Advertisement putting method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an advertisement putting method and device, equipment and a medium, and the method comprises the steps: taking a putting strategy currently executed by a target advertisement as a to-be-evaluated strategy, and obtaining putting parameters of the to-be-evaluated strategy; inputting the putting parameters and strategy parameters of the to-be-evaluated strategy into a pre-trained target prediction model, and obtaining putting performance corresponding to execution of the to-be-evaluated strategy by the target advertisement output by the target prediction model; under the condition that the delivery performance does not meet the preset requirement, determining a target delivery strategy based on the delivery performance; and adjusting the putting strategy executed by the target advertisement to the target putting strategy. According to the embodiment of the invention, the delivery performance of the currently executed delivery strategy of the target advertisement is determined through the pre-trained target prediction model, automatic evaluation of the delivery performance of the delivery strategy can be realized, artificial analysis by related business personnel is not needed, and the labor cost can be greatly reduced.

Description

Technical Field

[0001] The present invention belongs to the field of computer technology, and in particular relates to an advertisement delivery method, device, electronic equipment and storage medium. Background Art

[0002] With the development of computer technology, more and more advertising platforms have emerged, and manufacturers of other application products can place advertisements on advertising platforms. Currently, many advertising platforms provide Real-Time API (RTA). Manufacturers can use different delivery strategies to place advertisements on advertising platforms. Delivery strategies can include the delivery method of advertisements, the data return method, and the purpose of advertisement delivery. Different delivery strategies produce different advertising delivery effects. Therefore, in actual scenarios, manufacturers need to adjust delivery strategies in real time through RTA.

[0003] Currently, relevant business personnel usually manually analyze the delivery performance of the current delivery strategy and adjust the delivery strategy, which has high labor costs. Summary of the invention

[0004] The present invention provides an advertisement delivery method, device, electronic device and storage medium, so as to solve the problem of high labor cost of advertisement delivery.

[0005] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0006] In a first aspect, the present invention provides an advertisement delivery method, characterized in that the method comprises:

[0007] The delivery strategy currently executed by the target advertisement is used as the strategy to be evaluated, and delivery parameters of the strategy to be evaluated are obtained;

[0008] Input the delivery parameters and the strategy parameters of the strategy to be evaluated into a pre-trained target prediction model, and obtain the delivery performance of the target advertisement output by the target prediction model corresponding to the execution of the strategy to be evaluated;

[0009] In the case where the delivery performance does not meet the preset requirements, determining a target delivery strategy based on the delivery performance;

[0010] The delivery strategy executed by the target advertisement is adjusted to the target delivery strategy.

[0011] Optionally, the target prediction model is trained in the following manner:

[0012] Get the historical delivery parameters and reference delivery performance of the historical delivery strategy;

[0013] Inputting the historical delivery parameters and the historical strategy parameters of the historical delivery strategy into an initial prediction model, and obtaining the predicted delivery performance output by the initial prediction model;

[0014] Based on the predicted delivery performance and the reference delivery performance, the model parameters of the initial prediction model are adjusted until a training stop condition is reached, and the current initial prediction model is determined as a target prediction model.

[0015] Optionally, determining a target delivery strategy based on the delivery performance includes:

[0016] Determining a strategy adjustment requirement based on the delivery performance and the preset requirements;

[0017] Obtaining the strategy characteristics of each candidate delivery strategy from a pre-built delivery strategy library;

[0018] A candidate delivery strategy whose strategy characteristics meet the strategy adjustment requirements is selected as the target delivery strategy.

[0019] Optionally, the delivery performance includes budget consumption and / or conversion rate; after obtaining the delivery performance of the target advertisement output by the target prediction model executing the strategy to be evaluated, the method further includes:

[0020] When the budget consumption of the strategy to be evaluated is not less than the target consumption, and the conversion rate is not less than the target conversion rate, determining that the delivery performance meets the preset requirements;

[0021] Furthermore, when the budget consumption of the strategy to be evaluated is less than the target consumption, and / or the conversion rate is less than the target conversion rate, it is determined that the delivery performance does not meet the preset requirements.

[0022] Optionally, the selecting a candidate delivery strategy whose strategy characteristics meet the strategy adjustment requirement as the target delivery strategy includes:

[0023] When the budget consumption of the strategy to be evaluated is less than the target consumption, selecting a candidate delivery strategy whose strategy feature is a first strategy feature as the target delivery strategy; the first strategy feature indicates that the candidate delivery strategy is used to increase the budget consumption;

[0024] And / or, when the conversion rate of the strategy to be evaluated is less than the target conversion rate, a candidate delivery strategy having a strategy feature of a second strategy feature is selected as the target delivery strategy; the second strategy feature indicates that the candidate delivery strategy is used to improve the conversion rate.

