Method, device and storage medium for advertising delivery

Abstract

This application relates to the field of advertising delivery technology and discloses a method for advertising delivery, applicable to a demand-side platform (DSP). The method comprises: collecting data representing the effectiveness of advertising delivery for N advertisements in real time, where N is an integer greater than 1; analyzing the delivery effectiveness of each of the N advertisements based on the collected data; and adjusting the delivery strategy for the N advertisements based on the analyzed delivery effectiveness. This method can perceive the delivery effectiveness of multiple advertisements in real time, facilitating timely adjustment of multiple advertising delivery strategies during the delivery process. This application also discloses an apparatus and storage medium for advertising delivery.

Description

Technical Field

[0001] The present application relates to the technical field of advertisement delivery, and in particular to a method, device, and storage medium for advertisement delivery. Background Art

[0002] Currently, in the field of programmatic advertising, advertisers, media providers, and third-party publishers all need to know the effectiveness of their advertising. Therefore, ad monitoring technology has become a must-have for programmatic advertising practitioners. The current mainstream ad monitoring technology involves adding code to the pages of advertising materials, collecting exposure, click, and browsing records, and then analyzing the monitoring logs using big data technology to evaluate the advertising's post-hoc effectiveness. Demand-side platform (DSP) advertising requires not only knowing the post-hoc effectiveness of advertising, but also real-time perception of advertising effectiveness and adjustments to advertising strategies during the advertising process.

[0003] In the prior art, there is also a method of grouping advertisements and predicting the push ratio and withdrawal ratio of advertisement traffic in the next cycle to obtain the predicted delivery probability of the group.

[0004] This technology has the following disadvantages:

[0005] Although the ad delivery probability for the next cycle is predicted, it is not possible to adjust the ad exposure probability in real time after the next cycle begins. In addition, it is not possible to adjust the ad exposure probability for multiple ads in real time. As a result, it is impossible to adjust the delivery strategy in real time during the delivery process. Summary of the Invention

[0006] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0007] The embodiments of the present disclosure provide a method, apparatus, and storage medium for advertisement delivery, which can perceive the delivery effects of multiple advertisements in real time, facilitating timely adjustment of multiple advertisement delivery strategies during the delivery process.

[0008] In some embodiments, applied to a demand-side platform (DSP), the method includes: for N advertisements, collecting data representing the effectiveness of advertisement delivery in real time, where N is an integer greater than 1; analyzing the delivery effect of each of the N advertisements based on the collected data; and adjusting the delivery strategy of the N advertisements based on the analyzed delivery effect.

[0009] Optionally, the data representing the effectiveness of advertising delivery include advertising exposure and advertising clicks.

[0010] Optionally, analyzing the placement effect of each of the N advertisements based on the collected data includes: when Ai < Ln1, placing the ith advertisement in the first exposure group indicating less exposure; when Ln1 ≤ Ai < Ln2, placing the ith advertisement in the second exposure group indicating appropriate exposure; when Ai ≥ Ln2, placing the ith advertisement in the third exposure group indicating more exposure; where i = 1, …, N; Ai is the advertisement exposure of the ith advertisement, Ln1 is the first threshold, Ln2 is the second threshold, and Ln1 < Ln2.

[0011] Optionally, adjusting the placement strategy of the N advertisements according to the analyzed placement effect of the advertisements includes: increasing the exposure probability of each advertisement in the first exposure group and decreasing the exposure probability of each advertisement in the third exposure group.

[0012] Optionally, increasing the exposure probability of each advertisement in the first exposure group includes: increasing the exposure probability of each advertisement in the first exposure group according to the first step size, where the first step size is obtained based on the difference between the exposure of the first exposure group and the exposure of the third exposure group and the number of advertisements in the first exposure group; or increasing the exposure probability of each advertisement in the first exposure group according to the second step size, where the second step size is obtained based on the difference between the estimated exposure obtained from the ratio of the click-through rate to the exposure and the current exposure of the first exposure group and the number of advertisements in the first exposure group.

[0013] Optionally, after increasing the exposure probability of the first exposure group, it further includes: when the exposure of the advertisement included in the first exposure group meets the condition of the second exposure group, migrating the advertisement from the first exposure group to the second exposure group; determining whether the condition for stopping adjustment is met, and if it is met, stopping the adjustment, otherwise adjusting again.

[0014] Optionally, the condition for meeting the stop adjustment includes: the first exposure group or the third exposure group is empty.

