Data distribution method, apparatus, device, and medium

Abstract

Embodiments of the present application provide a data allocation method, device, equipment and medium. The method comprises: obtaining an expected display value of each to-be-displayed data according to first user feedback data of each to-be-displayed data; allocating a remaining proportion according to the expected display value of each to-be-displayed data to obtain an allocation proportion of each to-be-displayed data; obtaining a target proportion of each to-be-displayed data according to the allocation proportion of each to-be-displayed data and a preset proportion corresponding to each to-be-displayed data, the target proportion of each to-be-displayed data being greater than the corresponding preset proportion; and allocating data resources to each to-be-displayed data according to the target proportion of each to-be-displayed data. When displaying a plurality of to-be-displayed data, the data resources allocated to the to-be-displayed data are not accurate due to the timeliness of the to-be-displayed data.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a data distribution method, apparatus, device, and medium. Background Technology

[0002] With the rapid development of computer technology, a large number of user behaviors have emerged based on the internet, especially the increasing promotional activities for various products, services, e-commerce stores, and even physical stores. Currently, the promotion method for these businesses typically involves pre-promoting certain services to obtain user feedback, and then determining user acceptance of these products based on that feedback.

[0003] The inventors discovered through research that user browsing or feedback on various products, services, e-commerce stores, and even physical stores has a certain time sensitivity. For example, the feedback data for various products differs on weekdays and holidays, or during different commuting hours. This can lead to inaccurate calculations of product acceptance, meaning that the data resources allocated when promoting and displaying products online (such as traffic data or money allocated during promotion) are inaccurate, thus affecting the merchant's revenue. Summary of the Invention

[0004] In view of this, embodiments of this application propose a data allocation method, apparatus, and medium that can improve the accuracy of data allocation when promoting and showcasing products.

[0005] In a first aspect, embodiments of this application provide a data allocation method, the method comprising: obtaining preset ratios corresponding to multiple pieces of data to be displayed, remaining ratios of the multiple pieces of data to be displayed, and first user feedback data of each piece of data to be displayed obtained by displaying each piece of data to be displayed within a display period, wherein the sum of the preset ratios corresponding to each piece of data to be displayed and the sum of the remaining ratios of the multiple pieces of data to be displayed are not greater than 1; obtaining a display expectation value for each piece of data to be displayed based on the first user feedback data of each piece of data to be displayed; allocating the remaining ratios according to the display expectation values ​​of each piece of data to be displayed to obtain an allocation ratio for each piece of data to be displayed; obtaining a target ratio for each piece of data to be displayed based on the allocation ratios of each piece of data to be displayed and the preset ratios corresponding to each piece of data to be displayed, wherein the target ratio of the data to be displayed is greater than the corresponding preset ratio; and allocating data resources to each piece of data to be displayed based on the target ratios of each piece of data to be displayed.

[0006] Secondly, embodiments of this application provide a data allocation device, comprising: a data acquisition module, an expectation value acquisition module, an allocation ratio acquisition module, a target ratio acquisition module, and a data resource allocation module. The data acquisition module is used to acquire multiple data sets to be displayed, a preset ratio corresponding to each data set to be displayed, a remaining ratio of the multiple data sets to be displayed, and first user feedback data of each data set to be displayed obtained by displaying each data set to be displayed within a display period, wherein the sum of the preset ratios corresponding to each data set to be displayed and the sum of the remaining ratios of the multiple data sets to be displayed are not greater than 1; the expectation value acquisition module is used to obtain a display expectation value for each data set to be displayed based on the first user feedback data of each data set to be displayed; the allocation ratio acquisition module is used to allocate the remaining ratios according to the display expectation values ​​of each data set to be displayed to obtain an allocation ratio for each data set to be displayed; the target ratio acquisition module is used to obtain a target ratio for each data set to be displayed based on the allocation ratios of each data set to be displayed and the preset ratios corresponding to each data set to be displayed, wherein the target ratio of the data set to be displayed is greater than the corresponding preset ratio; and the data resource allocation module is used to allocate data resources to each data set to be displayed according to the target ratio of each data set to be displayed.

[0007] In one possible implementation, the device further includes a data display module and an expectation value update module. The data display module is used to display each piece of data to be displayed, which is allocated data resources according to the target ratio, in the next display cycle; the data acquisition module is further used to acquire second user feedback data of each piece of data to be displayed obtained by displaying each piece of data to be displayed in the next display cycle; the expectation value update module is used to update the display expectation value of each piece of data to be displayed based on the second user feedback data of each piece of data to be displayed.

[0008] In one possible implementation, the second user feedback data includes at least two types, and the expected value update module includes an adjustment value acquisition submodule and an update submodule. The adjustment value acquisition submodule is used to obtain the adjustment expected value of each piece of data to be displayed based on the second user feedback data of each piece of data to be displayed obtained in the next display cycle and the weight corresponding to each type of second user feedback data; the update submodule is used to sum the adjustment expected value of each piece of data to be displayed with the corresponding display expected value to obtain the updated display expected value.

[0009] In one possible implementation, the adjustment value acquisition submodule is further configured to select the data to be displayed with the largest display expectation value from each of the data to be displayed, as the target data to be displayed; take the second user feedback data corresponding to the target data to be displayed as the target user feedback data; for each data to be displayed obtained in the next display cycle, according to the second user feedback data of the same type and the target user feedback data, obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed, and perform a weighted summation of the adjustment values ​​of each type of second user feedback data of the data to be displayed to obtain the adjustment expectation value of the data to be displayed.

[0010] In one possible implementation, the adjustment value acquisition submodule is further configured to, for each piece of data to be displayed obtained in the next display cycle, calculate the difference between the second user feedback data of the same type and the target user feedback data to obtain the difference value corresponding to each type of second user feedback data of the data to be displayed; and compare the difference value corresponding to each type of second user feedback data of the data to be displayed with the corresponding target user feedback data to obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed.

[0011] In one possible implementation, the allocation ratio acquisition module includes a data acquisition submodule, an initial ratio acquisition submodule, and a ratio allocation submodule. The data acquisition submodule is used to acquire the target temperature coefficient of the Softmax algorithm and the maximum expected display value among the expected display values ​​of each of the data to be displayed. The initial ratio acquisition submodule is used to calculate the initial ratio of each of the data to be displayed using the Softmax algorithm based on the target temperature coefficient and the expected display value of each of the data to be displayed. The ratio allocation submodule is used to allocate the remaining ratios using the initial ratios of each of the data to be displayed to obtain the allocation ratio of each of the data to be displayed.

[0012] In one possible implementation, the data acquisition submodule is further configured to obtain the target temperature coefficient of the Softmax algorithm based on the maximum display expectation value among the display expectation values ​​of each of the data to be displayed and a preset correspondence relationship, wherein the preset correspondence relationship includes multiple preset temperature coefficients and a preset expectation value corresponding to each preset temperature coefficient.

[0013] In one possible implementation, the target ratio obtaining module is further configured to sum the preset greedy ratio, the allocation ratio corresponding to the target data to be displayed among the multiple display data, and the preset ratio to obtain the target ratio of the target data to be displayed, wherein the target data to be displayed is the data to be displayed with the largest allocation ratio among the data to be displayed, and the sum of the preset greedy ratio, the preset ratio corresponding to each of the data to be displayed, and the remaining ratio of the multiple data to be displayed is 1; and to sum the allocation ratio and preset ratio corresponding to each of the other data to be displayed among the multiple display data excluding the target data to be displayed to obtain the target ratio corresponding to each of the other data to be displayed.

[0014] In one possible implementation, the first user feedback data includes at least two types, and the expectation value acquisition module is further configured to perform a weighted summation of the first user feedback data of at least two types for each of the data to be displayed, to obtain the display expectation value of each of the data to be displayed.

[0015] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory; one or more programs are stored in the memory and configured to be executed by the processor to implement the above-described method.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, wherein the above-described method is executed when the program code is run by a processor.