[0025] Optionally, the strategy parameters include at least one of an advertisement delivery page, an advertisement target group, an advertisement data return method, and an advertisement delivery target.

[0026] Optionally, the delivery parameter includes at least one of delivery time, delivery cost, available quota and delivery income.

[0027] In a second aspect, the present invention provides an advertisement delivery device, characterized in that the device comprises:

[0028] A first acquisition module is used to take the delivery strategy currently executed by the target advertisement as the strategy to be evaluated, and acquire delivery parameters of the strategy to be evaluated;

[0029] An input module, used to input the delivery parameters and the strategy parameters of the strategy to be evaluated into a pre-trained target prediction model, and obtain the delivery performance of the target advertisement output by the target prediction model corresponding to the execution of the strategy to be evaluated;

[0030] A strategy determination module, configured to determine a target delivery strategy based on the delivery performance when the delivery performance does not meet preset requirements;

[0031] The strategy adjustment module is used to adjust the delivery strategy executed by the target advertisement to the target delivery strategy.

[0032] Optionally, the device further comprises:

[0033] The second acquisition module is used to obtain historical delivery parameters of historical delivery strategies and reference delivery performance;

[0034] An initial input module, used to input the historical delivery parameters and the historical strategy parameters of the historical delivery strategy into an initial prediction model, and obtain the predicted delivery performance output by the initial prediction model;

[0035] The parameter adjustment module is used to adjust the model parameters of the initial prediction model based on the predicted delivery performance and the reference delivery performance until the training stop condition is reached, and the current initial prediction model is determined as the target prediction model.

[0036] Optionally, the policy adjustment module includes:

[0037] A demand determination submodule, used for determining a strategy adjustment demand based on the delivery performance and the preset requirements;

[0038] The third acquisition submodule is used to obtain the strategy characteristics of each candidate delivery strategy from the pre-built delivery strategy library;

[0039] The selection submodule is used to select a candidate delivery strategy whose strategy characteristics meet the strategy adjustment requirements as the target delivery strategy.

[0040] Optionally, the delivery performance includes budget consumption and / or conversion rate; and the device further includes:

[0041] A first determination module is used to determine that the delivery performance meets the preset requirements when the budget consumption of the strategy to be evaluated is not less than the target consumption and the conversion rate is not less than the target conversion rate;

[0042] And, a second determination module is used to determine that the delivery performance does not meet the preset requirements when the budget consumption of the strategy to be evaluated is less than the target consumption and / or the conversion rate is less than the target conversion rate.

[0043] Optionally, the selection submodule is specifically used to:

[0044] When the budget consumption of the strategy to be evaluated is less than the target consumption, selecting a candidate delivery strategy for increasing the budget consumption as the target delivery strategy;

[0045] And / or, when the conversion rate of the strategy to be evaluated is less than the target conversion rate, a candidate delivery strategy for improving the conversion rate is selected as the target delivery strategy.

[0046] Optionally, the delivery parameter includes at least one of delivery time, delivery cost, available quota and delivery income.

[0047] Optionally, the strategy parameters include at least one of an advertisement delivery page, an advertisement target group, an advertisement data return method, and an advertisement delivery target.

[0048] In a third aspect, the present invention provides an electronic device comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0049] In a fourth aspect, the present invention provides a readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the method described in the first aspect above.

[0050] The advertisement delivery method provided in the embodiment of the present invention can determine the delivery performance of the delivery strategy currently executed by the target advertisement through the pre-trained target prediction model, and can realize the automatic evaluation of the delivery performance of the delivery strategy, without the need for manual analysis by relevant business personnel, which can greatly reduce the labor cost. At the same time, determining the delivery performance through the model can also avoid the problem of poor accuracy caused by the subjectivity of manual analysis to a certain extent, improve the accuracy of delivery performance evaluation, and then adjust the delivery strategy through delivery performance, which can improve the accuracy of delivery strategy adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 is a flowchart of a method for placing advertisements provided by an embodiment of the present invention;

[0053] Figure 2 is a flow chart of another advertisement delivery method provided by an embodiment of the present invention;

[0054] Figure 3 is a structural diagram of an advertisement delivery device provided by an embodiment of the present invention;

[0055] Figure 4 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Figure 1 is a flowchart of a method for delivering advertisements provided by an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0058] Step 101: taking the delivery strategy currently executed by the target advertisement as the strategy to be evaluated, and obtaining delivery parameters of the strategy to be evaluated.