[0015] Optionally, decreasing the exposure probability of the advertisements in the third exposure group includes: decreasing the exposure probability of each advertisement in the third exposure group according to the third step size, where the third step size is obtained based on the difference between the exposure of the first exposure group and the exposure of the third exposure group and the number of advertisements in the third exposure group; or decreasing the exposure probability of each advertisement in the third exposure group according to the fourth step size, where the fourth step size is obtained based on the difference between the estimated exposure obtained from the ratio of the click-through rate to the exposure and the current exposure of the third exposure group and the number of advertisements in the third exposure group.

[0016] Optionally, after lowering the exposure probability of the third exposure group, the method further includes: if the exposure volume of the advertisement included in the third exposure group satisfies the exposure volume of the second exposure group, the advertisement is transferred from the third exposure group to the second exposure group. Optionally, the method further includes:

[0017] Use small text file cookies to identify the browser and collect ad impressions in real time;

[0018] Use device ID to identify mobile terminals and collect ad exposure in real time;

[0019] Use device ID to identify OTT terminals and collect advertising exposure in real time.

[0020] Optionally, the above also includes:

[0021] Aggregate data representing advertising effectiveness from multiple terminals into streaming logs through message queues;

[0022] Parse streaming logs to extract data representing advertising effectiveness across multiple terminals and write it to an in-memory database.

[0023] Parse the streaming logs to extract data representing the effectiveness of advertising on multiple terminals and write them into log files.

[0024] In some embodiments, the system includes a processor and a memory storing program instructions, wherein the processor is configured to execute the above-described method for advertisement delivery when running the program instructions.

[0025] In some embodiments, program instructions are stored, and when the program instructions are executed, the method for advertising delivery as described above is executed.

[0026] Data representing the effectiveness of advertising is collected in real time from multiple display devices for multiple ads and stored on storage media. The effectiveness of each ad is analyzed and grouped according to the analyzed results. Based on the desired impressions or clicks, the impression probability of each ad group is adjusted to implement changes in advertising strategies.

[0027] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] One or more embodiments are exemplarily described by corresponding drawings. These exemplary descriptions and drawings do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation. In addition,

[0029] Figure 1This is a structural diagram of a method for advertising delivery provided by an embodiment of the present disclosure;

[0030] Figure 2 is a flow chart of a method for advertising delivery provided by an embodiment of the present disclosure;

[0031] Figure 3 This is a flow chart of changing an advertisement delivery strategy according to exposure provided by an embodiment of the present disclosure;

[0032] Figure 4 This is a flow chart of changing an advertisement delivery strategy according to click volume provided by an embodiment of the present disclosure;

[0033] Figure 5 This is a schematic diagram of an apparatus for advertising delivery provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The accompanying drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0035] In the description and claims of the embodiments of the present disclosure, as well as in the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar items and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate to describe the embodiments of the present disclosure herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0036] Unless otherwise stated, the term "plurality" means two or more.

[0037] Combine Figure 1As shown in the figure, it is a schematic structural diagram of a method for advertising placement. The exposure and click collection service collects advertising exposure data and click data from various terminal devices, and the terminal devices include computer PC browsers, mobile terminals, and OTT terminals. The exposure and click collection service transmits the exposure data and click data to the streaming log in the form of a message queue. The streaming log records the advertising exposure volume and click volume of each terminal, and stores them in the in-memory database and the log file respectively. Moreover, the log file stores the daily advertising exposure volume and click volume in the in-memory database. The advertising placement strategy service obtains the advertising exposure volume and click volume from the in-memory database, compares the exposure groups where each advertisement is located, and analyzes to obtain the advertising placement strategy. The advertising placement strategy service adjusts the advertising placement according to the advertising placement strategy.

[0038] Combined with Figure 2 As shown in the figure, it is a flowchart of a method for advertising placement, including:

[0039] S01. For N advertisements, the advertising placement system collects in real time the data representing the advertising placement effect, where N is an integer greater than 1.

[0040] S02. The advertising placement system analyzes the placement effect of each of the N advertisements according to the collected data.

[0041] S03. The advertising placement system adjusts the placement strategy of the N advertisements according to the analyzed advertising placement effect.

[0042] In this way, the advertising placement system collects in real time multiple data representing the advertising placement effect from various advertising display terminals, analyzes the effect of each collected advertisement, and adjusts the advertising placement strategy in real time according to the analysis result.

[0043] Optionally, in step S01, the data representing the advertising placement effect includes the advertising exposure volume and the advertising click volume.

[0044] In this way, the advertising exposure volume and the advertising click volume are the two most influential factors on the advertising placement effect.

