user clicks and browses the commodity.

[0074] In this way, in application, the ESMM two-tower model shows the introduction of CTR (Click-Through-Rate) and CTCVR (Click-Through-Conversion-Rate) as auxiliary tasks according to the user behavior sequence jointly characterized by the exposure-to-order data and other supplementary data, and roundaboutly learns CVR (Conversion Rate), so as to achieve the training and prediction work of the conversion rate prediction model. In addition, the AUC value can also be used to evaluate the effect of the conversion rate prediction model.

[0075] In one embodiment, when the data volume of the historical exposure-to-order data is small and only the exposure-to-order data of some positions can be obtained, the accuracy of the operation result of the trained model may be reduced. Therefore, correspondingly, the following processing can also be included in the training of the above conversion rate prediction model: If the sample volume of the exposure-to-order data of the target commodity is lower than the preset sample threshold, then fit the exposure-to-order data to obtain the fitting exponential curve of the exposure-to-order data; based on the fitting exponential curve, obtain the simulated conversion data corresponding to the exposure position where the exposure-to-order data is missing.

[0076] In implementation, after the intelligent terminal obtains the data related to the target commodity for training the conversion rate prediction model, it can compare the obtained sample volume with the preset sample threshold. If the sample volume is lower than the sample threshold, it is necessary to supplement the sample data, and the simulated conversion data can be obtained at the exposure position where the exposure-to-order data is missing by means of exponential curve fitting. Specifically, the sample threshold can be set based on the exposure position, and the sample threshold can be set to 20, 25, or 30, etc., that is, the intelligent terminal needs to obtain at least all the exposure-to-order data of the target commodity when the exposure position is between 1-20, 1-25, 1-30.

[0077] In implementation, when the intelligent terminal fits an exponential curve, it can use the exposure position of the target product as the X-axis, and the conversion rate corresponding to the target product at different exposure positions as the Y-axis. 𝑅2 can be 0.9801. In this way, the exponential curve can be made to approximate the relationship between the average exposure position and the conversion rate. The formula can be as follows:

[0078] y = 0.004ln (x) + 0.0193;

[0079] R2 = 0.9801;

[0080] In this way, during the training process of the conversion rate prediction model, the missing data can be simulated and supplemented, which helps to improve the accuracy of the conversion rate prediction model.

[0081] On the other hand, the intelligent terminal can obtain the historical order data of the target product and the basic information of the target product itself, including product price, product use, store address, etc., and use this as the training data set to train and obtain an order prediction model. Since order prediction has high requirements for the update performance of the prediction model, the LightGBM model can be selected for training the order prediction model. The rolling iteration method can be used for prediction, that is, the data within a certain time window can be selected as the training data set to predict the order volume within the next time window to be predicted. As time rolls, the order volume within the next time window to be predicted is reconstructed into the training data set, and then a new prediction is made. In this embodiment, the rolling iteration training can be performed with a one-week time window.

[0082] In one embodiment, the order volume of the target product may be affected by various factors. Therefore, the following processing may be included in the training process of the order prediction model: obtaining the historical order data of the target product and at least one supplementary reference feature, where the supplementary reference feature at least includes holiday features and product quality; obtaining an order prediction model based on the historical order data and the supplementary reference features.

[0083] In implementation, when the intelligent terminal constructs the training data set of the order prediction model, it can add supplementary reference features to the training data set. The supplementary reference features can be set from multiple dimensions related to the order volume of the target product, such as: the quality fluctuation of the target product, the adjustment of the time window for data statistics, the order fluctuation data of the product and the corresponding fluctuation factors, the historical order volume and the corresponding order time, holiday dimensions and other feature dimensions.

[0084] In this way, in the training data set constructed by the intelligent terminal for the order prediction model, based on the historical order data, the basic information of the target product itself and the supplementary reference features can be supplemented, which is beneficial to improving the accuracy of order prediction.

[0085] In one embodiment, after obtaining the order prediction model and the conversion rate prediction model, the following processing can be performed: obtaining the regulation requirement of the target commodity; obtaining a regulation plan that meets the regulation requirement based on the order prediction model and the conversion rate prediction model; the regulation plan is used to perform sorting adjustment on the commodity list output under the same search request for the target commodity.