[0059] Step 102: input the delivery parameters and the strategy parameters of the strategy to be evaluated into a pre-trained target prediction model to obtain the delivery performance of the target advertisement output by the target prediction model corresponding to the execution of the strategy to be evaluated.

[0060] Step 103: When the delivery performance does not meet the preset requirement, determine a target delivery strategy based on the delivery performance of the strategy to be evaluated.

[0061] Step 104: Adjust the delivery strategy executed by the target advertisement to the target delivery strategy.

[0062] With respect to the above steps 101 to 104, the embodiment of the present invention can be applied to any application product that has a demand for advertising. Accordingly, the above target advertisement refers to an advertisement that requires real-time adjustment of the delivery strategy, and can be any form of advertisement for any application product, for example, it can be a video advertisement or an advertisement in the form of graphics and text, and the embodiment of the present invention does not impose any limitation on this.

[0063] The strategy to be evaluated refers to the delivery strategy currently being executed by the target advertisement, that is, the target advertisement is currently delivered according to the strategy to be evaluated. The delivery strategy may include strategy parameters such as the advertisement delivery page, the target audience, the advertisement data return method, and the advertisement delivery target.

[0064] Among them, the advertising delivery page refers to the display page where the advertisement is located, that is, the page where the user can view the advertisement. For example, the advertising delivery page can be a start screen page, or a banner page within the platform, etc. The above-mentioned advertising target groups correspond to different user types. For example, the advertising target groups can be members or non-members. The above-mentioned advertising data feedback method corresponds to the type of advertising data. For example, for advertisements of video applications, its advertising data can be account registration data or video material data, so its delivery strategy can include advertising data feedback methods such as registration account feedback or material feedback. Among them, the above-mentioned advertising delivery target refers to the feedback expected by the advertisement, which can be downloading the application product, registering as a member in the application product, or launching the application product. Different advertising delivery pages, advertising target groups, advertising data feedback methods and advertising delivery targets can be set according to actual needs to obtain different delivery strategies.

[0065] Specifically, the above delivery parameters can be obtained through the data acquisition interface provided by the manufacturer of the target advertisement. Among them, the above delivery parameters may include data such as the delivery cost, available quota, delivery income, and delivery time of the strategy to be evaluated. Among them, the above delivery cost refers to the amount of money that has been consumed by the evaluation strategy, the above available quota refers to the difference between the total budget quota and the delivery cost, the above delivery income refers to the income generated for the manufacturer after the target advertisement adopts the strategy to be evaluated, and the above delivery time refers to the duration of the target advertisement using the strategy to be evaluated.

[0066] Among them, the above-mentioned target prediction model can be a pre-trained deep neural network model, and the target prediction model can be obtained by training based on historical delivery strategies, which is used to evaluate the delivery performance of the delivery strategy.

[0067] Among them, the above delivery performance may include budget consumption, conversion rate, etc., which are used to characterize the delivery effect of the target advertisement using the strategy to be evaluated in the future. Among them, budget consumption refers to the degree of consumption of the budget amount provided for the advertisement, and the above conversion rate refers to the proportion of effective advertising data brought by the advertisement. Specifically, budget consumption is usually related to the exposure of the advertisement. If the budget consumption is low, it means that the exposure of the target advertisement is low and the advertising delivery effect is poor. At the same time, the conversion rate is closely related to the advertising revenue. If the conversion rate is low, it means that the delivery effect of the target advertisement is poor.

[0068] Among them, the above-mentioned preset requirements can be pre-set by the manufacturer of the target advertisement, and can be set according to the purpose of the target advertisement. For example, the preset requirements can be set as: the delivery revenue is not less than the preset revenue value, or the exposure is not less than the preset exposure value, etc., and the embodiment of the present invention does not limit this. Further, after obtaining the delivery performance of the strategy to be evaluated, the embodiment of the present invention can determine the target delivery strategy based on the delivery performance when the delivery performance does not meet the above-mentioned preset requirements, and adjust the delivery strategy executed by the target advertisement to the target delivery strategy. Specifically, based on the delivery performance of the strategy to be evaluated, the delivery performance that needs to be adjusted can be determined according to actual needs, and the target delivery strategy that can adjust the delivery performance according to the needs can be selected to adjust the delivery strategy of the target advertisement. For example, when the exposure is less than the preset exposure value, it indicates that the exposure of the advertisement needs to be increased. At this time, the delivery strategy that can increase the exposure can be selected as the target delivery strategy.

