Advertisement placement effect prediction method and device

Abstract

Embodiments of the present invention provide an advertisement placement effect prediction method and a device. The method comprises: acquiring a plan identifier and an estimated placement cost that correspond to an advertisement placement plan; on the basis of the plan identifier and the estimated placement cost, determining placement function parameters in an advertisement placement function and weight function parameters in a weight function, wherein the advertisement placement function is used for identifying a relationship between a placement cost and a placement effect, and the weight function is used for determining the weight of the placement effect that is obtained by means of the advertisement placement function; and before the advertisement placement plan is placed, on the basis of the placement function parameters, the weight function parameters, the advertisement placement function, and the weight function, determining advertisement placement effects respectively corresponding to different placement costs, wherein said different placement costs at least comprise the estimated placement cost.

Description

Method and device for predicting advertising effect

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on August 29, 2023, with application number 202311102112.3 and application name “Method and Device for Predicting Advertising Effects”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present invention relates to the field of network information processing, and in particular to a method and device for predicting the effect of advertisement delivery. Background Art

[0003] With the rapid development of science and technology, there are more and more ways to promote information, and the scope of application is becoming increasingly broad. The main methods of information promotion can include advertising promotion and human promotion. Specifically, when advertisers implement information promotion operations by placing advertisements on the Internet, in order to achieve the promotion goals or objectives that advertisers want to achieve, advertisers often need to constantly modify the content of the plan. After a period of time after the modified plan is released, they can observe the advertising promotion effect. If the advertising promotion effect does not meet the requirements, they need to further adjust the plan content to obtain the advertising promotion effect that meets user needs. However, this not only incurs high trial and error costs for advertisers, but also faces the risk of customer churn.

[0004] Summary of the Invention

[0005] The embodiments of the present invention provide a method and device for predicting the effect of advertising delivery, which can obtain the effect of advertising delivery before the advertising delivery plan is launched. This not only reduces the trial and error cost of advertisers, but also helps to improve the efficiency of advertisers in making decisions.

[0006] In a first aspect, an embodiment of the present invention provides a method for predicting the effect of advertising delivery, comprising:

[0007] Obtaining a plan identifier corresponding to the advertising delivery plan and an estimated delivery cost;

[0008] Based on the plan identifier and the estimated delivery cost, determining a delivery function parameter in an advertisement delivery function and a weight function parameter in a weight function, wherein the advertisement delivery function is used to identify the relationship between the delivery cost and the delivery effect, and the weight function is used to determine the weight of the delivery effect obtained by the advertisement delivery function;

[0009] Before delivering the advertising delivery plan, based on the delivery function parameters, weight function parameters, advertising delivery function and the weight function, the advertising delivery effects corresponding to different delivery costs are determined, and the different delivery costs at least include estimated delivery costs.

[0010] In a second aspect, an embodiment of the present invention provides a device for predicting the effect of advertising delivery, comprising:

[0011] A first acquisition module is used to obtain a plan identifier corresponding to an advertisement delivery plan and an estimated delivery cost;

[0012] A first determination module is configured to determine, based on the plan identifier and the estimated delivery cost, delivery function parameters in an advertisement delivery function and weight function parameters in a weight function, wherein the advertisement delivery function is configured to identify a relationship between the delivery cost and the delivery effect, and the weight function is configured to determine a weight of the delivery effect obtained by the advertisement delivery function;

[0013] The first processing module is used to determine the advertising delivery effects corresponding to different delivery costs based on the delivery function parameters, weight function parameters, advertising delivery function and the weight function before delivering the advertising delivery plan, and the different delivery costs at least include estimated delivery costs.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device comprising: a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein when the one or more computer instructions are executed by the processor, the method for predicting the advertising delivery effect in the first aspect mentioned above is implemented.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program, wherein the computer program enables a computer to implement the method for predicting the effect of advertising delivery in the first aspect when executed.

