A method and system for determining placement points based on user click information

Abstract

The present application discloses a method and system for determining placement points based on user click information. The method includes: obtaining historical user click information at at least two candidate placement points in a display page, and determining click data and conversion data at each candidate placement point based on the historical user click information; obtaining target placement information of a commodity, and assigning click weights to the click data and conversion weights to the conversion data based on the target placement information; calculating placement effectiveness values of each candidate placement point based on the click weights, click data, conversion weights and conversion data, and sorting the placement effectiveness values to obtain the placement priorities of each candidate placement point; and determining a target placement point among the candidate placement points based on the placement priorities. Through this technical solution, the efficiency of determining placement points and the accuracy of the determination result can be improved, ensuring the placement benefits of merchants.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and particularly relates to a method and system for determining placement positions based on user click information. Background Art

[0002] With the diversification of commodity sales forms, online sales have gradually become the key sales form. During the online sales process, the placement positions of commodities on the display page of the sales platform are factors that merchants need to focus on when hanging commodities on the online platform. By placing commodities at different positions on the display page of the sales platform, the order and degree of customer attention to the commodities are different, and thus there are also differences in the click-through rate and conversion rate of the commodities. Merchants need to reasonably place the commodities at the optimal positions to obtain the maximum commodity sales revenue.

[0003] In the prior art, the method for determining the placement positions of commodities is often that merchants determine the optimal placement positions of the commodities to be sold on the display page of the sales platform according to their personal browsing habits or personal experience, or place the commodities at the positions corresponding to the page module identifiers on the display page of the sales platform. However, the prior art can only determine the placement positions based on merchants' experience, and cannot perform placements in combination with the actual click and conversion situations of each placement position. The placement results lack rationality and accuracy. Merchants cannot ensure the revenue brought by the placement positions, and a large amount of time for judging placement positions is required during the placement process, resulting in the problem of low efficiency in determining placement positions. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method and system for determining placement positions based on user click information, which solves the problems of low efficiency and inaccurate determination results in the prior art. By assigning corresponding weights to the historical user click data and conversion data of candidate placement positions based on the target placement information of the commodity, performing data processing on the weights and data to obtain the placement priorities of each candidate placement position, and determining the target placement position based on the placement priorities, the purpose of determining the final placement position based on the click information of users on each placement position can be achieved. There is no need for merchants to spend time judging positions, which improves the efficiency of determining placement positions and the accuracy of determination results, and ensures the placement benefits of merchants.

[0005] In a first aspect, the embodiments of this application provide a method for determining placement positions based on user click information, and the method includes:

[0006] Obtain the historical user click information at at least two candidate placement positions on the display page, and determine the click data and conversion data at each candidate placement position based on the historical user click information;

[0007] Obtain the target placement information of the product, allocate click weights to click data based on the target placement information, and allocate conversion weights to conversion data;

[0008] Calculate the placement effect values of each candidate placement point based on the click weights, click data, conversion weights, and conversion data, and sort the placement effect values to obtain the placement priorities of each candidate placement point;

[0009] Determine the target placement point among the candidate placement points based on the placement priorities.

[0010] Optionally, before determining the target placement point among the candidate placement points based on the placement priorities, the method further includes:

[0011] Obtain the placement unit price and product unit price at each candidate placement point respectively, calculate the placement cost based on the placement unit price and click data, and estimate the placement revenue based on the product unit price and conversion data;

[0012] Calculate the placement profit values of each candidate placement point based on the placement cost and placement revenue;

[0013] Update the placement priorities based on the placement profit values, and determine the target placement point among the candidate placement points based on the updated result of the placement priorities.

[0014] Optionally, determining the target placement point among the candidate placement points based on the placement priorities includes:

[0015] Obtain the occupancy status of the first candidate placement point based on the updated result of the placement priorities, and identify whether the occupancy status is an occupied status. The first candidate placement point is the candidate placement point corresponding to the first placement priority in the updated result of the placement priorities;

[0016] In the case where the occupancy status is an occupied status, poll the occupancy status of the second candidate placement point in the next placement priority until a candidate placement point in an unoccupied status is polled;

[0017] Use the candidate placement point in the unoccupied status as the target placement point.

[0018] Optionally, the historical user click information further includes: user add-to-cart information;

[0019] Correspondingly, before using the candidate placement point in the unoccupied status as the target placement point, the method further includes:

[0020] Identify multiple candidate placement points to be occupied with the same placement priority in the unoccupied status;

[0021] Determine the add-to-cart data of each candidate placement point based on the user add-to-cart information, and update the conversion weights of the multiple candidate placement points to be occupied respectively based on the add-to-cart data;

[0022] Update the click weight of the corresponding candidate placement points to be occupied based on the conversion weight update result, and recalculate the placement effect values of multiple candidate placement points to be occupied based on the conversion weight update result, conversion data, click weight update result, and click data;

[0023] Sort the recalculation results of the placement effect values to obtain the add-to-cart priorities of multiple candidate placement points to be occupied under the same placement priority, and determine the target placement points among multiple candidate placement points to be occupied based on the add-to-cart priorities.

[0024] Optionally, before obtaining the target placement information of the commodity, the method further includes:

[0025] Obtain the commodity type of the commodity, where the commodity type includes whether the commodity is a newly launched type;

[0026] In the case where the commodity type is a newly launched type, use the high click-through rate of the commodity as the target placement information of the commodity.