[0069] Specifically, the embodiment of the present invention can pre-construct a delivery strategy library, which can include multiple delivery strategies to be selected and the performance characteristics of each delivery strategy to be selected, so that the embodiment of the present invention can select a target delivery strategy from the delivery strategies to be selected based on the performance characteristics of each delivery strategy to be selected.

[0070] In summary, the advertising delivery method provided by the embodiment of the present invention takes the delivery strategy currently executed by the target advertisement as the strategy to be evaluated, obtains the delivery parameters of the strategy to be evaluated; inputs the delivery parameters and the strategy parameters of the strategy to be evaluated into a pre-trained target prediction model to determine the delivery performance of the strategy to be evaluated; when the delivery performance does not meet the preset requirements, determines the target delivery strategy based on the delivery performance of the strategy to be evaluated, and adjusts the delivery strategy executed by the target advertisement to the target delivery strategy. In this way, the embodiment of the present invention determines the delivery performance of the delivery strategy currently executed by the target advertisement through the pre-trained target prediction model, which can realize the automatic evaluation of the delivery performance of the delivery strategy, without the need for manual analysis by relevant business personnel, and can greatly reduce the labor cost. At the same time, determining the delivery performance through the model can also avoid the problem of poor accuracy caused by the subjectivity of manual analysis to a certain extent, improve the accuracy of delivery performance evaluation, and then adjust the delivery strategy through delivery performance, which can improve the accuracy of delivery strategy adjustment.

[0071] Optionally, in an embodiment of the present invention, the target prediction model is trained in the following manner:

[0072] S21. Obtain historical delivery parameters and reference delivery performance of historical delivery strategies.

[0073] S22: input the historical delivery parameters and the historical strategy parameters of the historical delivery strategy into an initial prediction model, and obtain the predicted delivery performance output by the initial prediction model.

[0074] S23. Based on the predicted delivery performance and the reference delivery performance, the model parameters of the initial prediction model are adjusted until a training stop condition is reached, and the current initial prediction model is determined as a target prediction model.

[0075] Among them, the above-mentioned initial prediction model can be a pre-built initial neural network (Deep Neural Networks, DNN), which can include a multi-layer perception structure (Multilayer Perceptron, MLP). At the same time, since the model in the embodiment of the present invention needs to evaluate the delivery performance of the delivery strategy, and the delivery performance often includes multiple dimensions, the above-mentioned initial prediction model can also include a multi-task learning structure (Multi-gate Mixture-of-Experts, MMOE), so as to facilitate the evaluation of delivery performance in multiple dimensions.

[0076] The above historical delivery strategies refer to different delivery strategies adopted by different advertisements within a historical period (e.g., a week or a month). Accordingly, the above historical delivery parameters refer to data such as delivery costs, available quotas, delivery revenues, and delivery time of historical delivery strategies within a historical period, and accordingly, the above historical strategy parameters refer to strategy parameters included in historical delivery strategies. The above reference delivery performance can be evaluated by relevant personnel according to the advertising delivery effects of different historical delivery strategies, and the above reference delivery performance can be obtained by receiving input information from relevant personnel.

[0077] The above-mentioned predicted delivery performance is data output by the initial prediction model based on historical delivery parameters and historical strategy parameters. The embodiment of the present invention can directly read the output data of the initial prediction model to obtain the predicted delivery performance.

[0078] Among them, the above-mentioned training stop condition can be that the training time reaches a preset time threshold, or the confidence of the model is not less than a preset confidence threshold, or the loss function of the model is not greater than a preset loss threshold. Different training stop conditions can be determined according to actual conditions, and the embodiment of the present invention does not limit this. Further, when the training stop condition is reached, it indicates that the prediction effect of the current model has met the requirements, and the current initial prediction model can be determined as the target prediction model at this time.

[0079] In an embodiment of the present invention, historical delivery parameters and reference delivery performance of a historical delivery strategy are obtained; the historical delivery parameters and the historical strategy parameters of the historical delivery strategy are input into an initial prediction model, and the predicted delivery performance output by the initial prediction model is obtained; based on the predicted delivery performance and the reference delivery performance, the model parameters of the initial prediction model are adjusted until the training stop condition is reached, and the current initial prediction model is determined as the target prediction model. In this way, the embodiment of the present invention adjusts the model parameters of the initial prediction model through historical delivery parameters, historical strategy parameters, and reference delivery performance, and can complete the training of the initial prediction model to obtain a target prediction model that meets the requirements.