[0016] In a fifth aspect, an embodiment of the present invention provides a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, causes the one or more processors to execute the steps in the method for predicting the effect of advertising delivery shown in the first aspect above.

[0017] The method and device for predicting the advertising delivery effect provided in this embodiment obtain a plan identifier and an estimated delivery cost corresponding to the advertising delivery plan, and then determine the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function based on the plan identifier and the estimated delivery cost. Before delivering the advertising delivery plan, the advertising delivery effects corresponding to different delivery costs are determined based on the delivery function parameters, the weight function parameters, the advertising delivery function and the weight function. This effectively achieves that before delivering the advertising delivery plan, the advertising delivery effects corresponding to different delivery costs can be directly determined. In this way, without the need for the user to set more information such as the target group, more and clearer advertising delivery effects can be displayed to advertisers. The displayed advertising delivery effects corresponding to different delivery costs can not only assist advertisers in making promotion decisions and improve the advertisers' decision-making efficiency, but also help promote network activity and increase the revenue of the network platform, further ensuring the practicality of the method and facilitating market promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to 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 any creative work.

[0019] FIG1 is a schematic diagram of a scenario of a method for predicting the effect of advertising provided by an embodiment of the present invention;

[0020] FIG2 is a flow chart of a method for predicting the effect of advertising provided by an embodiment of the present invention;

[0021] FIG3 is a flow chart of determining the advertising delivery effects corresponding to different delivery costs based on the delivery function parameters, weight function parameters, the advertising delivery function, and the weight function according to an embodiment of the present invention;

[0022] FIG4 is a flow chart of another method for predicting the effect of advertising provided by an embodiment of the present invention;

[0023] FIG5 is a flow chart of another method for predicting the effect of advertising provided by an embodiment of the present invention;

[0024] FIG6 is a schematic diagram showing the principle of a method for predicting the effect of advertising provided by an application embodiment of the present invention;

[0025] FIG7 is a schematic diagram of model training features provided by an application embodiment of the present invention;

[0026] FIG8 is a schematic diagram of the structure of an apparatus for predicting the effect of advertising provided by an embodiment of the present invention;

[0027] FIG9 is a schematic structural diagram of an electronic device corresponding to the apparatus for predicting advertising delivery effects provided by the embodiment shown in FIG8 . DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0029] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two, but does not exclude the inclusion of at least one.

[0030] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0031] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0032] It should also be noted that the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such product or system. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the product or system comprising the element.

[0033] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0034] Definition of terms:

[0035] ctr: click through rate, ad click-through rate.

[0036] ocpc: optimized cost per click, a smart bidding method with conversion as the goal. Unlike CPC bidding, ocpc will give different bids based on the current ad conversion rate.

[0037] Bid: The ad bid for a single request. Different bids will be given for different requests based on the traffic value.

[0038] To facilitate understanding of the specific implementation process and effects of the method and device for predicting the effect of advertising placement in this embodiment, the following briefly describes the relevant technologies:

[0039] With the rapid development of science and technology, there are more and more ways to promote information, and the scope of application is becoming increasingly broad. The main methods of information promotion can include advertising promotion and human promotion. Specifically, when advertisers implement information promotion operations by placing advertisements on the Internet, in order to achieve the promotion goals or objectives that advertisers want to achieve, advertisers often need to constantly modify the content of the plan. After a period of time after the modified plan is released, they can observe the advertising promotion effect. If the advertising promotion effect does not meet the requirements, they need to further adjust the plan content to obtain the advertising promotion effect that meets user needs. However, this not only incurs high trial and error costs for advertisers, but also faces the risk of customer churn.

[0040] In order to solve the above technical problems, a method for estimating advertising effects has been proposed in related technologies. Specifically, this method requires advertisers to first determine information such as the target user group, target time period, etc., and then perform effect estimation based on the determined target user group and target time period. In this case, advertisers need to input more information, thereby reducing the user experience.