[0027] Optionally, the target placement information includes: the association information between the placement time and the placement target;

[0028] Correspondingly, assigning click weights to click data and conversion weights to conversion data based on the target placement information includes:

[0029] Determine whether the placement target of the commodity in each target placement time period is a high click-through rate based on the association information between the placement time and the placement target;

[0030] In the case where the placement target of the commodity in each target placement time period is a high click-through rate, use the preset placement target ratio as the click weight of the click data, and calculate the conversion weight of the conversion data based on the click weight;

[0031] In the case where the placement target of the commodity in each target placement time period is not a high click-through rate, use the preset placement target ratio as the conversion weight of the conversion data, and calculate the click weight of the click data based on the conversion weight.

[0032] Optionally, determining the click data and conversion data at each candidate placement point based on historical user click information includes:

[0033] Determine multiple rounds of historical click data and multiple rounds of historical conversion data at the same candidate placement point within a preset duration based on historical user click information;

[0034] Calculate the average value of multiple rounds of historical click data at the same candidate placement point respectively to obtain the click data at each candidate placement point, and calculate the average value of multiple rounds of historical conversion data at the same candidate placement point respectively to obtain the conversion data at each candidate placement point.

[0035] In a second aspect, an embodiment of the present application provides a placement point determination system based on user click information. The system includes:

[0036] A data acquisition module, configured to acquire historical user click information at at least two candidate placement points in a display page, and determine click data and conversion data at each candidate placement point based on the historical user click information;

[0037] A weight assignment module, configured to acquire target placement information of a product, and assign a click weight to the click data and a conversion weight to the conversion data based on the target placement information;

[0038] A placement effect calculation module, configured to calculate a placement effect value of each candidate placement point based on the click weight, click data, conversion weight, and conversion data, and sort the placement effect values to obtain the placement priorities of each candidate placement point;

[0039] A placement point determination module, configured to determine a target placement point among the candidate placement points based on the placement priorities.

[0040] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the method in the first aspect are implemented.

[0041] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method in the first aspect are implemented.

[0042] In a fifth aspect, an embodiment of the present application further provides a computer program product, which includes a computer program. The computer program is stored in a computer-readable storage medium, and at least one processor of the device reads and executes the computer program, so that the device executes the method in the first aspect.

[0043] In an embodiment of the present application, historical user click information at at least two candidate placement points on a display page is obtained, and click data and conversion data at each candidate placement point are determined based on the historical user click information; target placement information of a product is obtained, a click weight is assigned to the click data based on the target placement information, and a conversion weight is assigned to the conversion data; a placement effect value of each candidate placement point is calculated based on the click weight, click data, conversion weight, and conversion data, and the placement effect values are sorted to obtain the placement priorities of each candidate placement point; a target placement point is determined from the candidate placement points based on the placement priorities. Through the above method for determining a placement point based on user click information, the problems of low efficiency in determining a placement point and inaccurate determination results in the prior art are solved. By assigning corresponding weights to the historical user click data and conversion data of the candidate placement points based on the target placement information of the product, and performing data processing on the weights and data to obtain the placement priorities of each candidate placement point, and determining the target placement point based on the placement priorities, the purpose of determining the final placement point based on the click information of the user on each placement point can be achieved, eliminating the need for merchants to spend time on point judgment, improving the efficiency of determining the placement point and the accuracy of the determination result, and ensuring the placement benefits of the merchants. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flowchart of a method for determining a placement point based on user click information provided by an embodiment of the present application;

[0045] Figure 2 is a display interface of the display page provided by the present application on a user terminal;

[0046] Figure 3 is a flowchart of updating the placement priorities of candidate placement points provided by an embodiment of the present application;

[0047] Figure 4 is a flowchart of determining a target placement point provided by an embodiment of the present application;

[0048] Figure 5 is a structural block diagram of a system for determining a placement point based on user click information provided by an embodiment of the present application;

[0049] Figure 6 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To make the objectives, technical solutions and advantages of this application clearer, the following provides a more detailed description of specific embodiments of this application with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. Additionally, it should be noted that for ease of description, only parts related to this application rather than all content are shown in the drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operations are completed, but it can also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0051] The following will clearly describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some but not all of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application belong to the scope of protection of this application.

[0052] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / ", generally represents an "or" relationship between the associated objects before and after.

[0053] First, the usage scenario of this solution can be a scenario of commodity sales or advertising placement based on an online platform, especially a scenario of placing commodity data at corresponding positions on the display page of the online platform to improve the commodity conversion rate. By respectively assigning corresponding weights to the historical user click data and conversion data of candidate placement points based on the target placement information of the commodity, performing data processing on the weights and data to obtain the placement priorities of each candidate placement point, and determining the target placement point based on the placement priorities, the purpose of determining the final placement point based on the click information of users on each placement point can be achieved. There is no need for merchants to spend time judging the placement points, which improves the determination efficiency of the placement points and the accuracy of the determination results, and ensures the placement benefits of merchants. Based on the above usage scenario, it can be understood that the execution entity of this solution can be a server.

[0054] The following will, in conjunction with the accompanying drawings, through specific embodiments and their application scenarios, elaborate in detail on a method and system for determining placement points based on user click information provided by the embodiments of the present application.