[0086] In implementation, after the intelligent terminal obtains the regulation requirement of the user, it can generate a corresponding regulation plan through the order prediction model and the conversion rate prediction model. Taking the regulation requirement described above in this embodiment as an example of generating an order increment A for the target commodity in the next time window, when the intelligent terminal obtains the regulation requirement of generating an order increment A, it first obtains the exposure position of the target commodity under the default sorting currently. The intelligent terminal can predict the order volume of the current target commodity in the next time window through the order prediction model. Assuming the prediction result is that the default order volume is B, the intelligent terminal can obtain that the final order volume that the target commodity needs to generate in the next time window is A + B. At this time, the intelligent terminal can predict the conversion rate of the commodity at different exposure positions through the conversion rate prediction model, and obtain how many exposure positions the commodity needs to rise to obtain the order volume of A + B.

[0087] In this way, the intelligent terminal can obtain a regulation plan for the regulation requirement of the target commodity, that is, the adjustment plan for the exposure position in different time windows. Furthermore, the regulation requirement of the target commodity can be accurately regulated.

[0088] Step 103: Perform secondary sorting on the initial commodity list based on the regulation plan to obtain a regulated commodity list.

[0089] In implementation, referring to Figure 2 , after the intelligent terminal generates a regulation plan through the order prediction model and the conversion rate prediction model, it can implement the regulation plan for the target commodity. It should be noted that due to different time windows, the regulation plan can include one or more regulations of the exposure position, so that the total order increment obtained by the target commodity in one or more time windows reaches the increment required in the regulation requirement. For example, the regulation requirement of the target commodity involves three time windows, namely time window 1, 2, and 3. The regulation requirement of the target commodity is an order increment A. In time window 1, the target commodity needs to be adjusted to the 4th position; in time window 2, the target commodity needs to be adjusted to the 6th position; in time window 3, the target commodity needs to be adjusted to the 7th position. When the order increments of a, b, and c are reached in the three time windows respectively, then when A = a + b + c, the regulation requirement is met.

[0090] In this way, the intelligent terminal uses the order prediction model and conversion rate prediction model obtained through training on product-related data to assist the intelligent terminal in generating a regulation plan, and guides the product to adjust the exposure position, so that the intelligent terminal obtains a regulated product list after traffic regulation. When the user enters a specified search request, the intelligent terminal returns the regulated product list to the user, thus fulfilling the regulation requirements for the target product.

[0091] In one embodiment, the adjustment plan involving multiple exposure position adjustments spans multiple time windows, which may lead to inaccurate predictions and thus reduce the accuracy of traffic regulation. Therefore, correspondingly, after step 103, the following processing can be performed: periodically obtain the actual order data of the product according to a preset time window, and obtain the regulation deviation data based on the actual order data of the target product and the regulation requirements; obtain a regulation compensation plan based on the regulation deviation data.

[0092] In implementation, the intelligent terminal can obtain the actual order data Xi within the current time window and the difference ΔXi between the target order and the actual order of the previous day, and set an initial control coefficient Ɑi. Through the above data, the updated value Ɑ of the control coefficient within each time window can be calculated, and the formula is as follows:

[0093] Ɑ = Ɑi * (Xi + ΔXi) / Xi;

[0094] In this way, the intelligent terminal can update the updated value of the control coefficient in the next time window, and the intelligent terminal can update the regulation plan according to the updated value to achieve the regulation requirements.

[0095] Based on the same technical concept, the embodiment of the present invention also provides a traffic regulation system. Refer to Figure 3 , the system includes:

[0096] An initial sorting module 1, configured to obtain a search request of a user, and obtain an initial product list based on the search request. The initial product list sorts products according to a preset sorting rule;

[0097] A regulation plan module 2, configured to obtain the regulation requirements of a target product, and obtain a regulation plan of the target product under the search request based on the regulation requirements;

[0098] A regulation output module 3, configured to perform secondary sorting on the initial product list based on the regulation plan to obtain a regulated product list.