[0041] In other instances, related technologies provide another method for estimating advertising effects, which completely relies on a pre-trained network model to implement advertising effect estimation operations. Since the advertising effect estimation operation process does not take into account the monotonicity of advertising bids and budgets on advertising effects, it is easy to produce abnormal results such as higher budgets and lower exposures, which greatly reduces the accuracy of advertising effect estimation.

[0042] In order to solve the above technical problems, this embodiment provides a method and device for predicting the effect of advertising. As shown in FIG1 , the execution subject of the method for predicting the effect of advertising can be a device for predicting the effect of advertising. It should be noted that the device for predicting the effect of advertising can be implemented as a local server or a server in the cloud. In this case, the method for predicting the effect of advertising can be executed in the cloud. Several computing nodes (cloud servers) can be deployed in the cloud, and each computing node has computing, storage and other processing resources. In the cloud, multiple computing nodes can be organized to provide a certain service. Of course, a computing node can also provide one or more services. The way to provide the service in the cloud can be to provide a service interface to the outside world, and the user calls the service interface to use the corresponding service. The service interface includes a software development kit (SDK), an application programming interface (API), and the like.

[0043] The device for predicting the effectiveness of advertising placement can be communicatively connected to a client, where the client is used by advertisers to determine the effectiveness of advertising placement. The client can be any computing device with sufficient data transmission capabilities. In specific implementations, the client can be a mobile phone, a personal computer (PC), a tablet computer, a configuration application, and the like. Furthermore, the basic structure of the client can include at least one processor. The number of processors depends on the configuration and type of the client. The client can also include memory, which can be volatile, such as random access memory (RAM), non-volatile, such as read-only memory (ROM), flash memory, or both. The memory typically stores an operating system (OS), one or more application programs, and may also store program data. In addition to the processing unit and memory, the client also includes some basic configurations, such as a network card chip, an I / O bus, a display component, and some peripheral devices. Optionally, some peripheral devices may include, for example, a keyboard, a mouse, a stylus, a printer, and the like. Other peripheral devices are well known in the art and are not described in detail here.

[0044] An advertising effectiveness prediction device refers to a device that can provide advertising effectiveness determination operations within a network virtual environment. It typically refers to a device that utilizes a network to perform information planning and advertising effectiveness determination operations. Physically, an advertising effectiveness prediction device can be any device that can provide computing services, respond to advertising effectiveness determination requests, and perform advertising effectiveness determination operations based on these determination requests. Examples include cluster servers, conventional servers, cloud servers, cloud hosts, virtual centers, and the like. The advertising effectiveness prediction device primarily comprises a processor, hard drive, memory, system bus, and other components, similar to a general-purpose computer architecture.

[0045] In the above embodiment, the client is connected to the device for predicting the effect of advertising delivery through a network connection, and the network connection can be a wireless or wired network connection. If the client can be connected to the device for predicting the effect of advertising delivery through a communication connection, the network standard of the mobile network can be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), WiMax, 5G, 6G, etc.

[0046] In an embodiment of the present application, the client is used for use by advertiser users to implement the operation of determining the effect of advertising delivery. Specifically, when the advertiser user has a demand for determining the effect of advertising delivery, a request for determining the effect of advertising delivery can be generated. The request for determining the effect of advertising delivery can include one or more advertising delivery plans to be analyzed. For each advertising delivery plan, in order to implement the operation of determining the effect of advertising delivery, the request for determining the effect of advertising delivery can be sent to a device for predicting the effect of advertising delivery.

[0047] An advertising delivery effect prediction device is used to receive a request for determining the advertising delivery effect sent by a client, and then obtain a plan identifier corresponding to the advertising delivery plan and an estimated delivery cost based on the request for determining the advertising delivery effect. The estimated delivery cost may include at least one of the following: an estimated delivery budget and an estimated delivery bid. The above-mentioned estimated delivery budget is the fee that a user needs to pay when performing a one-day advertising promotion operation, for example: 10,000 / day, 100,000 / day or 200,000 / day, etc. The estimated delivery bid is the price set by the advertiser that a user needs to pay when clicking on an advertisement once, for example: 8 yuan / time, 10 yuan / time, 15 yuan / time, 20 yuan / time, etc.