[0080] Optionally, in the embodiment of the present invention, the operation of determining the target delivery strategy based on the delivery performance may specifically include:

[0081] S31. Determine a strategy adjustment requirement based on the delivery performance and the preset requirement.

[0082] S32: Obtain the strategy characteristics of each candidate delivery strategy from a pre-built delivery strategy library.

[0083] S33: Select a candidate delivery strategy whose strategy characteristics meet the strategy adjustment requirements as the target delivery strategy.

[0084] Wherein, the above-mentioned strategy adjustment demand is determined based on the delivery performance and preset requirements, and the above-mentioned strategy adjustment demand can be to make the delivery performance meet the preset requirements. Wherein, the above-mentioned delivery strategy library can be pre-constructed, which contains multiple delivery strategies to be selected and the strategy characteristics of each delivery strategy to be selected, wherein the strategy characteristics are used to characterize the performance advantages of the delivery strategy, and the performance advantages of different delivery strategies are different. For example, the strategy characteristics of the delivery strategy A to be selected can be to increase the budget consumption, and for another example, the strategy characteristics of the delivery strategy B to be selected can be to increase the conversion rate. Wherein, the budget consumption refers to the degree of consumption of the budget amount provided for the advertisement, and the above-mentioned conversion rate refers to the proportion of effective advertising data brought by the advertisement. Specifically, the above-mentioned delivery strategies to be selected and the strategy characteristics can be input by relevant personnel, or can be determined based on the delivery performance of historical delivery strategies, and the embodiments of the present invention are not limited to this.

[0085] Furthermore, the embodiment of the present invention can determine the strategy adjustment requirements based on the delivery performance of the strategy to be evaluated, and then select the delivery strategy to be selected that meets the corresponding strategy adjustment requirements as the target delivery strategy according to the performance advantages of each delivery strategy to be selected. In this way, the strategy executed by the target advertisement can be adjusted according to the performance of the delivery strategy to meet the strategy adjustment requirements and improve the flexibility of advertisement delivery.

[0086] Optionally, the delivery performance includes budget consumption and / or conversion rate. After the operation of obtaining the delivery performance of the target advertisement output by the target prediction model executing the strategy to be evaluated, the embodiment of the present invention may further include:

[0087] S41: When the budget consumption of the strategy to be evaluated is not less than the target consumption and the conversion rate is not less than the target conversion rate, determine that the delivery performance meets the preset requirements.

[0088] And, S42, when the budget consumption of the strategy to be evaluated is less than the target consumption, and / or the conversion rate is less than the target conversion rate, it is determined that the delivery performance does not meet the preset requirements.

[0089] Among them, the above-mentioned target consumption and target conversion rate can be preset and can be set according to the actual needs of the advertising producer, and the embodiment of the present invention does not limit this. Specifically, when the budget consumption is less than the target consumption, it indicates that the exposure of the strategy to be evaluated is low, resulting in poor advertising delivery effect, and the delivery performance of the strategy to be evaluated does not meet the preset requirements. Correspondingly, when the conversion rate is less than the target conversion rate, it indicates that the profit of adopting the strategy to be evaluated is low, the advertising delivery effect is poor, and the delivery performance of the strategy to be evaluated does not meet the preset requirements.

[0090] Among them, when the budget consumption is not less than the target consumption and the conversion rate is not less than the target conversion rate, it indicates that the currently adopted strategy to be evaluated has met the advertising delivery needs. At this time, the strategy to be evaluated can continue to be used to deliver the target advertisement, that is, the delivery strategy of the target advertisement will not be adjusted for the time being.

[0091] Accordingly, when the budget consumption is less than the target consumption, and / or the conversion rate is less than the target conversion rate, it indicates that the currently adopted strategy to be evaluated has low exposure or low revenue. At this time, its delivery performance does not meet the advertising delivery needs, then the delivery strategy of the target advertisement can be adjusted.

[0092] In an embodiment of the present invention, the budget consumption and / or conversion rate can be used as the delivery performance, and whether the delivery performance of the strategy to be evaluated meets the preset requirements can be judged based on the budget consumption and / or conversion rate, which can ensure the objectivity of the judgment and further ensure the accuracy of the strategy adjustment.