[0055] Figure 1 is a flowchart of a method for determining placement points based on user click information provided by the embodiments of the present application. As Figure 1 shown, it specifically includes the following steps:

[0056] S101, Obtain historical user click information at at least two candidate placement points on the display page, and determine the click data and conversion data at each candidate placement point based on the historical user click information.

[0057] Among them, the display page can be a plane for displaying product information shown on the user terminal screen. The product information includes images, texts, data, etc. for describing product features. The candidate placement points can be positions on the display page where product links can be placed to display products. The specific positions, quantities, and positional relationships between multiple candidate placement points can be pre-set by the administrators of the online purchase platform of the product, and can include the top position, middle position, and bottom position of the page.

[0058] Figure 2 is the display interface of the display page provided by the present application on the user terminal.

[0059] As Figure 2 shown, the display page includes multiple placement points, and the positional relationships, sizes, and display methods between the placement points are all pre-set by the product purchase platform. Merchants can place products in the placement points under the product category display page corresponding to the product on the display page, and can also place products in the placement points under the recommended page on the display page. Since the product exposure rates of different placement points are different, the click-through rates of different placement points are also different. And because users are accustomed to browsing some products before making a purchase, the product conversion rates at different placement points are also different. The placement costs at different placement points are related to the click-through rates and conversion rates that the placement points can bring to the products. Users can enter the product name or category through the search bar on the display page. After the user clicks the search button, after the system retrieves the products that meet the user's needs, the corresponding retrieved products are displayed on the display page according to the placement points purchased by the merchants for the user to select. Due to the limited size of the display screen of the user terminal, when the user does not browse satisfactory products within the display screen range, the user can continue to browse the products at the placement points at the bottom of the page by sliding the page.

[0060] Historical user click information may be data on various page operations of users on products at the same candidate placement points recorded by a product purchase platform. The historical user click information includes whether the user clicks on the product at the candidate placement point on the display page, the duration of stay after the click, and whether the user clicks on the payment button on the product details page after the click, etc. The click data may be the time and number of times the product link at the same candidate placement point is clicked and viewed by the user. The conversion data may be the time and number of times the user clicks on the payment button on the product details page at the same candidate placement point.

[0061] In one embodiment, the historical user click information at at least two candidate placement points on the display page before the current moment may be obtained by reading the stored data of the product purchase platform. According to whether the products at each candidate placement point in the historical user click information are clicked and viewed on the display page and the time records of the clicks and views, the click data at each candidate placement point is determined; according to whether the products at each candidate placement point in the historical user click information are clicked on the payment button on the product details page and the time records of the clicks on the payment button, the conversion data at each candidate placement point is determined.

[0062] In one embodiment, optionally, determining the click data and conversion data at each candidate placement point based on the historical user click information includes:

[0063] Determining multi-round historical click data and multi-round historical conversion data at the same candidate placement point within a preset duration based on the historical user click information;

[0064] Calculating the average value of the multi-round historical click data at the same candidate placement point respectively to obtain the click data at each candidate placement point, and calculating the average value of the multi-round historical conversion data at the same candidate placement point respectively to obtain the conversion data at each candidate placement point.

[0065] Among them, the multi-round historical click data may be the total number of times the products at the same candidate placement point are clicked and viewed by all users within a preset duration. The multi-round historical conversion data may be the total number of times the products at the same candidate placement point are purchased after being viewed by all users within a preset duration.

[0066] In one embodiment, based on the time points when the products at each candidate placement point in the historical user click information are clicked and viewed by users on the display page, the total number of times the products at the same candidate placement point are clicked and viewed by all users within a preset duration can be counted. Based on the time points when the products at each candidate placement point in the historical user click information are clicked on the payment button on the product details page, the total number of times the products at the same candidate placement point are purchased after being viewed by all users within a preset duration can be counted. By calculating the ratio of the total number of times all users click and view at the same candidate placement point to the preset duration, the average value of the multi-round historical click data at this candidate placement point can be calculated, and then by traversing all candidate placement points, the click data at each candidate placement point can be obtained. By calculating the ratio of the total number of times all users purchase after viewing at the same candidate placement point to the preset duration, the average value of the average value of the multi-round historical conversion data at this candidate placement point can be calculated, and then by traversing all candidate placement points, the conversion data at each candidate placement point can be obtained.

[0067] In this solution, by determining the multi-round historical click data and multi-round historical conversion data at the same candidate placement point within a preset duration, and respectively calculating the average value of the multi-round historical click data and the average value of the multi-round historical conversion data at the same candidate placement point, the click data and conversion data at each candidate placement point can be obtained, which can achieve the effect of determining the average level of the click and conversion of the placement point by the user by combining the overall characteristics of the same placement point being clicked by the user in multiple rounds, and is beneficial to the subsequent evaluation and judgment of the placement point.

[0068] S102. Obtain the target placement information of the product, assign click weights to the click data based on the target placement information, and assign conversion weights to the conversion data.

[0069] Among them, the target placement information may be the purpose of the product being placed on the display page. The target placement information may be input by the merchant or determined by the system of the product purchase platform according to the product characteristics. For example, if the product characteristic is a re-listed product, it can be determined that the product requires a high conversion rate. The target placement information may include the ratio of the click-through rate to the conversion rate that the merchant expects the placement point to achieve after the product is placed. The click weight may be the data of the importance degree that the product needs to be clicked by the user. The conversion weight may be the data of the importance degree that the product needs to be purchased after being clicked by the user.