[0048] Specifically, an advertising delivery function and a weight function for determining the advertising delivery effect are pre-configured in the device for predicting the advertising delivery effect, wherein the advertising delivery function is used to identify the relationship between the delivery cost and the delivery effect, and the weight function is used to determine the weight of the delivery effect obtained by the advertising delivery function. For the advertising delivery function and the weight function, the advertising delivery function includes one or more delivery function parameters to be determined, and the weight function includes weight function parameters to be determined. Since the delivery function parameters and the weight function parameters are related to the estimated delivery cost and the advertising delivery plan corresponding to the advertising delivery plan, after obtaining the plan identifier and the estimated delivery cost, the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function can be determined based on the plan identifier and the estimated delivery cost.

[0049] Since the advertising delivery function and the weight function can be used to determine the effect of advertising delivery, before the advertising delivery plan is delivered, in order to accurately determine the effect of advertising delivery, after determining the delivery function parameters, the weight function parameters, the advertising delivery function and the weight function, the delivery function parameters, the weight function parameters, the advertising delivery function and the weight function can be analyzed and processed to determine the advertising delivery effects corresponding to different delivery costs. Different delivery costs include at least one of the following: a first type of cost greater than the expected delivery cost, a second type of cost less than the expected delivery cost, and the expected delivery cost. It should be noted that the delivery cost is positively correlated with the advertising delivery effect, that is, the advertising delivery effect corresponding to the first type of cost is greater than the advertising delivery effect corresponding to the expected delivery cost, and the advertising delivery effect corresponding to the expected delivery cost is greater than the advertising delivery effect corresponding to the second type of cost.

[0050] The technical solution provided in this embodiment effectively realizes that before the advertising delivery plan is launched, the advertising delivery effects corresponding to different delivery costs can be directly determined. In this way, without the need for users to set more information such as target groups, more and clearer advertising delivery effects can be displayed to advertisers. The advertising delivery effects corresponding to different delivery costs displayed can not only assist advertisers in making promotion decisions and improve the decision-making efficiency of advertisers, but also help promote network activity and increase the revenue of the network platform, further ensuring the practicality of this method.

[0051] Some embodiments of the present invention are described in detail below with reference to the accompanying drawings. The following embodiments and features thereof may be combined with one another unless they conflict with each other. Furthermore, the sequence of steps in the following method embodiments is provided for illustrative purposes only and is not intended to be a strict limitation.

[0052] FIG2 is a flow chart of a method for predicting the effect of advertising provided by an embodiment of the present invention; Referring to FIG2 , this embodiment provides a method for predicting the effect of advertising, the execution subject of which is a device for predicting the effect of advertising. It can be understood that the device for predicting the effect of advertising can be implemented as software, or a combination of software and hardware. Specifically, when the device for predicting the effect of advertising is implemented as hardware, it can be various electronic devices with an operation for determining the effect of advertising, including but not limited to personal computers, servers, etc. When the device for determining the effect of advertising is implemented as software, it can be installed in the electronic devices listed above. Based on the above-mentioned device for predicting the effect of advertising, the method for predicting the effect of advertising can include:

[0053] Step S201: Acquire a plan identifier corresponding to an advertisement delivery plan and an estimated delivery cost.

[0054] Step S202: Based on the plan identifier and the estimated delivery cost, determine the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function, wherein the advertising delivery function is used to identify the relationship between the delivery cost and the delivery effect, and the weight function is used to determine the weight of the delivery effect obtained through the advertising delivery function.

[0055] Step S203: Before the advertisement delivery plan is delivered, based on delivery function parameters, weight function parameters, advertisement delivery function and weight function, the advertisement delivery effects corresponding to different delivery costs are determined, where the different delivery costs at least include estimated delivery costs.