[0017] Fifthly, embodiments of this application provide a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device retrieves the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method described above.

[0018] This application provides a data allocation method, apparatus, and medium. The method includes: acquiring preset ratios corresponding to multiple pieces of data to be displayed, remaining ratios of the multiple pieces of data to be displayed, and first user feedback data of each piece of data to be displayed obtained by displaying each piece of data to be displayed within a display period, wherein the sum of the preset ratios corresponding to each piece of data to be displayed and the sum of the remaining ratios of the multiple pieces of data to be displayed are not greater than 1; obtaining a display expectation value for each piece of data to be displayed based on the first user feedback data of each piece of data to be displayed; allocating the remaining ratios according to the display expectation values ​​of each piece of data to be displayed to obtain an allocation ratio for each piece of data to be displayed; obtaining a target ratio for each piece of data to be displayed based on the allocation ratios of each piece of data to be displayed and the preset ratios corresponding to each piece of data to be displayed, wherein the target ratio of the data to be displayed is greater than the corresponding preset ratio; and allocating data resources to each piece of data to be displayed based on the target ratios of each piece of data to be displayed. By employing the method of this application, when displaying multiple pieces of data, even if the expected display value of the data is low, certain data resources can still be allocated to it. This avoids the situation where user feedback data obtained during a single display cycle is inaccurate (e.g., due to the time-sensitive nature of the data), preventing subsequent reasonable allocation of data resources. This improves the rationality of data resource allocation, thereby increasing the revenue gained from displaying data based on the allocated data resources. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This paper illustrates an application scenario diagram of a data allocation method provided in an embodiment of this application. Figure 2 A flowchart illustrating a data allocation method provided in an embodiment of this application is shown; Figure 3 This illustration shows a schematic diagram of allocating data resources for data to be displayed, according to an embodiment of this application. Figure 4 It shows Figure 2 A flowchart illustrating step S1320; Figure 5 This paper illustrates another flowchart of a data allocation method provided in an embodiment of this application. Figure 6This illustration shows another schematic diagram of allocating data resources for data to be displayed, according to an embodiment of this application. Figure 7 This illustration shows a schematic diagram illustrating the relationship between expected value and allocation ratio provided in an embodiment of this application; Figure 8 This illustration shows an application diagram of a data allocation method provided in this application; Figure 9 This paper shows a connection block diagram of a data distribution device provided in an embodiment of this application; Figure 10 A structural block diagram of an electronic device for performing the methods of embodiments of this application is shown. Detailed Implementation

[0021] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0022] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0023] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0024] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0025] It should be noted that "multiple" as mentioned in this article refers to two or more.

[0026] Before proceeding with specific explanations, the terms used in this application are explained as follows: Data to be displayed: Data to be displayed can be various products, such as videos, images, articles, or goods, or services, shops, etc. Multiple pieces of data to be displayed can be of the same type, such as video data of different playback lengths extracted from the same video, video data from different videos, different shops selling the same product, or goods with different styles or appearances, etc.

[0027] User feedback data: User feedback data can be at least one of the following metrics: mean, percentage, or ratio, based on user feedback on the data to be displayed. For example, if multiple data sets to be displayed represent different products, user feedback data could include average number of views per user, average number of purchases per user, average number of favorites per user, and purchase rate; if multiple data sets to be displayed represent video data of different playback durations, user feedback data could include average viewing time per user, average number of clicks per user, and completion rate. It should be understood that the above examples are merely illustrative and the above descriptions should not be construed as limiting this solution.

[0028] Data resources: Data resources can be the resources needed to promote and display multiple pieces of data to be displayed, such as traffic resources, monetary funds, or human resources.

[0029] The following describes an exemplary application of the device provided in the embodiments of the present invention for performing the above-described data allocation method. The data allocation method provided in the embodiments of the present invention can be applied to, for example... Figure 1 In the server within the application environment shown.

[0030] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application, such as... Figure 1 As shown, this application scenario includes a terminal device 10 and a server 20 that communicates with the terminal device 10 via a network.

[0031] Terminal device 20 may be equipped with a client for displaying the data to be displayed, such as a browser client, instant messaging client, education client, social networking client, shopping client, and audio / video playback client.

[0032] The network can be a wide area network (WAN), a local area network (LAN), or a combination of both. Terminal device 10 can be a smartphone, smart TV, tablet, laptop, desktop computer, smart speaker, smartwatch, etc.

[0033] Server 10 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0034] If using such Figure 1 When allocating data between terminal devices 10 and server 20, there can be multiple terminal devices 10. The specific steps are as follows: After obtaining the data to be displayed, server 20 can send the data to each terminal device 10, allowing users to view the data on their terminal devices 10 and perform corresponding operations (such as clicking, saving, liking, commenting, purchasing, etc.) and receive feedback back to server 20. This yields the first user feedback data for each piece of data to be displayed, obtained by displaying the data within the display period. Figure 1 The image shows a diagram illustrating how users can perform actions such as saving, liking, or commenting on videos on their devices.

[0035] Server 20 can obtain the display expectation value of each data to be displayed based on the first user feedback data of each data to be displayed; allocate the remaining proportion according to the display expectation value of each data to be displayed to obtain the allocation proportion of each data to be displayed; obtain the target proportion of each data to be displayed based on the allocation proportion of each data to be displayed and the preset proportion corresponding to each data to be displayed, and the target proportion of the data to be displayed is greater than the corresponding preset proportion; allocate data resources to each data to be displayed according to the target proportion of each data to be displayed.

[0036] By employing the data allocation method described above, even when the expected display value of the data to be displayed is low, certain data resources can still be allocated to it after it has been displayed. This avoids situations where user feedback data obtained during a single display cycle is inaccurate (e.g., due to the time-sensitive nature of the data), preventing subsequent allocation of data resources to that data from being displayed inappropriately. This improves the rationality of data resource allocation, thereby increasing the benefits gained from displaying data based on the allocated data resources.

[0037] It should be understood that the above-described method steps can also be executed by only the terminal device 10 or only by the server 20. That is, the method steps described above are merely illustrative and are not intended to limit this solution.

[0038] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0039] Please see Figure 2 and Figure 3 , Figure 2 The illustration shows a data allocation method provided in an embodiment of this application. This method can be applied to an electronic device, which may be, for example, […]. Figure 1 In the scenario shown, the server or terminal device, when executing the data allocation method, specifically performs steps S110 to S150: Step S110: Obtain the preset ratios corresponding to multiple data to be displayed, the remaining ratios of multiple data to be displayed, and the first user feedback data of each data to be displayed obtained by displaying each data to be displayed within the display period.

[0040] Among them, the sum of the preset proportions corresponding to each piece of data to be displayed and the sum of the remaining proportions of multiple pieces of data to be displayed shall not exceed 1.

[0041] Multiple data to be displayed can be multiple different texts, multiple different videos, multiple different images, multiple different products, multiple different service items, or multiple different stores (such as online stores), etc.

[0042] The display period can be one hour, one day, two days, one week, two weeks, or one month, depending on the type of data to be displayed and the actual needs.

[0043] The preset ratios for each piece of data to be displayed can be the same or different. That is, when displaying each piece of data within a display week, the resources allocated to each piece of data to be displayed (such as one or more data resources such as traffic resources, human resources, and the amount of money required for display) can be the same or different.

[0044] When the preset ratios for each piece of data to be displayed are different, a certain ratio can be randomly assigned to each piece of data as its preset ratio. Alternatively, a certain ratio can be assigned based on the file size of the data to be displayed, the data usage required for viewing, or the viewing time. The settings can be adjusted according to actual needs; no specific limitations are made here. It should be understood that when different data resources are allocated to each piece of data to be displayed, the corresponding exposure rate and number of exposures may differ. That is, each piece of data to be displayed will be shown to a different number of users.