[0099] Optionally, the system further includes:

[0100] An order prediction model module, configured to obtain the historical order data of the target product, and obtain an order prediction model based on the historical order data;

[0101] A conversion rate data module for obtaining the exposure and order placement data of the target product, where the exposure and order placement data at least includes the historical exposure positions of the target product and the order conversion data corresponding to the historical exposure positions;

[0102] A conversion rate prediction model module for generating a conversion rate prediction model based on the exposure and order placement data.

[0103] Optionally, the order prediction model module includes:

[0104] A supplementary feature sub-module for obtaining the historical order data of the target product and at least one supplementary reference feature, where the supplementary reference feature at least includes holiday features and product quality;

[0105] A model generation sub-module for obtaining an order prediction model based on the historical order data and the supplementary reference features.

[0106] Optionally, the regulation scheme module 2 includes:

[0107] A demand acquisition module for obtaining the regulation demand of the target product;

[0108] A scheme generation module for obtaining a regulation scheme that meets the regulation demand based on the order prediction model and the conversion rate prediction model; the regulation scheme is used to perform sorting adjustment on the product list output under the same search request for the target product.

[0109] Optionally, the conversion rate prediction model module includes:

[0110] A data fitting sub-module for fitting the exposure and order placement data to obtain a fitting exponential curve of the exposure and order placement data if the sample size of the exposure and order placement data of the target product is lower than a preset sample threshold;

[0111] A data filling sub-module for obtaining simulated conversion data corresponding to the exposure positions lacking exposure and order placement data based on the fitting exponential curve.

[0112] Optionally, after the regulation output module 3, there is further included:

[0113] An actual data acquisition module for periodically acquiring the actual order placement data of the product according to a preset time window;

[0114] A deviation acquisition module for obtaining regulation deviation data based on the actual order placement data of the target product and the regulation demand;

[0115] A regulation compensation module for obtaining a regulation compensation scheme based on the regulation deviation data.

[0116] This application embodiment also discloses an intelligent terminal, refer to Figure 4, the intelligent terminal includes a memory and a processor, and a computer program capable of being loaded and executed by the processor, such as the above-mentioned traffic regulation method, is stored on the memory.

[0117] Based on the same technical concept, the embodiment of the present application also discloses a computer-readable storage medium, including various steps in the above-mentioned traffic regulation method process that can be implemented when loaded and executed by a processor.

[0118] The computer-readable storage medium includes, for example: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0119] Those skilled in the art can clearly understand that for the convenience and simplification of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working processes of the above-described system, device, and unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0120] The above-described embodiments are only used to introduce the technical solutions of the present application in detail. However, the description of the above embodiments is only for helping to understand the method and its core idea of the present application and should not be construed as a limitation of the present application. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered within the protection scope of the present application.

Claims

1. A flow regulation method, characterized in that, The method includes the following steps: Obtain the user's search request, and obtain an initial product list based on the search request. The initial product list sorts products according to a preset sorting rule; Obtain the regulation requirements of the target product, and obtain a regulation plan for the target product under the search request based on the regulation requirements; Perform a secondary sorting on the initial product list based on the regulation plan to obtain a regulated product list; Before obtaining the regulation requirements of the target product and obtaining a regulation plan for the target product under the search request based on the regulation requirements, it further includes: obtaining the historical order data of the target product, and obtaining an order prediction model based on the historical order data; obtaining the exposure and order conversion data of the target product, where the exposure and order conversion data at least includes the historical exposure positions of the target product and the order conversion data corresponding to the historical exposure positions; generating a conversion rate prediction model based on the exposure and order conversion data; The obtaining the historical order data of the target product and obtaining an order prediction model based on the historical order data includes: obtaining the historical order data of the target product and at least one supplementary reference feature, where the supplementary reference feature at least includes holiday features and product quality; obtaining an order prediction model based on the historical order data and the supplementary reference features; The obtaining the regulation requirements of the target product and obtaining a regulation plan for the target product under the search request based on the regulation requirements includes: obtaining the regulation requirements of the target product; obtaining a regulation plan that meets the regulation requirements based on the order prediction model and the conversion rate prediction model; the regulation plan is used to perform sorting adjustment on the product list output under the same search request for the target product; Before generating a conversion rate prediction model based on the exposure and order conversion data, it further includes: if the sample size of the exposure and order conversion data of the target product is lower than a preset sample threshold, then fit the exposure and order conversion data to obtain a fitted exponential curve of the exposure and order conversion data; obtaining simulated conversion data corresponding to the exposure positions lacking exposure and order conversion data based on the fitted exponential curve; After performing a secondary sorting on the initial product list based on the regulation plan to obtain a regulated product list, it further includes: obtaining the actual order conversion data Xi within the current time window and the difference ΔXi between the target order and the actual order of the previous day, and setting an initial control coefficient αi, and calculating the updated value of the control coefficient within each time window according to the following formula: α = αi * (Xi + ΔXi) / Xi.