[0070] In one embodiment, the target placement information of the product can be obtained by reading the placement purpose input by the merchant, and the ratio of the click-through rate to the conversion rate that the merchant expects the placement point to achieve in the target placement information can be determined. Then, according to the ratio of the click-through rate to the conversion rate, click weights are respectively assigned to the click data at each candidate placement point and conversion weights are assigned to the conversion data at each candidate placement point.

[0071] In one embodiment, optionally, before obtaining the target placement information of a product, the method further includes:

[0072] Obtain the product type of the product, where the product type includes whether the product is a newly launched type;

[0073] When the product type is the newly launched type, use the high click-through rate of the product as the target placement information of the product.

[0074] Among them, the product type can be information indicating whether the product is a new product. The product type can be input or selected by the merchant in the product purchase platform before placing the product. The newly launched type can be a product that the merchant has not listed or placed on the product purchase platform before the current moment.

[0075] In one embodiment, the product type selected by the merchant for the product can be obtained, and it can be determined whether the product is a newly launched type. When the product type is the newly launched type, it is determined that the product requires high exposure. At this time, the high click-through rate of the product is used as the target placement information of the product. This solution is the target placement information of the product determined by the system of the product purchase platform according to the product characteristics. There is a preset ratio in the system. When the high click-through rate of the product is used as the target placement information of the product, the high click-through rate can be used as the high proportion item in the preset ratio, and then the conversion rate can be used as the low proportion item in the preset ratio. Then, click weights are assigned to click data and conversion weights are assigned to conversion data according to the preset ratio and the corresponding proportion items.

[0076] In this solution, by obtaining the product type of the product to determine whether the product is a newly launched type, and when the product type is the newly launched type, using the high click-through rate of the product as the target placement information of the product, the purpose of determining the product placement target based on the product characteristics can be achieved, and the accuracy of determining the product placement position is improved.

[0077] In one embodiment, optionally, the target placement information includes: the association information between the placement time and the placement target;

[0078] Correspondingly, assigning click weights to click data and conversion weights to conversion data based on the target placement information includes:

[0079] Determine whether the placement target of the product in each target placement time period is a high click-through rate based on the association information between the placement time and the placement target;

[0080] When the placement target of the product in each target placement time period is a high click-through rate, use the preset placement target ratio as the click weight of the click data, and calculate the conversion weight of the conversion data based on the click weight;

[0081] When the placement goal of a product during each target placement time period is not high click-through rate, use the preset placement goal ratio as the conversion weight of the conversion data, and calculate the click weight of the click data based on the conversion weight.

[0082] Among them, the associated information between the placement time and the placement goal can represent the corresponding relationship between the time when the product is placed and the purpose of the product being placed. For example: If the product is a traffic package of an operator, then the period from June to September is the peak period for handling traffic packages. At this time, the associated information can be that the placement goal from June to September is high conversion rate, and the placement goal for other months is high click-through rate. The target placement time period can be the time period input by the merchant for product placement. The preset placement goal ratio can be the ratio preset for the placement purpose of the product. For example: If the placement purpose of the product is high click-through rate, then the preset placement goal ratio can be the ratio of the click-through rate that needs to be achieved after the product is placed to the sum of the click-through rate and the conversion rate.

[0083] In one embodiment, it is possible to determine whether the placement goal corresponding to the product in each target placement time period is high click-through rate according to the associated information between the placement time and the placement goal. If the placement goal is high click-through rate, use the preset placement goal ratio as the click weight of the click data. Since the sum of the click weight and the conversion weight is equal to 1, the conversion weight of the conversion data can be calculated based on the click weight; if the placement goal is not high click-through rate, it means that the placement goal of the product in the target placement time period is high conversion rate. At this time, the preset placement goal ratio can be used as the conversion weight of the conversion data, and the click weight of the click data can be calculated based on the conversion weight.

[0084] In this solution, by associating the placement time with the placement goal, determining the placement goal according to the target placement time of the product, and using the preset placement goal ratio as the weight of the placement goal and calculating the weight of the remaining goal, the effect of flexibly allocating the click weight and the conversion weight based on the placement time can be achieved, further improving the rationality of the weight allocation.

[0085] S103, calculate the placement effect value of each candidate placement point based on the click weight, click data, conversion weight, and conversion data, and sort the placement effect values to obtain the placement priority of each candidate placement point.

[0086] Among them, the placement effect value can be the comprehensive evaluation data of the product being placed at the candidate placement point and being clicked and purchased by the user.

[0087] In one embodiment, the weighted sums of the click weights, click data, conversion weights, and conversion data corresponding to each candidate placement point can be calculated respectively, and the weighted sums are used as the placement effect values of each candidate placement point. Then, the placement effect values are sorted in descending order, and the sorting result is the placement priority of the product being placed at each candidate placement point.

[0088] S104. Determine the target placement point among the candidate placement points based on the placement priority.

[0089] Among them, the target placement point can be the candidate placement point where the product is finally placed.

[0090] In one embodiment, the candidate placement point with the highest priority can be determined as the target placement point among the candidate placement points according to the placement priority.