[0093] Optionally, the operation of selecting the candidate delivery strategy whose strategy characteristics meet the strategy adjustment requirement as the target delivery strategy may specifically include:

[0094] S311. When the budget consumption of the strategy to be evaluated is less than the target consumption, select a candidate delivery strategy having a first strategy feature as the target delivery strategy; the first strategy feature indicates that the candidate delivery strategy is used to increase the budget consumption.

[0095] And / or, S312, when the conversion rate of the strategy to be evaluated is less than the target conversion rate, selecting a candidate delivery strategy whose strategy feature is a second strategy feature as the target delivery strategy; the second strategy feature indicates that the candidate delivery strategy is used to improve the conversion rate.

[0096] Among them, the strategy feature is used to characterize the performance advantage of the delivery strategy, and the performance advantages of different delivery strategies are different. For example, the strategy feature of the delivery strategy A to be selected can be to increase the budget consumption, and for another example, the strategy feature of the delivery strategy B to be selected can be to increase the conversion rate. Specifically, the above-mentioned strategy features can be input by relevant personnel, or can be determined based on the delivery performance of historical delivery strategies, and the embodiments of the present invention are not limited to this. Exemplarily, since the budget consumption is related to the exposure, the advertising delivery page is a popular page (for example: open screen advertising), or the delivery strategy with the advertising target population as all users can often increase the budget consumption, and the strategy feature of this type of delivery strategy is the first strategy feature. In another exemplary example, the conversion rate is related to the advertising cost and revenue, and the advertising target population is member users, or the delivery strategy with the advertising delivery page as a non-hot page can increase advertising revenue and reduce advertising costs, thereby improving the conversion rate, and the strategy feature of this type of delivery strategy is the second strategy feature.

[0097] Specifically, when the budget consumption is less than the target consumption, it indicates that the exposure of the strategy to be evaluated is low. Therefore, the strategy adjustment requirement is to increase the budget consumption. Then, the candidate delivery strategy for increasing the budget consumption can be selected as the target delivery strategy to increase the exposure of the target advertisement and improve the advertising delivery effect. When the conversion rate is less than the target conversion rate, it indicates that the profit of the strategy to be evaluated is low. Therefore, the strategy adjustment requirement can be to increase the conversion rate. Then, the candidate delivery strategy for increasing the conversion rate can be selected as the target delivery strategy to increase the profit of the target advertisement and improve the advertising delivery effect. In this way, the corresponding candidate delivery strategy is selected as the target delivery strategy based on the strategy characteristics to meet the strategy adjustment requirements and ensure the advertising delivery effect.

[0098] In the embodiment of the present invention, the delivery strategy can be adjusted in time based on the budget consumption and / or conversion rate of the strategy to be evaluated, and the strategy adjustment can be achieved by calling the RTA interface provided by the advertising platform, and the strategy adjustment can be achieved by calling the RTA interface and inputting the strategy parameters of the target delivery strategy. Furthermore, the RTA interfaces of different advertising platforms may be different, and the embodiment of the present invention does not limit this.

[0099] Figure 2 is a flow chart of another advertisement delivery method provided by an embodiment of the present invention. Figure 2 As shown, Figure 2The media advertising platform in the description refers to the platform where the advertisement is delivered. The strategy rules, strategy consumption, strategy budget and strategy income of the currently executed delivery strategy are obtained through the media advertising platform, wherein the strategy rules correspond to the above-mentioned strategy parameters, and the strategy consumption, strategy budget and strategy income correspond to the above-mentioned delivery parameters. Furthermore, the strategy parameters and delivery parameters are input into the deep network model (i.e., the aforementioned target prediction model), and the delivery performance of the strategy to be evaluated is obtained by reading the output of the deep network model, and the delivery performance includes the budget consumption and the conversion rate.

[0100] Furthermore, the budget consumption and conversion rate predicted by the model are used to determine whether the delivery strategy needs to be adjusted. If the budget consumption is not less than the target consumption, and the conversion rate is not less than the target conversion rate, it is determined that the delivery performance meets the preset requirements, and there is no need to adjust the delivery strategy. Correspondingly, if the budget consumption is less than the target consumption, and / or the conversion rate is less than the target conversion rate, it is determined that the delivery performance does not meet the preset requirements, and it is necessary to adjust the delivery strategy. Furthermore, if the delivery strategy needs to be adjusted, the corresponding target delivery strategy is selected from the delivery strategy library and output to the media advertising platform. Correspondingly, if no adjustment is required, the current strategy to be evaluated can be maintained.