2. The flow rate regulation method according to claim 1, characterized in that: The obtaining the regulation requirements of the target product and obtaining a regulation plan for the target product under the search request based on the regulation requirements includes: Obtaining the regulation requirements of the target product; Obtaining a regulation plan that meets the regulation requirements based on the order prediction model and the conversion rate prediction model; The regulation plan is used to perform sorting adjustment on the product list output under the same search request for the target product.

3. The flow rate control method according to claim 1, characterized in that: After performing a secondary sorting on the initial product list based on the regulation plan to obtain a regulated product list, it further includes: Periodically obtaining the actual order conversion data of the product according to a preset time window.

4. A flow regulation method according to claim 3, characterized in that: After periodically obtaining the actual order conversion data of the target product according to a preset time window, it further includes: Obtain the regulation deviation data based on the actual order completion data and regulation requirements of the target commodity; Obtain the regulation compensation plan based on the regulation deviation data.

5. A flow regulation system, characterized in that, The system includes: An initial sorting module (1) for obtaining a user's search request and obtaining an initial commodity list based on the search request, where the initial commodity list sorts commodities based on a preset sorting rule; A regulation plan module (2) for obtaining the regulation requirements of the target commodity and obtaining a regulation plan for the target commodity under the search request based on the regulation requirements; A regulation output module (3) for performing a secondary sort on the initial commodity list based on the regulation plan to obtain a regulated commodity list; Before obtaining the regulation requirements of the target commodity and obtaining a regulation plan for the target commodity under the search request based on the regulation requirements, it further includes: obtaining the historical order data of the target commodity and obtaining an order prediction model based on the historical order data; obtaining the exposure order completion data of the target commodity, where the exposure order completion data at least includes the historical exposure positions of the target commodity and the order conversion data corresponding to the historical exposure positions; generating a conversion rate prediction model based on the exposure order completion data; The obtaining the historical order data of the target commodity and obtaining an order prediction model based on the historical order data includes: obtaining the historical order data of the target commodity and at least one supplementary reference feature, where the supplementary reference feature at least includes holiday features and commodity quality; obtaining an order prediction model based on the historical order data and the supplementary reference features; The obtaining the regulation requirements of the target commodity and obtaining a regulation plan for the target commodity under the search request based on the regulation requirements includes: obtaining the regulation requirements of the target commodity; obtaining a regulation plan that meets the regulation requirements based on the order prediction model and the conversion rate prediction model; the regulation plan is used to perform sorting adjustment on the commodity list output under the same search request for the target commodity; Before generating a conversion rate prediction model based on the exposure order completion data, it further includes: if the sample size of the exposure order completion data of the target commodity is lower than a preset sample threshold, fitting the exposure order completion data to obtain a fitting exponential curve of the exposure order completion data; obtaining simulated conversion data corresponding to the exposure positions lacking exposure order completion data based on the fitting exponential curve; After performing a secondary sort on the initial commodity list based on the regulation plan to obtain a regulated commodity list, it further includes: obtaining the actual order completion data Xi within the current time window and the difference ΔXi between the target order and the actual order on the previous day, and setting an initial control coefficient αi, and calculating the updated value of the control coefficient within each time window according to the following formula: α = αi * (Xi + ΔXi) / Xi.

6. An intelligent terminal, characterized in that, The intelligent terminal includes a processor and a memory, and at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement a traffic regulation method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement a traffic control method as described in any one of claims 1 to 4.

Images