[0091] The technical solution provided by the embodiments of the present application obtains the historical user click information at at least two candidate placement points on the display page, determines the click data and conversion data at each candidate placement point based on the historical user click information; obtains the target placement information of the product, and assigns click weights to the click data and conversion weights to the conversion data based on the target placement information; calculates the placement effect values of each candidate placement point based on the click weights, click data, conversion weights, and conversion data, and sorts the placement effect values to obtain the placement priorities of each candidate placement point; determines the target placement point among the candidate placement points based on the placement priority. Through the above method for determining the placement point based on user click information, the problems of low efficiency and inaccurate determination results in the prior art are solved. By assigning corresponding weights to the historical user click data and conversion data of the candidate placement points based on the target placement information of the product, processing the weights and data to obtain the placement priorities of each candidate placement point, and determining the target placement point based on the placement priority, the purpose of determining the final placement point based on the user's click information on each placement point can be achieved, eliminating the need for merchants to spend time judging the placement points, improving the efficiency and accuracy of the determination of the placement points, and ensuring the placement benefits of the merchants.

[0092] Figure 3 It is a flowchart for updating the placement priorities of candidate placement points provided by the embodiments of the present application. As Figure 3 shown, it specifically includes the following steps:

[0093] S301. Obtain the placement unit price and product unit price at each candidate placement point respectively, calculate the placement cost based on the placement unit price and click data, and estimate the placement revenue based on the product unit price and conversion data.

[0094] Among them, the placement unit price includes the basic fee that a merchant needs to pay for placing a product at a certain candidate placement point and the click fee that the merchant needs to pay for each click of the product by a user. The product unit price can be the selling price of the product. The placement unit price is related to the position of the display page where the candidate placement point is located and is preset by the system-related personnel of the product purchase platform. The placement cost can be the total fee amount that a merchant needs to pay for placing a product at a certain candidate placement point. The estimated placement revenue can be the total fee amount that a merchant expects to receive for placing a product at a certain candidate placement point.

[0095] In one embodiment, the placement unit prices preset by the system at each candidate placement point and the product unit prices input by the merchant can be obtained respectively. The click-through rate at each candidate placement point can be calculated based on the click data at each candidate placement point, and the conversion rate at each candidate placement point can be calculated based on the conversion data at each candidate placement point. The placement cost is calculated based on the basic fee in the placement unit price and the product of the click fee and the click-through rate, and the estimated placement revenue for placing the product at each candidate placement point is calculated by calculating the product of the product unit price and the conversion rate.

[0096] S302. Calculate the placement profit value of each candidate placement point based on the placement cost and the placement revenue.

[0097] Among them, the placement profit value of each candidate placement point can be the profit value after removing the placement cost for placing the product at each candidate placement point.

[0098] In one embodiment, the placement profit value of each candidate placement point can be obtained by calculating the difference between the placement revenue and the placement cost for placing the product at each candidate placement point.

[0099] S303. Update the placement priority based on the placement profit value, so as to determine the target placement point among the candidate placement points based on the updated result of the placement priority.

[0100] In one embodiment, the placement priority can be updated according to the placement profit value, reducing the priority of the candidate placement points with lower placement profit values and increasing the priority of the candidate placement points with higher placement profit values. For example: sort the placement profit values of each candidate placement point according to the magnitude relationship, and adjust the placement priority order of each candidate placement point to the same order as the sorting result of the placement profit values. According to the updated result of the placement priority, determine the candidate placement point with the highest priority in the updated result as the target placement point.

[0101] The technical solution provided by the embodiments of the present application calculates the placement cost based on the placement unit price and point data, estimates the placement revenue based on the commodity unit price and conversion data, calculates the placement profit value of each candidate placement point, and then updates the placement priority. Based on the updated result of the placement priority, the target placement point among the candidate placement points is determined, which can achieve the purpose of automatically updating the target placement point in combination with the placement cost, and improve the efficiency of determining the target placement point and the comprehensiveness of evaluation.

[0102] Figure 4 is the flowchart for determining the target placement point provided by the embodiments of the present application. As Figure 4 shown, it specifically includes the following steps:

[0103] S401. Obtain the occupancy status of the first candidate placement point based on the updated result of the placement priority, and identify whether the occupancy status is an occupied status. The first candidate placement point is the candidate placement point corresponding to the first placement priority in the updated result of the placement priority.

[0104] Among them, the occupancy status may indicate whether there are other commodities that have been placed at the first candidate placement point at the current moment or at the target placement time of the commodity. The occupancy status includes whether the first candidate placement point is in an occupied status. The first placement priority may be the highest placement priority among the placement priorities corresponding to each candidate placement point.

[0105] In one embodiment, the first candidate placement point may be determined according to the candidate placement point corresponding to the first placement priority in the updated result of the placement priority, the occupancy status of the first candidate placement point is obtained, and it is identified whether the occupancy status is an occupied status.

[0106] S402. When the occupancy status is an occupied status, poll the occupancy status of the second candidate placement point in the next placement priority until a candidate placement point in an unoccupied status is polled.

[0107] Among them, the next placement priority may be the priority lower than the first placement priority and adjacent to the first placement priority in the placement priority. The second candidate placement point may be the candidate placement point corresponding to the above next placement priority.

[0108] In one embodiment, when the occupancy status is an occupied status, it means that the first candidate placement point cannot be placed continuously. Poll the occupancy status of the second candidate placement point in the next placement priority until a candidate placement point in an unoccupied status is polled.

[0109] S403. Use the candidate placement point in the unoccupied status as the target placement point.

[0110] In one embodiment, after polling for a candidate placement point in the unoccupied state, the candidate placement point in the unoccupied state can be used as the target placement point for the product.