[0045] Optionally, in step S02, analyzing the placement effect of each of the N advertisements according to the collected data includes: when Ai < Ln1, placing the i-th advertisement in the first exposure group representing a smaller exposure volume; when Ln1 ≤ Ai < Ln2, placing the i-th advertisement in the second exposure group representing an appropriate exposure volume; when Ai ≥ Ln2, placing the i-th advertisement in the third exposure group representing a larger exposure volume; where i = 1,..., N; Ai is the advertising exposure volume of the i-th advertisement, Ln1 is the first threshold, Ln2 is the second threshold, and Ln1 < Ln2.

[0046] In this way, advertisements are grouped according to their exposure volume, and the advertisements in each group are processed separately through the relationship between the groups. Compared with directly adjusting the exposure volume of each advertisement, the advertisements in the group can be processed collectively while maintaining the association between the exposure volumes of each group, thereby realizing cluster processing of advertisement exposure volume.

[0047] Optionally, in step S03, the delivery strategies of the N advertisements are adjusted according to the analyzed advertising delivery effects, including: increasing the exposure probability of each advertisement in the first exposure group, and decreasing the exposure probability of each advertisement in the third exposure group.

[0048] In this way, the first exposure group is associated with the third exposure group. When the exposure probability of the first exposure group is increased, the exposure probability of the third exposure group is decreased, so that the advertisements in the first exposure group and the third exposure group are adjusted at the same time and enter the second exposure group.

[0049] Optionally, the above-mentioned increasing the exposure probability of each advertisement in the first exposure group includes: increasing the exposure probability of each advertisement in the first exposure group according to the first step length, wherein the first step length is obtained based on the difference between the exposure amount of the first exposure group and the exposure amount of the third exposure group and the number of advertisements in the first exposure group; or, increasing the exposure probability of each advertisement in the first exposure group according to the second step length, wherein the second step length is obtained based on the difference between the estimated exposure amount obtained based on the ratio of clicks to exposure amount and the current exposure amount of the first exposure group and the number of advertisements in the first exposure group.

[0050] In this way, there are two ways to adjust the advertising exposure strategy. One is to compare the exposure of each group, and the other is to adjust the advertising exposure strategy based on the ratio of clicks to exposure and the current exposure.

[0051] Optionally, after increasing the exposure probability of each advertisement in the first exposure group, the method further includes: if the exposure amount of the advertisement included in the first exposure group satisfies the second exposure group, the advertisement is migrated from the first exposure group to the second exposure group; judging whether the condition for stopping adjustment is met, if so, stopping the adjustment, otherwise adjusting again

[0052] In this way, when the advertisement of the first exposure group meets the requirements of the second exposure group, the advertisement is migrated to the second exposure group, thereby completing the adjustment of the advertisement exposure.

[0053] Optionally, the condition for stopping adjustment includes: the first exposure group or the third exposure group is empty.

[0054] In this way, when one of the first exposure group or the third exposure group is empty, the adjustment of the advertisement exposure can be ended.

[0055] Optionally, reducing the exposure probability of advertisements in the third exposure group as described above includes: reducing the exposure probability of each advertisement in the third exposure group according to a third step size, where the third step size is obtained based on the difference between the exposure amount of the first exposure group and the exposure amount of the third exposure group and the number of advertisements in the third exposure group; or reducing the exposure probability of each advertisement in the third exposure group according to a fourth step size, where the fourth step size is obtained based on the difference between the estimated exposure amount obtained from the ratio of the click-through rate to the exposure amount and the current exposure amount of the third exposure group and the number of advertisements in the third exposure group.

[0056] In this way, while increasing the first exposure group, the third exposure group is correspondingly reduced, so that the exposure amounts of each advertisement quickly reach equilibrium.

[0057] Optionally, after reducing the exposure probability of the third exposure group as described above, it further includes: when the exposure amount of the advertisement included in the third exposure group meets that of the second exposure group, the advertisement is migrated from the third exposure group to the second exposure group.

[0058] In this way, when the advertisement in the third exposure group meets the conditions of the second exposure group, the advertisement is migrated to the second exposure group, thereby realizing the adjustment of advertisement exposure.

[0059] Combined with Figure 3 As shown, a flowchart of changing the advertisement placement strategy according to the exposure amount includes:

[0060] S100, the advertisement placement system collects the exposure data of N advertisements from the terminal.

[0061] S101, the advertisement placement system sets an exposure threshold Ln1, Ln2 for each of the N advertisements and sets the first exposure group, the second exposure group, and the third exposure group.

[0062] S102, the advertisement placement system obtains the current exposure amount Ai of the i-th advertisement.

[0063] S103, when Ai < Ln1, advertisement i is placed in the first exposure group; when Ln1 ≤ Ai < Ln2, advertisement i is placed in the second exposure group; when Ai ≥ Ln2, advertisement i is placed in the third exposure group.