[0045] When the preset ratios corresponding to each piece of data to be displayed are the same, that is, when the data resources allocated to each piece of data to be displayed are the same, the exposure rate or number of exposures corresponding to each piece of data to be displayed can tend to be the same. Correspondingly, the number of users corresponding to each piece of data to be displayed usually tends to be the same when it is displayed.

[0046] To ensure more accurate user feedback data for each piece of data to be displayed during the display period, in one possible implementation of this application, the same data resources are allocated to each piece of data when it is displayed during the display period. That is, by allocating the same data resources to each piece of data, displaying each piece of data during the display period will yield the first user feedback data for each piece of data.

[0047] For example, at least one of the following is the same: the traffic data, human resources, or amount of money allocated to each piece of data to be displayed, so that each piece of data to be displayed has the same or similar exposure rate, and the number of users who see each piece of data to be displayed is the same or similar.

[0048] The type of the first user feedback data to be displayed can be one or more (at least two).

[0049] If the data to be displayed is text, the first user feedback data may include one or more types of data such as average number of views per person, average browsing time per person, and average completion rate per person. If the data to be displayed is video, the first user feedback data may include one or more types of data such as average number of plays per person, average viewing time per person, average completion rate per person, and average collection rate per person. If the data to be displayed is image, the first user feedback data may include one or more types of data such as average number of views per person, average number of downloads per person, and average number of collections per person. If the data to be displayed consists of multiple different products, the first user feedback data may include one or more types of data such as average number of views per person, average number of purchases per person, and average number of collections per person. If the data to be displayed is a store, the first user feedback data may include one or more types of data such as average number of store visits per person, average number of store collections per person, or average number of purchases per person. It should be understood that the above types of user feedback data are only illustrative, and the types of user feedback data will vary depending on the category of the data to be displayed.

[0050] Step S120: Based on the first user feedback data for each piece of data to be displayed, obtain the expected display value for each piece of data to be displayed.

[0051] It should be noted that the expected value of the data to be displayed can be used to represent the revenue that merchants or users who need to display the data can obtain based on the data. The higher the expected value, the higher the revenue obtained. Correspondingly, the lower the expected value, the lower the revenue obtained.

[0052] The type of the first user feedback data for each piece of data to be displayed can be one or more.

[0053] When there are multiple types of first user feedback data to be displayed, the display expectation value corresponding to the first user feedback data to be displayed can be found in the preset correspondence table between user feedback data and expected value as the display expectation value of the data to be displayed.

[0054] When there are multiple types of first user feedback data to be displayed (at least two), the first user feedback data of at least two types for each data to be displayed can be weighted and summed to obtain the display expectation value of each data to be displayed.

[0055] In this approach, the display expectation value corresponding to each type of first user feedback data of the data to be displayed can be found from the pre-set correspondence table between user feedback data and expected values. The display expectation values ​​corresponding to each type of first user display data of the data to be displayed are then weighted and summed to obtain the display expectation value of the data to be displayed.

[0056] Step S130: Allocate the remaining proportions according to the expected display values ​​of each data to be displayed, and obtain the allocation proportions of each data to be displayed.

[0057] It should be understood that the higher the expected display value of each piece of data to be displayed, the higher the allocation ratio obtained by allocating the remaining proportions.

[0058] In one possible implementation, step S130 may involve calculating the sum of the expected display values ​​of each piece of data to be displayed, and allocating the remaining proportion according to the proportion of the expected display value of each piece of data to the sum. For example, when the remaining proportion is 6 / 10, there are three pieces of data to be displayed, and the expected display values ​​of the three pieces of data are 2, 3, and 5 respectively, the proportions of the expected display values ​​of the three pieces of data to the sum are 2 / 10, 3 / 10, and 5 / 10 respectively. The allocation proportions of the remaining proportions for the three pieces of data to be displayed are 12 / 100, 18 / 100, and 30 / 100. That is, the allocation proportion corresponding to the expected display value of 2 is 12 / 100, the allocation proportion corresponding to the expected display value of 3 is 18 / 100, and the allocation proportion corresponding to the expected display value of 5 is 30 / 100.

[0059] In another possible implementation, step S130 above can also be to calculate the expected display value of each data to be displayed using one or more of the following algorithms: epsilon-Greedy algorithm, softmax algorithm, Upper Confidence Bound (UCB) algorithm, Exp3 algorithm, etc., to obtain the initial ratio of each data to be displayed, and to allocate the remaining ratio using the initial ratio of each data to be displayed to obtain the allocation ratio of each data to be displayed.

[0060] In this implementation, step S130 may specifically include the following steps: Step S132: Obtain the target temperature coefficient of the Softmax algorithm and the maximum expected display value among the expected display values ​​of each data to be displayed.

[0061] The target temperature coefficient of the Softmax algorithm can be a pre-set fixed value, or it can be determined based on the expected display value of each data to be displayed, such as the maximum or average value among the expected display values.

[0062] In one possible implementation of this application, the target temperature coefficient of the Softmax algorithm can be obtained by: obtaining the target temperature coefficient of the Softmax algorithm based on the maximum display expectation value among the display expectation values ​​of each data to be displayed and a preset correspondence, wherein the preset correspondence includes multiple preset temperature coefficients and a preset expectation value corresponding to each preset temperature coefficient.

[0063] For example, the preset correspondence stores multiple temperature coefficients and the expected value range corresponding to each preset temperature coefficient. The larger the average value of each preset expected value range, the larger the corresponding target temperature coefficient. This results in a more even distribution of the allocation ratio calculated using the Softmax algorithm based on the target temperature coefficient, and a more accurate calculated return.

[0064] The target temperature coefficient τ of the Softmax algorithm is used to adjust the spacing of the allocation ratios for each piece of data to be displayed. When τ approaches 0, the Softmax algorithm tends to utilize only (i.e., allocate a higher allocation ratio to the maximum display expectation value); when τ approaches infinity, the Softmax algorithm tends to explore only (i.e., allocate a higher allocation ratio to the minimum display expectation value). Specifically, the smaller τ is, the closer the allocation ratio of the data to be displayed corresponding to the maximum display expectation value is to the remaining ratio, and the smaller the allocation ratio corresponding to the display expectation values ​​of other data to be displayed. Conversely, the larger τ is, the more even the allocation ratios corresponding to the display expectation values ​​of each piece of data to be displayed become.

[0065] Step S134: Calculate the target temperature coefficient and the expected display value of each data to be displayed using the Softmax algorithm to obtain the initial ratio of each data to be displayed.

[0066] The sum of the initial proportions of the multiple data sets to be displayed is 1. If the number of data sets to be displayed is... If there are 1, then for each data point i to be displayed, the initial ratio of each data point i can be calculated using the following Softmax algorithm formula, where the Softmax algorithm formula is: ,in, The initial scale of data I to be displayed. The expected display value for data I to be displayed. Let I be the target temperature coefficient, where I ranges from 1 to N when the number of data points to be displayed is N. It should be understood that different data points to be displayed can also be distinguished by letters or symbols, such as data A, data B, and data C.

[0067] Step S136: Allocate the remaining proportions using the initial proportions of each data to be displayed to obtain the allocation proportions of each data to be displayed.

[0068] Specifically, step S136 can be performed by multiplying the initial ratio of each data point to be displayed by the remaining ratio to obtain the allocation ratio of each data point to be displayed. Alternatively, it can be performed by weighted summation of the initial ratio and the remaining ratio of each data point to be displayed to obtain the allocation ratio of each data point to be displayed.

[0069] Please refer to it again. Figure 4 For example, for any data I to be displayed, the initial ratio of the data I to be displayed can be... Multiply by the remaining proportion to obtain the allocation proportion of the data I to be displayed. That is, the allocation ratio of data 1 to be displayed is The allocation ratio of the data N to be displayed is .

[0070] By adopting the proportional allocation method in steps S132-S136, a more accurate allocation ratio can be assigned to each piece of data to be displayed, so as to allocate data resources more accurately in the subsequent allocation of data resources to the data to be displayed based on the allocation ratio.