[0111] In one embodiment, optionally, the historical user click information further includes: user add-to-cart information;

[0112] Correspondingly, before using the candidate placement point in the unoccupied state as the target placement point, the method further includes:

[0113] Identifying multiple candidate placement points to be occupied with the same placement priority in the unoccupied state;

[0114] Determining the add-to-cart data of each candidate placement point based on the user add-to-cart information, and respectively updating the conversion weights of the multiple candidate placement points to be occupied based on the add-to-cart data;

[0115] Updating the click weights of the corresponding candidate placement points to be occupied based on the updated results of the conversion weights, and recalculating the placement effect values of the multiple candidate placement points to be occupied based on the updated results of the conversion weights, conversion data, updated results of the click weights, and click data;

[0116] Sorting the recalculation results of the placement effect values to obtain the add-to-cart priorities of the multiple candidate placement points to be occupied under the same placement priority, and determining the target placement point among the multiple candidate placement points to be occupied based on the add-to-cart priorities.

[0117] Among them, the user add-to-cart information can be the operation of whether the user clicks the add-to-cart button on the product detail page and the time of clicking the add-to-cart button. The candidate placement points to be occupied can be candidate placement points with the same priority and in the unoccupied state. The add-to-cart data can be the number of times the user clicks the add-to-cart button on the product detail page. The add-to-cart priority can be the order in which the product is preferentially added to the cart among multiple candidate placement points to be occupied.

[0118] In one embodiment, after polling a candidate placement point in an unoccupied state, determine whether the occupied states of all candidate placement points at this priority are in the unoccupied state according to the priority of the candidate placement point, and use the multiple candidate placement points in the unoccupied state as candidate placement points to be occupied. Count the number of times the product is clicked on the add-to-cart button by the user at each candidate placement point according to the user's add-to-cart information, and obtain the number of times the product is added to the cart at each candidate placement point. Calculate the ratio of the number of times the product is added to the cart at each candidate placement point to be occupied to the number of times the product is added to the cart at all candidate placement points to be occupied, and update the conversion weights of the multiple candidate placement points to be occupied by calculating the product of this ratio and the original conversion weight of the corresponding candidate placement point to be occupied. Update the click weights of the corresponding candidate placement points to be occupied according to the updated conversion weight results, and calculate the weighted sum of the updated conversion weight results, conversion data, updated click weight results, and click data to obtain the recalculation results of the placement effect values of the multiple candidate placement points to be occupied. Sort the recalculation results of the placement effect values according to the magnitude relationship to obtain the add-to-cart priorities of the multiple candidate placement points to be occupied at the same placement priority, and determine the candidate placement point to be occupied with the highest add-to-cart priority as the target placement point.

[0119] In this solution, by determining the add-to-cart data of each candidate placement point based on the user's add-to-cart information, updating the conversion weights of the candidate placement points to be occupied based on the add-to-cart data, and then recalculating the placement effect values of the candidate placement points to be occupied to obtain the add-to-cart priorities and determine the target placement point among the multiple candidate placement points to be occupied, it is possible to achieve the purpose of determining the target placement point by combining the add-to-cart effects of each placement point, and improve the comprehensiveness of determining the target placement point.

[0120] The technical solution provided by the embodiment of the present application can avoid the problem of subsequent placement failure caused by the target placement point being occupied by identifying whether the occupied state of the candidate placement point is the occupied state and using the candidate placement point in the unoccupied state as the target placement point, and can automatically screen the target placement point, improving the accuracy of the placement result.

[0121] Figure 5 It is a structural block diagram of a placement point determination system based on user click information provided by an embodiment of the present application. As Figure 5 shown, it specifically includes the following:

[0122] The data acquisition module 501 is used to acquire the historical user click information at at least two candidate placement points on the display page, and determine the click data and conversion data at each candidate placement point based on the historical user click information;

[0123] The weight distribution module 502 is used to obtain the target placement information of the product, allocate click weights to click data and conversion weights to conversion data based on the target placement information;

[0124] The placement effect calculation module 503 is used to calculate the placement effect values of each candidate placement point based on the click weight, click data, conversion weight and conversion data, and sort the placement effect values to obtain the placement priorities of each candidate placement point;

[0125] The placement point determination module 504 is used to determine the target placement point among the candidate placement points based on the placement priority.

[0126] Optionally, the placement point determination module 504 is further used to:

[0127] Obtain the placement unit price and product unit price at each candidate placement point respectively, calculate the placement cost based on the placement unit price and click data, and estimate the placement revenue based on the product unit price and conversion data;

[0128] Calculate the placement profit values of each candidate placement point based on the placement cost and placement revenue;

[0129] Update the placement priority based on the placement profit value, and determine the target placement point among the candidate placement points based on the updated result of the placement priority.

[0130] Optionally, the placement point determination module 504 is specifically used to:

[0131] Obtain the occupancy status of the first candidate placement point based on the updated result of the placement priority, and identify whether the occupancy status is an occupied status. The first candidate placement point is the candidate placement point corresponding to the first placement priority in the updated result of the placement priority;

[0132] When the occupancy status is an occupied status, poll the occupancy status of the second candidate placement point in the next placement priority until a candidate placement point in an unoccupied status is polled;

[0133] Use the candidate placement point in the unoccupied status as the target placement point.