[0064] S104, the advertisement placement system determines whether the first exposure group or the third exposure group is empty. If neither the first exposure group nor the third exposure group is empty, step S105 is executed; otherwise, it ends.

[0065] S105, the advertisement placement system obtains the exposure increase amount in the first exposure group and the exposure decrease amount in the third exposure group based on the difference between the exposure amounts of the third exposure group and the first exposure group.

[0066] S106. The advertising delivery system calculates the exposure step of each advertisement in the first exposure group based on the exposure growth of the first exposure group, the number of advertisements in the first exposure group, and the total number of advertisements in all exposure groups, and adjusts the exposure amount. It also calculates the exposure step of each advertisement in the third exposure group based on the exposure reduction of the third exposure group, the number of advertisements in the third exposure group, and the total number of advertisements in all exposure groups, and adjusts the exposure amount.

[0067] S107. The advertising delivery system migrates the advertisements in the first exposure group and the third exposure group that meet the conditions of the second exposure group to the second exposure group, and returns to step S104.

[0068] According to the above steps, for example, there are 6 advertisements with exposure amounts of 1 time, 2 times, 4 times, 4 times, 6 times, and 7 times respectively. Then, the first exposure group has advertisements with exposure amounts of 1 time and 2 times, the second exposure group has advertisements with exposure amounts of 4 times and 4 times, and the third exposure group has advertisements with exposure amounts of 6 times and 7 times. The difference in exposure amount between the third exposure group and the first exposure group is 10. The total exposure amount of the first exposure group needs to be increased by 5 times, with an average increase of 2.5 times for each advertisement. Similarly, the total exposure amount of the third exposure group needs to be decreased by 5 times, with an average decrease of 2.5 times for each advertisement. Then, according to the total number of advertisements, it can be calculated that when exposing advertisements in each cycle, the exposure amount of the advertisements in the first exposure group should be increased, and at the same time, the exposure amount of the advertisements in the third exposure group should be decreased accordingly. Thus, the advertisements in the first exposure group and the third exposure group can be simply and quickly migrated to the second exposure group.

[0069] Combined Figure 4 shown, a flowchart of changing the advertising delivery strategy according to the click volume, including:

[0070] S200. The advertising delivery system collects the exposure data of N advertisements from the terminals.

[0071] S201. The advertising delivery system sets an exposure threshold Ln1, Ln2 for each of the N advertisements, and sets the first exposure group, the second exposure group, and the third exposure group.

[0072] S202. The advertising delivery system obtains the current exposure amount Ai of the i-th advertisement.

[0073] S203. When Ai < Ln1, the advertisement i is placed in the first exposure group; when Ln1 ≤ Ai < Ln2, the advertisement i is placed in the second exposure group; when Ai ≥ Ln2, the advertisement i is placed in the third exposure group.

[0074] S204. The advertising delivery system determines whether the first exposure group or the third exposure group is empty. If the first exposure group and the third exposure group are not empty, then step S205 is executed; otherwise, it ends.

[0075] S205, the advertising delivery system obtains the exposure increase of the first exposure group by the difference between the estimated exposure amount and the current exposure amount of the first exposure group according to the ratio of clicks and exposures, and obtains the exposure decrease of the third exposure group by the difference between the estimated exposure amount and the current exposure amount of the third exposure group according to the ratio of clicks and exposures.

[0076] S206, the advertising delivery system calculates the exposure step length of each advertisement in the first exposure group and adjusts the exposure amount based on the exposure increase of the first exposure group, the number of advertisements in the first exposure group, and the total number of advertisements in all exposure groups; calculates the exposure step length of each advertisement in the third exposure group and adjusts the exposure amount based on the exposure decrease of the third exposure group, the number of advertisements in the third exposure group, and the total number of advertisements in all exposure groups.

[0077] S207 , the advertising delivery system migrates the advertisements in the first exposure group and the third exposure group that meet the conditions of the second exposure group to the second exposure group, and returns to step S204 .

[0078] The estimated exposure can be obtained through the ratio of ad clicks to exposure. Therefore, the clicks can be indirectly adjusted by adjusting the exposure, thereby meeting the requirements for ad clicks.

[0079] Combine Figure 5 As shown, an embodiment of the present disclosure provides an apparatus for advertising delivery, including a processor 100 and a memory 101. Optionally, the apparatus may further include a communication interface 102 and a bus 103. The processor 100, the communication interface 102, and the memory 101 may communicate with each other via the bus 103. The communication interface 102 may be used for information transmission. The processor 100 may call the logic instructions in the memory 101 to execute the method for advertising delivery of the above embodiment.