[0071] Step S140: Obtain the target ratio of each data to be displayed based on the allocation ratio of each data to be displayed and the preset ratio corresponding to each data to be displayed.

[0072] The target proportion of the data to be displayed is greater than the corresponding preset proportion.

[0073] There are several ways to obtain the target proportion of each data to be displayed based on the allocation ratio of each data to be displayed and the preset ratio corresponding to each data to be displayed.

[0074] In one possible implementation, the target ratio of each piece of data to be displayed can be obtained by adding the allocation ratio of each piece of data to be displayed to the preset ratio of that piece of data.

[0075] In another possible implementation, the target ratio of each piece of data to be displayed can be obtained by weighted summing the allocation ratio of each piece of data to be displayed and the preset ratio of the data to be displayed.

[0076] In another possible implementation, the target ratio of the target data to be displayed can be obtained by summing the preset greedy ratio, the allocation ratio corresponding to the target data to be displayed among the multiple display data, and the preset ratio. The target data to be displayed is the data to be displayed with the largest allocation ratio among the data to be displayed, and the sum of the preset greedy ratio, the preset ratio corresponding to each data to be displayed, and the remaining ratio of the multiple data to be displayed is 1. The allocation ratio and preset ratio corresponding to each of the other data to be displayed among the multiple display data, excluding the target data to be displayed, can be summed to obtain the target ratio corresponding to each of the other data to be displayed.

[0077] Step S150: Allocate data resources to each piece of data to be displayed according to the target proportion of each piece of data to be displayed.

[0078] In this embodiment of the application, the target proportion of each piece of data to be displayed can be multiplied by the allocable data resources to obtain the data resources allocated to each piece of data to be displayed.

[0079] For example, if the data resource is traffic data and the allocable traffic data is M gigabytes of data traffic, then the target proportion of each data to be displayed can be multiplied by the M gigabytes of data traffic to obtain the corresponding allocated data traffic for each data to be displayed.

[0080] By employing the data allocation method described in this application, even when displaying multiple pieces of data with low expected display values, certain data resources can still be allocated to each piece of data. This avoids situations where user feedback data obtained during a single display cycle is inaccurate (e.g., due to the time-sensitive nature of the data), preventing subsequent allocation of data resources to that data. This improves the rationality of data resource allocation, thereby increasing the revenue gained from displaying data based on the allocated data resources.

[0081] Please see Figure 5 Another embodiment of this application provides a data allocation method applicable to electronic devices, the method comprising: Step S210: Obtain the preset ratios corresponding to multiple data to be displayed, the remaining ratios of multiple data to be displayed, and the first user feedback data of each data to be displayed obtained by displaying each data to be displayed within the display period.

[0082] The sum of the preset proportions corresponding to each piece of data to be displayed and the sum of the remaining proportions of multiple pieces of data to be displayed shall not exceed 1.

[0083] Step S220: Based on the first user feedback data for each piece of data to be displayed, obtain the expected display value for each piece of data to be displayed.

[0084] Step S230: Allocate the remaining proportions according to the expected display values ​​of each data to be displayed, and obtain the allocation proportions of each data to be displayed.

[0085] Step S240: Obtain the target ratio of each data to be displayed based on the allocation ratio of each data to be displayed and the preset ratio corresponding to each data to be displayed.

[0086] The target proportion of the data to be displayed is greater than the corresponding preset proportion.

[0087] Step S250: Allocate data resources to each piece of data to be displayed according to the target proportion of each piece of data to be displayed.

[0088] For a detailed description of steps S210-S250 above, please refer to the detailed description of steps S110-S150 in the foregoing embodiments. They will not be repeated in this embodiment.

[0089] Step S260: In the next display cycle, display each piece of data to be displayed, according to the data resources allocated according to the target ratio.

[0090] It should be noted that the display duration can be the same for different display cycles. After allocating data resources to the data to be displayed according to the proportion, since the data resources allocated to each piece of data to be displayed are different, the resulting number of exposures and exposure rate (the proportion seen by users) will be different, that is, the number of users displayed will be different.

[0091] Step S270: Obtain the second user feedback data for each data to be displayed, obtained from the display of each data in the next display cycle.

[0092] For a detailed description of step S270, please refer to the previous description of step S110.

[0093] It should be understood that the type of the second user feedback data for each data to be displayed in the next display cycle should be the same as the type of the first user feedback data.

[0094] For example, when the data to be displayed is text, and the first user feedback data includes three types of data: average number of views per person, average viewing time per person, and average viewing completion rate per person, then the second user feedback data also includes three types of data: average number of views per person, average viewing time per person, and average viewing completion rate per person. When the data to be displayed is video, and the first user feedback data includes four types of data: average number of plays per person, average viewing time per person, average playback completion rate per person, and average collection rate per person, then the second user feedback data also includes four types of data: average number of plays per person, average viewing time per person, average playback completion rate per person, and average collection rate per person.

[0095] Step S280: Based on the second user feedback data for each piece of data to be displayed, update the display expectation value for each piece of data to be displayed, and return to execute step S230.

[0096] After updating the expected display values ​​for each piece of data to be displayed, the system can count the number of times these values ​​are updated. Once a preset number of updates is reached, data resources can be allocated for widespread promotion and display of each piece of data based on the target proportion corresponding to the expected display value obtained from the last update. The preset number of updates can be 10, 20, 50, or 100, etc., and can be set according to actual needs; no specific limitation is made here.

[0097] There are several ways to update the display expectation value of each piece of data based on the second user feedback data.

[0098] In one possible implementation, the expected display value of each piece of data to be displayed can be obtained from the first user feedback data of each piece of data to be displayed, and used as the first expected value of each piece of data to be displayed; the second expected value of each piece of data to be displayed can be calculated using the second user feedback data of each piece of data to be displayed; and the result of the weighted calculation of the first expected value and the second expected value of each piece of data to be displayed can be used as the new first expected value. That is, the new first expected value is used as the updated expected display value of the data to be displayed.

[0099] In another possible implementation, the adjustment expectation value for each piece of data to be displayed can be obtained based on the second user feedback data for each piece of data to be displayed obtained in the next display cycle and the weight corresponding to each type of second user feedback data. The updated display expectation value is obtained by summing the adjustment expectation value of each piece of data to be displayed with the corresponding display expectation value.

[0100] In this implementation, the method for obtaining the adjustment expectation value of each piece of data to be displayed based on the second user feedback data of each piece of data to be displayed obtained in the next display cycle and the weight corresponding to each type of second user feedback data can be as follows: select a target piece of data to be displayed from multiple pieces of data to be displayed, take the second user feedback data corresponding to the target piece of data to be displayed as the target user feedback data, for each piece of data to be displayed obtained in the next display cycle, obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed based on the second user feedback data of the same type and the target user feedback data, and perform a weighted summation of the adjustment values ​​of each type of second user feedback data of the data to be displayed to obtain the adjustment expectation value of the data to be displayed.

[0101] In this implementation, the method for obtaining the adjustment expectation value of each piece of data to be displayed based on the second user feedback data of each piece of data to be displayed obtained in the next display cycle and the weight corresponding to each type of second user feedback data can be as follows: select the data to be displayed with the largest display expectation value from the data to be displayed as the target data to be displayed; take the second user feedback data corresponding to the target data to be displayed as the target user feedback data; for each piece of data to be displayed obtained in the next display cycle, obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed based on the second user feedback data of the same type and the target user feedback data; and perform a weighted summation of the adjustment values ​​of each type of second user feedback data of the data to be displayed to obtain the adjustment expectation value of the data to be displayed.

[0102] In the two implementation methods described above, the adjustment value for each type of data to be displayed can be obtained in the following way: for each type of data to be displayed obtained in the next display cycle, the difference between the second user feedback data of the same type and the target user feedback data is calculated to obtain the difference value corresponding to each type of second user feedback data of the data to be displayed; the difference value corresponding to each type of second user feedback data of the data to be displayed is compared with the corresponding target user feedback data to obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed.