[0134] Optionally, the historical user click information further includes: user add-to-cart information;

[0135] Correspondingly, the placement point determination module 504 is further used to:

[0136] Identify multiple candidate placement points to be occupied with the same placement priority in the unoccupied status;

[0137] Determine the add-to-cart data of each candidate placement point based on the user add-to-cart information, and update the conversion weights of multiple candidate placement points to be occupied respectively based on the add-to-cart data;

[0138] Update the click weight corresponding to the candidate placement point to be occupied based on the conversion weight update result, and recalculate the placement effect values of multiple candidate placement points to be occupied based on the conversion weight update result, conversion data, click weight update result, and click data;

[0139] Sort the recalculation results of the placement effect values to obtain the add-to-cart priorities of multiple candidate placement points to be occupied under the same placement priority, and determine the target placement point among multiple candidate placement points to be occupied based on the add-to-cart priorities.

[0140] Optionally, the weight allocation module 502 is further configured to:

[0141] Obtain the product type of the product, where the product type includes whether the product is a newly launched type;

[0142] In the case where the product type is a newly launched type, use the high click-through rate of the product as the target placement information of the product.

[0143] Optionally, the target placement information includes: the associated information between the placement time and the placement target;

[0144] Correspondingly, the weight allocation module 502 is specifically configured to:

[0145] Determine whether the placement target of the product in each target placement time period is a high click-through rate based on the associated information between the placement time and the placement target;

[0146] In the case where the placement target of the product in each target placement time period is a high click-through rate, use the preset placement target ratio as the click weight of the click data, and calculate the conversion weight of the conversion data based on the click weight;

[0147] In the case where the placement target of the product in each target placement time period is not a high click-through rate, use the preset placement target ratio as the conversion weight of the conversion data, and calculate the click weight of the click data based on the conversion weight.

[0148] Optionally, the data acquisition module 501 is specifically configured to:

[0149] Determine the multi-round historical click data and multi-round historical conversion data at the same candidate placement point within a preset duration based on the historical user click information;

[0150] Calculate the average value of the multi-round historical click data at the same candidate placement point respectively to obtain the click data at each candidate placement point, and calculate the average value of the multi-round historical conversion data at the same candidate placement point respectively to obtain the conversion data at each candidate placement point.

[0151] For the technical solution provided by the embodiment of the present application, a data acquisition module is configured to acquire historical user click information at at least two candidate placement points on a display page, and determine click data and conversion data at each candidate placement point based on the historical user click information; a weight assignment module is configured to acquire target placement information of a product, and assign a click weight to the click data and a conversion weight to the conversion data based on the target placement information; a placement effect calculation module is configured to calculate a placement effect value of each candidate placement point based on the click weight, click data, conversion weight, and conversion data, and sort the placement effect values to obtain the placement priority of each candidate placement point; a placement point determination module is configured to determine a target placement point among the candidate placement points based on the placement priority. Through the above placement point determination system based on user click information, the problems of low efficiency and inaccurate determination results in the prior art are solved. By assigning corresponding weights to the historical user click data and conversion data of the candidate placement points based on the target placement information of the product, performing data processing on the weights and data to obtain the placement priority of each candidate placement point, and determining the target placement point based on the placement priority, the purpose of determining the final placement point based on the user's click information on each placement point can be achieved, eliminating the need for merchants to spend time on point judgment, improving the determination efficiency of the placement point and the accuracy of the determination result, and ensuring the placement benefit of the merchants.

[0152] A placement point determination system based on user click information in an embodiment of the present application can be configured in components, integrated circuits, or chips in a terminal. It can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiment of the present application does not make specific limitations.

[0153] A placement point determination system based on user click information in an embodiment of the present application can be an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems. The embodiment of the present application does not make specific limitations.

[0154] The placement point determination system based on user click information provided by the embodiments of the present application can implement each process implemented by the above method embodiments. To avoid repetition, it will not be described in detail here.

[0155] As Figure 6 shown, an electronic device 600 is further provided in an embodiment of the present application, including a processor 601, a memory 602, and a program or instruction stored on the memory 602 and executable on the processor 601. When the program or instruction is executed by the processor 601, it implements each process of the above method embodiment of the placement point determination method based on user click information, and can achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0156] It should be noted that the electronic device in the embodiments of the present application includes the above-mentioned mobile electronic device and non-mobile electronic device.

[0157] An embodiment of the present application further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above method embodiment of the placement point determination method based on user click information, and can achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0158] Among them, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disc, etc.

[0159] Another program product is provided in an embodiment of the present application, which includes program code. When the program product runs on a computer device, the program code is used to cause the computer device to execute the steps in the methods according to various exemplary embodiments of the present application described above in this specification. For example, the computer device can execute a placement point determination method recorded in an embodiment of the present application. The program product can be implemented by any combination of one or more readable media.