[0080] In addition, the logic instructions in the memory 101 can be implemented in the form of software functional units and can be stored in a readable storage medium when sold or used as an independent product.

[0081] Memory 101, as a storage medium, can be used to store software programs and executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. Processor 100 executes the program instructions / modules stored in memory 101 to execute functional applications and data processing, thereby implementing the methods for advertising delivery in the above-described embodiments.

[0082] The memory 101 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the terminal device, etc.

[0083] An embodiment of the present disclosure provides a storage medium storing executable instructions, wherein the executable instructions are configured to execute the above-mentioned method for advertisement delivery.

[0084] The above-mentioned storage medium is a non-transitory readable storage medium.

[0085] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible variations. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to also include plural forms. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variations "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups of these. In the absence of further restrictions, an element defined by the sentence "comprising a..." does not exclude the presence of other identical elements in the process, method or device that includes the element. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments can be referenced to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can be found in the description of the method part.

[0086] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. The technicians will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0087] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, and can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of the present disclosure may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and program products according to the embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in an order different from that marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. Each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or action, or may be implemented using a combination of dedicated hardware and instructions.

Claims

1. A method for advertising delivery, applied to a demand-side platform (DSP), characterized in that: The method includes: For N advertisements, data characterizing the advertisement delivery effect is collected in real time, where N is an integer greater than 1; among them, the data characterizing the advertisement delivery effect includes advertisement exposure volume and advertisement click volume; Analyze the delivery effect of each of the N advertisements based on the collected data; specifically including: when Ai < Ln1, place the i-th advertisement in the first exposure group indicating less exposure volume; when Ln1 ≤ Ai < Ln2, place the i-th advertisement in the second exposure group indicating appropriate exposure volume; when Ai ≥ Ln2, place the i-th advertisement in the third exposure group indicating more exposure volume; where i = 1,..., N; Ai is the advertisement exposure volume of the i-th advertisement, Ln1 is the first threshold, Ln2 is the second threshold, and Ln1 < Ln2; Adjust the delivery strategy of the N advertisements according to the analyzed advertisement delivery effect; specifically including: increasing the exposure probability of each advertisement in the first exposure group, and decreasing the exposure probability of each advertisement in the third exposure group; where increasing the exposure probability of each advertisement in the first exposure group includes increasing the exposure probability of each advertisement in the first exposure group according to the first step size; the first step size is obtained based on the difference between the exposure volume of the first exposure group and the exposure volume of the third exposure group and the number of advertisements in the first exposure group; decreasing the exposure probability of each advertisement in the third exposure group includes decreasing the exposure probability of each advertisement in the third exposure group according to the third step size; the third step size is obtained based on the difference between the exposure volume of the first exposure group and the exposure volume of the third exposure group and the number of advertisements in the third exposure group.

2. The method according to claim 1, characterized in that Increasing the exposure probability of each advertisement in the first exposure group further includes: Increasing the exposure probability of each advertisement in the first exposure group according to the second step size, where the second step size is obtained based on the difference between the estimated exposure volume obtained from the ratio of click volume to exposure volume and the current exposure volume of the first exposure group and the number of advertisements in the first exposure group.

3. The method according to claim 1, characterized in that After increasing the exposure probability of the first exposure group, it further includes: When the exposure volume of the advertisement included in the first exposure group meets that of the second exposure group, the advertisement migrates from the first exposure group to the second exposure group; Judge whether the condition for stopping adjustment is met. If it is met, stop the adjustment; otherwise, adjust again.

4. The method according to claim 3, characterized in that The condition for meeting the stop adjustment includes: The first exposure group or the third exposure group is empty.

5. The method according to claim 1, wherein Decreasing the exposure probability of the advertisement in the third exposure group further includes: Decreasing the exposure probability of each advertisement in the third exposure group according to the fourth step size, where the fourth step size is obtained based on the difference between the estimated exposure volume obtained from the ratio of click volume to exposure volume and the current exposure volume of the third exposure group and the number of advertisements in the third exposure group.

6. The method according to claim 1, characterized in that After decreasing the exposure probability of the third exposure group, it further includes: When the exposure volume of the advertisement included in the third exposure group meets that of the second exposure group, the advertisement migrates from the third exposure group to the second exposure group.

7. A device for advertising delivery, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for advertisement delivery according to any one of claims 1 to 6 when running the program instructions.

8. A storage medium storing program instructions, characterized in that: When the program instructions are running, execute the method for advertisement delivery according to any one of claims 1 to 6.

Images