[0103] For example, taking three data points A, B, and C to be displayed, the second user feedback data corresponding to each data point has three types: e, f, and g. The weight value corresponding to type e is w11, the weight value corresponding to type f is w22, and the weight value corresponding to type g is w33. The second user feedback data for data A to be displayed are a11, a22, and a33; the second user feedback data for data B to be displayed are b11, b22, and b33; and the second user feedback data for data C to be displayed are c11, c22, and c33. If the selected target data to be displayed is data A, then the expected adjustment value Q(A) corresponding to data A is: The expected adjustment value Q(B) corresponding to the data B to be displayed is: The expected adjustment value Q(C) corresponding to the data C to be displayed is: .

[0104] By updating the expected display value of each piece of data to be displayed using the adjustment expected value of each data point, and ensuring that each data point is allocated at least a preset proportion of data resources during the update process, even data points that initially perform very poorly will not have their data resources reduced to zero. After a period of experimentation, if a poorly performing data point improves due to the time effect, the proportion of data resources allocated to that data point will gradually increase. Ultimately, this ensures that the total benefit (total expected display value) of displaying all data points is maximized after a period of adjustment.

[0105] Furthermore, by adopting the above method, it is possible to dynamically adjust the data resources allocated to each piece of data to be displayed. It can also avoid the situation where the data resources allocated to each piece of data to be displayed are inaccurate due to the time when users view the data to be displayed, such as different times of weekdays and holidays, commuting hours, etc.

[0106] Please see Figure 6 Taking three video data sets (Video A, Video B, and Video C) with different playback durations as the data to be displayed, the preset ratios for each data set to be displayed are 0.1, the residual ratio is 0.4, and the preset greedy ratio is 0.3. The user feedback data obtained from displaying the data to be displayed is of three types (type e, type f, and type g), and each type of user feedback data is assigned a weight: the weight for type e is w11, the weight for type f is w22, and the weight for type g is w33. The first user feedback data for the three types of data to be displayed are a01, a02, and a03, respectively; the first user feedback data for the three types of data to be displayed are b01, b02, and b03, respectively; and the first user feedback data for the three types of data to be displayed are c01, c02, and c03, respectively, as an example, this will be explained.

[0107] When allocating data resources for the data to be displayed, the following steps are performed: For the data A to be displayed, the expected display value of the data A is calculated using the following formula. ,and =a01×w11+a02×w12+a03×w33, similarly, the expected display value of data B to be displayed. ,and =b01×w11+b02×w12+b03×w33, the expected display value of the data C to be displayed. ,and =c01×w11+c02×w12+c03×w33.

[0108] The target temperature coefficient of the Softmax algorithm is obtained by matching the maximum expected value among the expected values ​​of each data to be displayed with the preset correspondence.

[0109] Specifically, the preset correspondence includes multiple preset temperature coefficients and a preset expected value corresponding to each preset temperature coefficient.

[0110] For example, the preset correspondence includes multiple consecutive preset expected value ranges, each of which corresponds to a target temperature coefficient. The larger the mean of each preset expected value range, the larger the corresponding target temperature coefficient. This makes the distribution of the allocation ratio calculated using the Softmax algorithm based on the target temperature coefficient more uniform, and the calculated benefits more accurate.

[0111] The target temperature coefficient and the expected display values ​​of each piece of data to be displayed are calculated using the Softmax algorithm to obtain the initial proportions of each piece of data. The Softmax algorithm formula is as follows: ,in, This is the initial scale of data I to be displayed. The number of data to be displayed. The expected display value for data I to be displayed. is the target temperature coefficient. Here, the data to be displayed, I, can be data A, B, or C.

[0112] For any data I to be displayed, the allocation ratio of each data I to be displayed can be obtained by using the following formula. ,and .

[0113] The target ratio of the target data to be displayed is obtained by summing the preset greedy ratio, the allocation ratio of the target data to be displayed in multiple display data, and the preset ratio. The allocation ratio and preset ratio of each of the other data to be displayed in multiple display data, excluding the target data, are summed to obtain the target ratio of each of the other data to be displayed.

[0114] Among them, the target data to be displayed is the data with the largest proportion among all the data to be displayed.

[0115] It should be understood that when the allocation ratio is at its maximum, the corresponding expected value of the display is also at its maximum.

[0116] For example, if the allocation ratio of data A to be displayed is at its maximum, then the target ratio of data A to be displayed is... ,and .

[0117] When the allocation ratio of data A to be displayed is at its maximum, the corresponding allocation ratios of data B and data C to be displayed are at their minimum. Therefore, the target ratio for data B to be displayed is... ,and The target proportion of data B to be displayed is ,and .

[0118] Data resources are allocated to each piece of data to be displayed based on the target proportion of each piece of data. Specifically, when the total data resources are W, for any piece of data I to be displayed, the data resources W(I) allocated to the piece of data I can be obtained using the formula W(I) = W × P(I).

[0119] After allocating resources to each piece of data to be displayed, the data to be displayed, according to the target proportion, will be shown in the next display cycle. Second user feedback data for each piece of data to be displayed will be obtained from the display of each piece of data in the next display cycle.

[0120] Select the data with the highest expected display value from all the data to be displayed, and use it as the target data to be displayed. Use the second user feedback data corresponding to the target data to be displayed as the target user feedback data. For each data to be displayed obtained in the next display cycle, calculate the expected adjustment value for that data using the expected adjustment formula based on the second user feedback data and the target feedback data.

[0121] For any data I to be displayed, the expected adjustment value is calculated as follows: Where Q(I) is the expected adjustment value of the data to be displayed I, wjj is the weight of the j-th type of second user feedback data of the data to be displayed I, njj is the j-th type of second user feedback data of the data to be displayed I, and ajj is the j-th type of target user feedback data. Specifically, any data to be displayed I can be data A, data B, or data C.

[0122] Take any data I to be displayed, and combine its expected adjustment value Q(I) with its expected display value. Adding these together yields the updated expected display value. Then, the process returns to the previous steps of calculating the target temperature coefficient and the expected display value for each piece of data using the Softmax algorithm to obtain the initial proportions for each piece of data. Finally, data resources are allocated again for display in the next cycle.

[0123] like Figure 7The image shows how to display data (data A, data B, and data C) over a period of 10 minutes. Figure 8 As can be seen, the expected display value of data C to be displayed is the highest in the first 30 minutes, so the corresponding initial proportion is the largest, and the corresponding allocation proportion is also the largest. As the expected display value of the data to be displayed changes in each period, the initial proportion also changes accordingly, and the corresponding allocation proportion also changes accordingly. After 80 minutes, the expected display value of data B gradually surpasses that of data C, and it receives the largest initial proportion, at which point it also receives the largest allocation proportion.

[0124] By employing the above methods and steps, a minimum traffic (preset ratio) can be reserved for each piece of data to be displayed when allocating data resources. Even if the data to be displayed performs very poorly in the early stages, there is no need to worry about the allocated data resources dropping to zero. After displaying each piece of data for a period of time, if the poorly performing data to be displayed reverses due to the time effect, this solution will also increase the corresponding allocation ratio to increase the resources allocated to the data to be displayed. Ultimately, by observing the fluctuations in the data resources corresponding to each piece of data to be displayed, it is possible to understand whether the expected value (return) of displaying each piece of data has a time effect, while ensuring that the merchants or promoters obtain the maximum return on each piece of data during the display process.

[0125] Furthermore, by updating the display expectation value of each data to be displayed based on the second user feedback data obtained in the next display cycle, the data resources allocated to each data to be displayed can be dynamically adjusted. This can also effectively avoid the situation where the data traffic allocated to each data to be displayed is inaccurate due to the time effect of different feedback data generated by users viewing the data to be displayed at different times, such as different weekdays and holidays, commuting times, etc.