[0101] In summary, the advertising delivery method provided by the embodiment of the present invention takes the delivery strategy currently executed by the target advertisement as the strategy to be evaluated, obtains the delivery parameters of the strategy to be evaluated; inputs the delivery parameters and the strategy parameters of the strategy to be evaluated into the pre-trained target prediction model, obtains the delivery performance corresponding to the target advertisement executing the strategy to be evaluated output by the target prediction model; when the delivery performance does not meet the preset requirements, determines the target delivery strategy based on the delivery performance, and adjusts the delivery strategy executed by the target advertisement to the target delivery strategy. In this way, the embodiment of the present invention determines the delivery performance of the delivery strategy currently executed by the target advertisement through the pre-trained target prediction model, and can realize the automatic evaluation of the delivery performance of the delivery strategy, without the need for manual analysis by relevant business personnel, which can greatly reduce the labor cost. At the same time, determining the delivery performance through the model can also avoid the problem of poor accuracy caused by the subjectivity of manual analysis to a certain extent, improve the accuracy of delivery performance evaluation, and then adjust the delivery strategy through delivery performance, which can improve the accuracy of delivery strategy adjustment.

[0102] Figure 3 is a structural diagram of an advertisement delivery device provided by an embodiment of the present invention, such as Figure 3 As shown, the device 20 may include:

[0103] The first acquisition module 201 is used to take the delivery strategy currently executed by the target advertisement as the strategy to be evaluated, and acquire delivery parameters of the strategy to be evaluated;

[0104] An input module 202 is used to input the delivery parameters and the strategy parameters of the strategy to be evaluated into a pre-trained target prediction model to obtain the delivery performance of the target advertisement output by the target prediction model corresponding to the execution of the strategy to be evaluated;

[0105] A strategy determination module 203, configured to determine a target delivery strategy based on the delivery performance when the delivery performance does not meet preset requirements;

[0106] The strategy adjustment module 204 is used to adjust the delivery strategy executed by the target advertisement to the target delivery strategy.

[0107] Optionally, the device further comprises:

[0108] The second acquisition module is used to obtain historical delivery parameters of historical delivery strategies and reference delivery performance;

[0109] An initial input module, used to input the historical delivery parameters and the historical strategy parameters of the historical delivery strategy into an initial prediction model, and obtain the predicted delivery performance output by the initial prediction model;

[0110] The parameter adjustment module is used to adjust the model parameters of the initial prediction model based on the predicted delivery performance and the reference delivery performance until the training stop condition is reached, and the current initial prediction model is determined as the target prediction model.

[0111] Optionally, the policy adjustment module 203 includes:

[0112] A demand determination submodule, used for determining a strategy adjustment demand based on the delivery performance and the preset requirements;

[0113] The third acquisition submodule is used to obtain the strategy characteristics of each candidate delivery strategy from the pre-built delivery strategy library;

[0114] The selection submodule is used to select a candidate delivery strategy whose strategy characteristics meet the strategy adjustment requirements as the target delivery strategy.

[0115] Optionally, the device further comprises:

[0116] A first determination module is used to determine that the delivery performance meets the preset requirements when the budget consumption of the strategy to be evaluated is not less than the target consumption and the conversion rate is not less than the target conversion rate;

[0117] And, a second determination module is used to determine that the delivery performance does not meet the preset requirements when the budget consumption of the strategy to be evaluated is less than the target consumption and / or the conversion rate is less than the target conversion rate.

[0118] Optionally, the selection submodule is specifically used to:

[0119] When the budget consumption of the strategy to be evaluated is less than the target consumption, selecting a candidate delivery strategy for increasing the budget consumption as the target delivery strategy;

[0120] And / or, when the conversion rate of the strategy to be evaluated is less than the target conversion rate, a candidate delivery strategy for improving the conversion rate is selected as the target delivery strategy.

[0121] Optionally, the delivery parameter includes at least one of delivery time, delivery cost, available quota and delivery income.

[0122] Optionally, the strategy parameters include at least one of an advertisement delivery page, an advertisement target group, an advertisement data return method, and an advertisement delivery target.

[0123] In summary, the advertising delivery device provided by the embodiment of the present invention can determine the delivery performance of the delivery strategy currently executed by the target advertisement through the pre-trained target prediction model, and can realize the automatic evaluation of the delivery performance of the delivery strategy, without the need for manual analysis by relevant business personnel, which can greatly reduce the labor cost. At the same time, determining the delivery performance through the model can also avoid the problem of poor accuracy caused by the subjectivity of manual analysis to a certain extent, improve the accuracy of delivery performance evaluation, and then adjust the delivery strategy through delivery performance, which can improve the accuracy of delivery strategy adjustment.