[0160] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or system comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or system comprising such element. In addition, it should be pointed out that the scope of the methods and systems in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0161] From the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0162] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

[0163] The above is only the preferred embodiment of the present application and the technical principles applied. The present application is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments and substitutions that can be made by those skilled in the art will not depart from the protection scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments. Without departing from the concept of the present application, more other equivalent embodiments may be included, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for determining a delivery point based on user click information, characterized in that: The method comprises: Acquire historical user click information of at least two candidate delivery points in the display page, and determine click data and conversion data of each of the candidate delivery points based on the historical user click information; Acquire target delivery information of the product, assign a click weight to the click data based on the target delivery information, and assign a conversion weight to the conversion data; Calculating the delivery effect value of each candidate delivery point based on the click weight, the click data, the conversion weight and the conversion data, and sorting the delivery effect values ​​to obtain the delivery priority of each candidate delivery point; Respectively obtaining the delivery unit price and the commodity unit price at each of the candidate delivery points, calculating the delivery cost based on the delivery unit price and the click data, estimating the delivery revenue based on the commodity unit price and the conversion data, calculating the delivery profit value of each of the candidate delivery points based on the delivery cost and the delivery revenue, and updating the delivery priority based on the delivery profit value; Determine a target delivery point among the candidate delivery points based on the delivery priority, including: acquiring the occupancy status of the first candidate delivery point based on the delivery priority update result, and identifying whether the occupancy status is an occupied state, the first candidate delivery point is the candidate delivery point corresponding to the first delivery priority in the delivery priority update result; when the occupancy status is the occupied state, poll the occupancy status of the second candidate delivery point in the next delivery priority until a candidate delivery point in an unoccupied state is polled; and use the candidate delivery point in the unoccupied state as the target delivery point.

2. The method for determining the delivery point based on user click information according to claim 1, characterized in that: The historical user click information also includes: user purchase information; Accordingly, before taking the candidate delivery point in the unoccupied state as the target delivery point, the method further includes: Identify multiple candidate delivery points to be occupied in the unoccupied state with the same delivery priority; Determining the additional purchase data of each of the candidate delivery points based on the additional purchase information of the user, and updating the conversion weights of the plurality of candidate delivery points to be occupied respectively based on the additional purchase data; Based on the conversion weight update result, the click weight of the corresponding candidate delivery point to be occupied is updated, and based on the conversion weight update result, the conversion data, the click weight update result and the click data, the delivery effect values ​​of the multiple candidate delivery points to be occupied are recalculated; The recalculated results of the delivery effect values ​​are sorted to obtain the purchase priority of the multiple candidate delivery points to be occupied under the same delivery priority, and the target delivery point among the multiple candidate delivery points to be occupied is determined based on the purchase priority.

3. The method for determining the delivery point based on user click information according to claim 1, characterized in that: Before obtaining the target delivery information of the commodity, the method further includes: Obtaining the product type of a product, wherein the product type includes whether the product is a newly launched type; In the case that the product type is a newly launched type, a high click rate of the product is used as the target delivery information of the product.

4. The method for determining the delivery point based on user click information according to claim 1, characterized in that: The target delivery information includes: the association information between the delivery time and the delivery target; Accordingly, allocating a click weight to the click data based on the target delivery information, and allocating a conversion weight to the conversion data, includes: Determining whether the delivery target of the product in each target delivery time period is a high click rate based on the association information between the delivery time and the delivery target; When the delivery target of the product in each target delivery time period is a high click rate, a preset delivery target ratio is used as a click weight of the click data, and a conversion weight of the conversion data is calculated based on the click weight; When the delivery target of the product in each target delivery time period is not a high click-through rate, the preset delivery target ratio is used as the conversion weight of the conversion data, and the click weight of the click data is calculated based on the conversion weight.

5. The method for determining the delivery point based on user click information according to claim 1, characterized in that: The step of determining the click data and conversion data at each of the candidate delivery locations based on the historical user click information includes: Determining multiple rounds of historical click data and multiple rounds of historical conversion data at the same candidate delivery point within a preset time period based on the historical user click information; The average values ​​of the multiple rounds of historical click data at the same candidate delivery point are calculated respectively to obtain the click data at each candidate delivery point, and the average values ​​of the multiple rounds of historical conversion data at the same candidate delivery point are calculated respectively to obtain the conversion data at each candidate delivery point.

6. A delivery point determination system based on user click information, characterized in that: The system comprises: A data acquisition module, used to acquire historical user click information of at least two candidate delivery points in the display page, and determine click data and conversion data of each candidate delivery point based on the historical user click information; A weight allocation module, used to obtain target delivery information of commodities, allocate click weights to the click data based on the target delivery information, and allocate conversion weights to the conversion data; A delivery effect calculation module, used to calculate the delivery effect value of each candidate delivery point based on the click weight, the click data, the conversion weight and the conversion data, and sort the delivery effect values ​​to obtain the delivery priority of each candidate delivery point; A delivery point determination module is used to respectively obtain the delivery unit price and the commodity unit price at each of the candidate delivery points, calculate the delivery cost based on the delivery unit price and the click data, and estimate the delivery income based on the commodity unit price and the conversion data, calculate the delivery profit value of each of the candidate delivery points based on the delivery cost and the delivery income, and update the delivery priority based on the delivery profit value; The delivery point determination module is also used to determine the target delivery point among the candidate delivery points based on the delivery priority, which includes: obtaining the occupancy status of the first candidate delivery point based on the delivery priority update result, and identifying whether the occupancy status is an occupied state, the first candidate delivery point is the candidate delivery point corresponding to the first delivery priority in the delivery priority update result; when the occupancy status is the occupied state, polling the occupancy status of the second candidate delivery point in the next delivery priority until a candidate delivery point in an unoccupied state is polled; and taking the candidate delivery point in the unoccupied state as the target delivery point.

7. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of a method for determining a delivery point based on user click information as described in any one of claims 1 to 5 are implemented.

8. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of a method for determining a delivery point based on user click information as described in any one of claims 1-5 are implemented.

Images