[0126] It should be noted that the data allocation methods in the above embodiments can be applied to electronic devices, such as terminal devices or servers. Specifically, when the above data allocation methods are applied to electronic devices, they can be implemented using a distributed scheduler. The distributed scheduler can be implemented using a Redis+Lua script based on the Golang language, or it can be implemented based on other distributed schedulers such as the TRPC framework, TAB framework, content open platform, or open-source task scheduling solutions (e.g., XXL-JOB, a lightweight distributed task scheduling platform).

[0127] like Figure 8 As shown, the above data allocation method is applied to the TAB framework as an example for illustration.

[0128] The TAB framework includes a business server, a TAB backend manager, a distributed timer scheduler, a timer scheduler consumer, a data warehouse, and a data dashboard. The timer scheduler consumer includes a data source timer scheduler and a primary timer scheduler.

[0129] The business server receives data such as preset greed ratios, preset ratios, remaining ratios, and display periods set by developers or merchants. It also receives user feedback data from user actions based on the data to be displayed and transmits this data to the TAB backend manager. The TAB backend manager creates multi-armed problem experiments based on the acquired data. The distributed scheduler, after the experiment is created, starts working by calling either the data source scheduler in the consumer or the first scheduler. When used by the distributed scheduler, the data source scheduler periodically acquires user data from the business server within a display period and stores this user feedback data in a data warehouse. The first scheduler, when used by the distributed scheduler, calculates the expected display value for each piece of data based on the user feedback data. It then calculates the allocation ratio for each piece of data based on the remaining ratio and the expected display value, ultimately obtaining the target ratio for each piece of data. The data panel displays the target ratio and allocation ratio for each piece of data.

[0130] Specifically, when using the aforementioned TAB framework to execute the data allocation method, the following process can be performed: After completing the creation of the issue of allocating traffic to multiple data to be displayed, use the TAB backend manager to create a scheduled task and send it to the scheduled task.

[0131] The distributed scheduler starts the data source scheduler in the consumer end based on the scheduled task to schedule the display of the data to be displayed within the display period. The user data obtained is then stored in the data warehouse. When the distributed scheduler starts the first scheduled scheduler in the consumer terminal based on the scheduled task, it can call the first user data in the data warehouse to calculate the expected display value of each data to be displayed, the target temperature coefficient of the Softmax algorithm, and allocate the remaining proportions based on the target temperature coefficient and the expected display value of each data to be displayed using the Softmax algorithm to obtain the allocation proportion of each data to be displayed. Based on the allocation proportion of each data to be displayed and the preset proportion corresponding to each data to be displayed, the target proportion of each data to be displayed is obtained, and data resources are allocated to each data to be displayed according to the target proportion. The data panel can display the allocation proportion and target proportion of each data to be displayed.

[0132] Subsequently, the distributed scheduler starts the data source scheduler in the consumer end of the scheduler based on the scheduled task, and displays the data to be displayed in the next display period according to the target ratio of the data resources to be displayed, and then stores the obtained second user feedback data in the data warehouse. So that when the first timer in the consumer terminal of the distributed scheduler starts based on the timed scheduling task, it can call the second user feedback data in the data warehouse again to calculate the updated display expectation value, and use the Softmax algorithm to allocate the remaining proportion based on the target temperature coefficient obtained for the first time and the updated display expectation value of each data to be displayed, so as to obtain the allocation proportion of each data to be displayed again; and obtain the target proportion of each data to be displayed according to the allocation proportion of each data to be displayed again and the preset proportion corresponding to each data to be displayed, and allocate data resources to each data to be displayed according to the target proportion of each data to be displayed.

[0133] By applying the data allocation method to the aforementioned TAB framework, parameters generated during the data allocation process, such as the target temperature coefficient, first user feedback data, second user feedback data, and data resources allocated in each display period, can be stored in the database of the TAB framework. This gives the entire TAB framework good memory, allowing users to review data from different display periods.

[0134] It should be noted that the device embodiments in this application correspond to the aforementioned method embodiments. The specific principles in the device embodiments can be found in the content of the aforementioned method embodiments, and will not be repeated here.

[0135] Figure 9 It is a data distribution device according to one embodiment, such as Figure 9 As shown, the data allocation device 400 includes: a data acquisition module 410, an expected value acquisition module 420, an allocation ratio acquisition module 430, a target ratio acquisition module 440, and a data resource allocation module 450.

[0136] The data acquisition module 410 is used to acquire multiple data to be displayed, a preset ratio corresponding to each data to be displayed, the remaining ratio of the multiple data to be displayed, and the first user feedback data of each data to be displayed obtained by displaying each data to be displayed within the display period. The sum of the preset ratios corresponding to each data to be displayed and the sum of the remaining ratios of the multiple data to be displayed are not greater than 1. The expected value acquisition module 420 is used to obtain the display expected value of each data to be displayed based on the first user feedback data of each data to be displayed. The allocation ratio acquisition module 430 is used to allocate the remaining ratios according to the display expected values ​​of each data to be displayed to obtain the allocation ratio of each data to be displayed. The target ratio acquisition module 440 is used to obtain the target ratio of each data to be displayed based on the allocation ratio of each data to be displayed and the preset ratio corresponding to each data to be displayed. The target ratio of the data to be displayed is greater than the corresponding preset ratio. The data resource allocation module 450 is used to allocate data resources to each data to be displayed according to the target ratio of each data to be displayed.

[0137] In one possible implementation, the first user feedback data includes at least two types, and the expectation value acquisition module 420 is further used to perform a weighted summation of the first user feedback data of at least two types for each data to be displayed to obtain the display expectation value of each data to be displayed.

[0138] In one possible implementation, the allocation ratio acquisition module 430 includes a data acquisition submodule, an initial ratio acquisition submodule, and a ratio allocation submodule.

[0139] The data acquisition submodule is used to acquire the target temperature coefficient of the Softmax algorithm and the maximum expected display value among the expected display values ​​of each data to be displayed; the initial ratio acquisition submodule is used to calculate the target temperature coefficient and the expected display value of each data to be displayed using the Softmax algorithm to obtain the initial ratio of each data to be displayed; the ratio allocation submodule is used to allocate the remaining ratio using the initial ratio of each data to be displayed to obtain the allocation ratio of each data to be displayed.

[0140] In this implementation, the data acquisition submodule is also used to obtain the target temperature coefficient of the Softmax algorithm based on the maximum display expectation value among the display expectation values ​​of each data to be displayed and the preset correspondence. The preset correspondence includes multiple preset temperature coefficients and a preset expectation value corresponding to each preset temperature coefficient.

[0141] In one possible implementation, the target ratio obtaining module 440 is further configured to sum the preset greedy ratio, the allocation ratio corresponding to the target data to be displayed among the multiple display data, and the preset ratio to obtain the target ratio of the target data to be displayed, wherein the target data to be displayed is the data to be displayed with the largest allocation ratio among the data to be displayed, and the sum of the preset greedy ratio, the preset ratio corresponding to each data to be displayed, and the remaining ratio of the multiple data to be displayed is 1; and to sum the allocation ratio and preset ratio corresponding to each of the other data to be displayed among the multiple display data excluding the target data to be displayed to obtain the target ratio corresponding to each of the other data to be displayed.

[0142] In one possible implementation, the device 400 further includes a data display module and an expectation value update module. The data display module is used to display each piece of data to be displayed, which is allocated data resources according to a target ratio, in the next display cycle; the data acquisition module is further used to acquire second user feedback data of each piece of data to be displayed obtained by displaying each piece of data in the next display cycle; the expectation value update module is used to update the display expectation value of each piece of data to be displayed based on the second user feedback data of each piece of data to be displayed.

[0143] In one possible implementation, the second user feedback data includes at least two types, and the expected value update module includes an adjustment value acquisition submodule and an update submodule. The adjustment value acquisition submodule is used to obtain the adjustment expected value of each piece of data to be displayed based on the second user feedback data of each piece of data to be displayed obtained in the next display cycle and the weight corresponding to each type of second user feedback data; the update submodule is used to sum the adjustment expected value of each piece of data to be displayed with the corresponding display expected value to obtain the updated display expected value.