[0124] The present invention also provides an electronic device, see Figure 4 , including: a processor 301, a memory 302, and a computer program 3021 stored in the memory and executable on the processor, wherein the processor implements the advertisement delivery method of the aforementioned embodiment when executing the program.

[0125] The present invention also provides a readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the advertisement delivery method of the aforementioned embodiment.

[0126] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0127] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0128] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0129] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0130] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0131] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present invention. The present invention may also be implemented as a device or apparatus program for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0132] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0133] Those skilled in the art can 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.

[0134] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0135] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An advertisement delivery method, characterized in that: The method comprises: The delivery strategy currently executed by the target advertisement is used as the strategy to be evaluated, and delivery parameters of the strategy to be evaluated are obtained; Input the delivery parameters and the strategy parameters of the strategy to be evaluated into a pre-trained target prediction model, and obtain the delivery performance of the target advertisement output by the target prediction model corresponding to the execution of the strategy to be evaluated; In the case where the delivery performance does not meet the preset requirements, determining a target delivery strategy based on the delivery performance; The delivery strategy executed by the target advertisement is adjusted to the target delivery strategy.

2. The method according to claim 1, characterized in that The target prediction model is trained in the following way: Get the historical delivery parameters and reference delivery performance of the historical delivery strategy; Inputting the historical delivery parameters and the historical strategy parameters of the historical delivery strategy into an initial prediction model, and obtaining the predicted delivery performance output by the initial prediction model; Based on the predicted delivery performance and the reference delivery performance, the model parameters of the initial prediction model are adjusted until a training stop condition is reached, and the current initial prediction model is determined as a target prediction model.

3. The method according to claim 1, characterized in that The determining of the target delivery strategy based on the delivery performance includes: Determining a strategy adjustment requirement based on the delivery performance and the preset requirements; Obtaining the strategy characteristics of each candidate delivery strategy from a pre-built delivery strategy library; A candidate delivery strategy whose strategy characteristics meet the strategy adjustment requirements is selected as the target delivery strategy.

4. The method according to claim 3, characterized in that The delivery performance includes budget consumption and / or conversion rate; after obtaining the delivery performance of the target advertisement output by the target prediction model executing the strategy to be evaluated, the method further includes: When the budget consumption of the strategy to be evaluated is not less than the target consumption, and the conversion rate is not less than the target conversion rate, determining that the delivery performance meets the preset requirements; Furthermore, when the budget consumption of the strategy to be evaluated is less than the target consumption, and / or the conversion rate is less than the target conversion rate, it is determined that the delivery performance does not meet the preset requirements.

5. The method according to claim 4, characterized in that The selected delivery strategy whose strategy characteristics meet the strategy adjustment requirements as the target delivery strategy includes: When the budget consumption of the strategy to be evaluated is less than the target consumption, selecting a candidate delivery strategy whose strategy feature is a first strategy feature as the target delivery strategy; the first strategy feature indicates that the candidate delivery strategy is used to increase the budget consumption; And / or, when the conversion rate of the strategy to be evaluated is less than the target conversion rate, a candidate delivery strategy having a strategy feature of a second strategy feature is selected as the target delivery strategy; the second strategy feature indicates that the candidate delivery strategy is used to improve the conversion rate.

6. The method according to any one of claims 1 to 5, characterized in that: The strategy parameters include at least one of an advertisement delivery page, an advertisement target group, an advertisement data return method, and an advertisement delivery target.

7. The method according to any one of claims 1 to 5, characterized in that: The delivery parameters include at least one of delivery time, delivery cost, available quota and delivery income.

8. An advertisement delivery device, characterized in that: The device comprises: A first acquisition module is used to take the delivery strategy currently executed by the target advertisement as the strategy to be evaluated, and acquire delivery parameters of the strategy to be evaluated; An input module, used to input the delivery parameters and the strategy parameters of the strategy to be evaluated into a pre-trained target prediction model, and obtain the delivery performance of the target advertisement output by the target prediction model corresponding to the execution of the strategy to be evaluated; A strategy determination module, configured to determine a target delivery strategy based on the delivery performance when the delivery performance does not meet preset requirements; The strategy adjustment module is used to adjust the delivery strategy executed by the target advertisement to the target delivery strategy.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

10. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 7.

Images