[0144] In the above implementation, the adjustment value acquisition submodule is further configured to select the data to be displayed with the largest display expectation value from each data to be displayed, as the target data to be displayed; take the second user feedback data corresponding to the target data to be displayed as the target user feedback data; for each data to be displayed obtained in the next display cycle, based on the second user feedback data of the same type and the target user feedback data, obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed, and perform a weighted summation of the adjustment values ​​of each type of second user feedback data of the data to be displayed to obtain the adjustment expectation value of the data to be displayed.

[0145] In one possible implementation, the adjustment value acquisition submodule is further configured to, for each piece of data to be displayed obtained in the next display cycle, calculate the difference between the second user feedback data of the same type and the target user feedback data to obtain the difference value corresponding to each type of second user feedback data of the data to be displayed; and compare the difference value corresponding to each type of second user feedback data of the data to be displayed with the corresponding target user feedback data to obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed.

[0146] The following will combine Figure 10 This application describes an electronic device.

[0147] Please see Figure 10 Based on the data allocation method provided in the above embodiments, this application also provides another electronic device 100 including a processor 102 capable of executing the aforementioned method. The electronic device 100 can be a server or a terminal device, and the terminal device can be a smartphone, tablet computer, computer, or portable computer, etc.

[0148] The electronic device 100 also includes a memory 104. The memory 104 stores a program that can execute the contents of the foregoing embodiments, and the processor 102 can execute the program stored in the memory 104.

[0149] The processor 102 may include one or more cores for data processing and message matrix units. The processor 102 connects to various parts within the electronic device 100 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 104, and by calling data stored in the memory 104. Optionally, the processor 102 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 102 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 102 and may be implemented separately using a communication chip.

[0150] The memory 104 may include random access memory (RAM) or read-only memory (ROM). The memory 104 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 104 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described below, etc. The data storage area may also store data acquired by the electronic device 100 during use (e.g., signature fields and asymmetric keys).

[0151] The electronic device 100 may also include a network module and a screen. The network module is used to receive and transmit electromagnetic waves, converting electromagnetic waves into electrical signals, thereby enabling communication with communication networks or other devices, such as audio playback devices. The network module may include various existing circuit elements used to perform these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, SIM cards, memory, etc. The network module can communicate with various networks such as the Internet, corporate intranets, and wireless networks, or communicate with other devices via wireless networks. The aforementioned wireless networks may include cellular telephone networks, wireless local area networks, or metropolitan area networks. The screen can display interface content and facilitate data interaction.

[0152] In some embodiments, the electronic device 100 may further include a peripheral interface and at least one peripheral device. The processor 102, memory 104, and peripheral interface 106 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral interface via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency component 108, a positioning component 112, a camera 114, an audio component 116, a display screen 118, and a power supply 122. Peripheral interface 106 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 102 and memory 104. In some embodiments, processor 102, memory 104 and peripheral interface 106 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 102, memory 104 and peripheral interface 106 can be implemented on separate chips or circuit boards, and this application embodiment does not limit this.

[0153] The radio frequency (RF) component 108 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF component 108 communicates with communication networks and other communication devices via electromagnetic signals. The RF component 108 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF component 108 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF component 108 can communicate with other terminals via at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF component 108 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0154] Positioning component 112 is used to locate the current geographic location of an electronic device to enable navigation or LBS (Location Based Service). Positioning component 112 can be a positioning component based on the US GPS (Global Positioning System), BeiDou system, or Galileo system.

[0155] Camera 114 is used to capture images or videos. Optionally, camera 114 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the electronic device 100, and the rear-facing camera is located on the back of the electronic device 100. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, camera 114 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cool light flash, which can be used for light compensation at different color temperatures.

[0156] Audio component 116 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals that are input to processor 102 for processing, or input to radio frequency component 108 for voice communication. For stereo acquisition or noise reduction purposes, there may be multiple microphones, each located at a different part of electronic device 100. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from processor 102 or radio frequency component 108 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into sound waves that humans can hear, but also into sound waves that humans cannot hear for purposes such as ranging. In some embodiments, audio component 114 may also include a headphone jack.

[0157] Display screen 118 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 118 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 102 for processing. In this case, display screen 118 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 118, which serves as the front panel of electronic device 100; in other embodiments, there may be at least two display screens, respectively disposed on different surfaces of electronic device 100 or in a folded design; in still other embodiments, display screen 118 may be a flexible display screen, disposed on a curved or folded surface of electronic device 100. Furthermore, display screen 118 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 118 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0158] Power supply 122 is used to supply power to various components in electronic device 100. Power supply 122 can be alternating current, direct current, a disposable battery, or a rechargeable battery. When power supply 122 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0159] This application also provides a structural block diagram of a computer-readable storage medium. The computer-readable medium stores program code, which can be called by a processor to execute the methods described in the above method embodiments.

[0160] Computer-readable storage media can be electronic storage devices such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, computer-readable storage media includes non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program code that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code can be compressed, for example, in a suitable form.

[0161] This application also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods described in the various optional implementations above.

[0162] In summary, the data allocation method, apparatus, device, and medium provided in this application acquire preset ratios corresponding to multiple pieces of data to be displayed, remaining ratios of the multiple pieces of data to be displayed, and first user feedback data of each piece of data to be displayed obtained by displaying each piece of data within a display period. Based on the first user feedback data of each piece of data to be displayed, the display expectation value of each piece of data to be displayed is obtained. Based on the display expectation value of each piece of data to be displayed, the remaining ratio is allocated to obtain the allocation ratio of each piece of data to be displayed. Based on the allocation ratio of each piece of data to be displayed and the preset ratio corresponding to each piece of data to be displayed, the target ratio of each piece of data to be displayed is obtained. Thus, data resources are allocated to each piece of data to be displayed according to the target ratio. This ensures that when displaying multiple pieces of data to be displayed, even if the display expectation value of a piece of data to be displayed is low, a certain amount of data resources can still be allocated to that piece of data. This avoids the situation where the user feedback data obtained during the display of a piece of data within a single display period is inaccurate (e.g., due to the time-sensitive nature of the data to be displayed), which could lead to the inability to reasonably allocate data resources to that piece of data in the future. This improves the rationality of data resource allocation, thereby increasing the benefits obtained from displaying data based on the allocated data resources.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A data allocation method, characterized in that, The method includes: The system obtains the preset ratios corresponding to multiple data to be displayed, the remaining ratios of multiple data to be displayed, and the first user feedback data of each data to be displayed obtained by displaying each data to be displayed within the display period. The sum of the preset ratios corresponding to each data to be displayed and the sum of the remaining ratios of multiple data to be displayed are not greater than 1. Based on the first user feedback data of each of the data to be displayed, obtain the expected display value of each of the data to be displayed; The remaining proportions are allocated according to the expected display values ​​of each of the data to be displayed, to obtain the allocation proportions of each of the data to be displayed; The target ratio of each data to be displayed is obtained based on the allocation ratio of each data to be displayed and the preset ratio corresponding to each data to be displayed. The target ratio of the data to be displayed is greater than the corresponding preset ratio. Data resources are allocated to each of the data to be displayed according to the target proportion of each of the data to be displayed.

2. The method according to claim 1, characterized in that, After allocating data resources to each of the data to be displayed according to the target proportion of each of the data to be displayed, the method further includes: In the next display cycle, each piece of data to be displayed will be shown according to the data resources allocated according to the target ratio; Second user feedback data for each of the data to be displayed is obtained by displaying each of the data to be displayed in the next display cycle; Based on the second user feedback data for each of the data to be displayed, update the display expectation value for each of the data to be displayed, and return to the step of allocating the remaining proportion according to the display expectation value for each of the data to be displayed to obtain the allocation proportion for each of the data to be displayed.

3. The method according to claim 2, characterized in that, The second user feedback data includes at least two types, and updating the display expectation value of each piece of data to be displayed based on the second user feedback data of each piece of data to be displayed obtained in the next display cycle includes: Select the data with the highest expected display value from all the data to be displayed, and use it as the target data to be displayed. The second user feedback data corresponding to the target data to be displayed is used as the target user feedback data; For each piece of data to be displayed obtained in the next display cycle, based on the second user feedback data of the same type and the target user feedback data, the adjustment value corresponding to each type of second user feedback data of the data to be displayed is obtained, and the adjustment value of each type of second user feedback data of the data to be displayed is weighted and summed to obtain the expected adjustment value of the data to be displayed. The adjusted expected value of each of the data to be displayed is summed with the corresponding display expected value to obtain the updated display expected value.

4. The method according to claim 3, characterized in that, For each piece of data to be displayed obtained in the next display cycle, based on the same type of second user feedback data and target user feedback data, an adjustment value corresponding to each type of second user feedback data for the data to be displayed is obtained, including: For each piece of data to be displayed obtained in the next display cycle, the difference between the second user feedback data of the same type and the target user feedback data is calculated to obtain the difference value corresponding to each type of second user feedback data of the data to be displayed; the difference value corresponding to each type of second user feedback data of the data to be displayed is compared with the corresponding target user feedback data to obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed.

5. The method according to claim 1, characterized in that, The step of allocating the remaining proportions according to the display expectation values ​​of each of the data to be displayed, to obtain the allocation proportions for each of the data to be displayed, includes: Obtain the maximum expected display value among the expected display values ​​of each of the data to be displayed; Based on the maximum expected value among the expected values ​​of each of the data to be displayed and the preset correspondence, the target temperature coefficient of the Softmax algorithm is obtained. The preset correspondence includes multiple preset temperature coefficients and a preset expected value corresponding to each preset temperature coefficient. The target temperature coefficient and the expected display value of each of the data to be displayed are calculated using the Softmax algorithm to obtain the initial ratio of each of the data to be displayed; The remaining proportions are allocated using the initial proportions of each of the data to be displayed, thereby obtaining the allocation proportions of each of the data to be displayed.

6. The method according to claim 1, characterized in that, The step of obtaining the target ratio of each of the data to be displayed based on the allocation ratio of each of the data to be displayed and the preset ratio corresponding to each data to be displayed includes: The target ratio of the target data to be displayed is obtained by summing the preset greedy ratio, the allocation ratio of the target data to be displayed in the multiple display data, and the preset ratio. The target data to be displayed is the data to be displayed with the largest allocation ratio among all the data to be displayed, and the sum of the preset greedy ratio, the preset ratio corresponding to each of the data to be displayed, and the remaining ratio of the multiple data to be displayed is 1. The allocation ratio and preset ratio of each of the other data to be displayed (excluding the target data to be displayed) are summed to obtain the target ratio of each of the other data to be displayed.

7. The method according to claim 1, characterized in that, The first user feedback data includes at least two types. Based on the first user feedback data for each of the data to be displayed, the expected display value for each of the data to be displayed is obtained, including: The expected display value of each piece of data to be displayed is obtained by weighted summing of at least two types of first user feedback data for each piece of data to be displayed.

8. A data distribution device, characterized in that, The device includes: The data acquisition module is used to acquire multiple data to be displayed, a preset ratio corresponding to each data to be displayed, a remaining ratio of the multiple data to be displayed, and first user feedback data of each data to be displayed obtained by displaying each data to be displayed within a display period. The sum of the preset ratios corresponding to each data to be displayed and the sum of the remaining ratios of the multiple data to be displayed are not greater than 1. The expected value acquisition module is used to obtain the expected display value of each of the data to be displayed based on the first user feedback data of each of the data to be displayed; The allocation ratio acquisition module is used to allocate the remaining ratio according to the display expectation value of each of the data to be displayed, and obtain the allocation ratio of each of the data to be displayed; The target ratio acquisition module is used to obtain the target ratio of each of the data to be displayed based on the allocation ratio of each of the data to be displayed and the preset ratio corresponding to each data to be displayed, wherein the target ratio of the data to be displayed is greater than the corresponding preset ratio. The data resource allocation module is used to allocate data resources to each of the data to be displayed according to the target proportion of each of the data to be displayed.

9. The apparatus according to claim 8, characterized in that, The device further includes: The data display module is used to display each piece of data to be displayed, according to the target ratio, within the next display cycle; The data acquisition module is also used to acquire second user feedback data of each of the data to be displayed, obtained by displaying each of the data to be displayed in the next display cycle; The expected value update module is used to update the display expected value of each of the data to be displayed based on the second user feedback data of each of the data to be displayed, and return to the step of allocating the remaining proportion according to the display expected value of each of the data to be displayed to obtain the allocation proportion of each of the data to be displayed.

10. The apparatus according to claim 9, characterized in that, The second user feedback data includes at least two types, and the expected value update module includes: The adjustment value acquisition submodule is used to select the data with the largest expected display value from the data to be displayed as the target data to be displayed; to take the second user feedback data corresponding to the target data to be displayed as the target user feedback data; and for each data to be displayed obtained in the next display cycle, to obtain the adjustment value corresponding to each type of second user feedback data of the data to be displayed based on the second user feedback data of the same type and the target user feedback data, and to perform a weighted summation of the adjustment values ​​of each type of second user feedback data of the data to be displayed to obtain the adjustment expected value of the data to be displayed. The update submodule is used to sum the adjustment expectation value of each of the data to be displayed with the corresponding display expectation value to obtain the updated display expectation value.

11. The apparatus according to claim 10, characterized in that, The adjustment value acquisition submodule is also used for: For each piece of data to be displayed obtained in the next display cycle, the difference between the second user feedback data of the same type and the target user feedback data is calculated to obtain the difference value corresponding to each type of second user feedback data of the data to be displayed. The difference between each type of second user feedback data of the data to be displayed is compared with the corresponding target user feedback data to obtain the adjustment value for each type of second user feedback data of the data to be displayed.

12. The apparatus according to claim 8, characterized in that, The allocation ratio acquisition module includes: The data acquisition submodule is used to acquire the maximum display expectation value among the display expectation values ​​of each of the data to be displayed; and to obtain the target temperature coefficient of the Softmax algorithm based on the maximum display expectation value among the display expectation values ​​of each of the data to be displayed and a preset correspondence relationship, wherein the preset correspondence relationship includes multiple preset temperature coefficients and a preset expectation value corresponding to each preset temperature coefficient. The initial ratio acquisition submodule is used to calculate the initial ratio of each of the data to be displayed by using the Softmax algorithm on the target temperature coefficient and the expected display value of each of the data to be displayed. The proportion allocation submodule is used to allocate the remaining proportions based on the initial proportions of each of the data to be displayed, thereby obtaining the allocation proportions of each of the data to be displayed.

13. The apparatus according to claim 8, characterized in that, The target ratio acquisition module is further configured to: The target ratio of the target data to be displayed is obtained by summing the preset greedy ratio, the allocation ratio of the target data to be displayed in the multiple display data, and the preset ratio. The target data to be displayed is the data to be displayed with the largest allocation ratio among all the data to be displayed, and the sum of the preset greedy ratio, the preset ratio corresponding to each of the data to be displayed, and the remaining ratio of the multiple data to be displayed is 1. The allocation ratio and preset ratio of each of the other data to be displayed (excluding the target data to be displayed) are summed to obtain the target ratio of each of the other data to be displayed.

14. The apparatus according to claim 8, characterized in that, The first user feedback data includes at least two types, and the expected value acquisition module is further configured to: perform a weighted summation of the first user feedback data of at least two types for each of the data to be displayed to obtain the display expected value for each of the data to be displayed.

15. An electronic device, characterized in that, include: One or more processors; Memory; One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the method as described in any one of claims 1-7.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that can be invoked by a processor to execute the method as described in any one of claims 1-7.

17. A computer program product comprising computer instructions, characterized in that, When executed by a processor, the computer instructions implement the steps of the method described in any one of claims 1-7.

Images