[0056] The following is a detailed description of the specific implementation process and results of each of the above steps:

[0057] Step S201: Acquire a plan identifier corresponding to an advertisement delivery plan and an estimated delivery cost.

[0058] During or after the advertiser configures an advertising plan, the configured advertising plan may be associated with a plan identifier, which serves as a unique identifier for the advertising plan. That is, different advertising plans may be associated with different plan identifiers. To determine the effectiveness of an advertisement before the advertisement is delivered, during or after the advertiser configures the advertising plan, the advertising effectiveness prediction device may obtain the plan identifier and estimated delivery cost corresponding to the advertisement. In some examples, the estimated delivery cost may include at least one of the following: an estimated delivery budget and an estimated delivery bid. The estimated delivery budget is the cost a user will pay for one day, one week, or one month of advertising promotion, such as 10,000 yuan / day, 100,000 yuan / day, 200,000 yuan / day, 800,000 yuan / week, or 1,000,000 yuan / week. The estimated delivery bid is the price set or pre-configured by the advertiser for a user to pay for a single click on an advertisement, such as 8 yuan / click, 10 yuan / click, 15 yuan / click, or 20 yuan / click.

[0059] In some instances, the plan identifier and estimated delivery cost corresponding to the advertising delivery plan can be obtained through human-computer interaction operations. In this case, obtaining the plan identifier and estimated delivery cost corresponding to the advertising delivery plan can include: displaying an interactive interface for configuring the advertising delivery plan; obtaining parameter configuration operations entered by the user on the interactive interface; and obtaining the plan identifier and estimated delivery cost corresponding to the advertising delivery plan based on the parameter configuration operations.

[0060] In other instances, the plan identifier and the estimated delivery cost can be obtained not only through human-computer interaction operations, but also through the client. In this case, obtaining the plan identifier and the estimated delivery cost corresponding to the advertising delivery plan may include: obtaining a client that is in communication with the advertising delivery effect prediction device, and determining the advertising delivery plan stored in the client; actively or passively obtaining the advertising delivery plan through the client, and then determining the estimated delivery cost and the plan identifier based on the advertising delivery plan, thereby effectively ensuring the accuracy and reliability of the acquisition of the estimated delivery cost and the plan identifier.

[0061] Step S202: Based on the plan identifier and the estimated delivery cost, determine the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function, wherein the advertising delivery function is used to identify the relationship between the delivery cost and the delivery effect, and the weight function is used to determine the weight of the delivery effect obtained through the advertising delivery function.

[0062] The prediction device for the effect of advertising delivery is equipped with an advertising delivery function and a weighting function for determining the effect of advertising delivery. The advertising delivery function is used to identify the relationship between delivery cost and delivery effect, and the weighting function is used to determine the weight of the delivery effect obtained by the advertising delivery function. The advertising delivery function can be a monotonic function used to identify the positive correlation between delivery cost and delivery effect. For example, the advertising delivery function can be expressed as y=ax+b, y=e ax+b And so on. In the above formula, y is the delivery effect, x is the delivery cost, a and b are preset parameters, that is, the delivery function parameters in the advertising delivery function may include a first parameter a for limiting the upper limit of the delivery effect and a second parameter b for limiting the change rate of the advertising delivery function; the delivery cost includes at least one of the following: delivery budget, delivery bid; the delivery effect may include at least one of the following: exposure, click volume, and consumption.

[0063] It should be noted that since the delivery effect can include exposure, clicks, and consumption, the delivery function parameters in the advertising delivery function corresponding to different delivery effects can be the same or different. For example, the exposure function can be expressed as: y1=a1*x+b1, or y1=e a1*x+b1 , a1 and b1 can be the first and second parameters of the exposure function respectively, y1 is the exposure, and x is the estimated cost of delivery; similarly, the click function can be expressed as: y2 = a2*x+b2, or y2 = e a2*x+b2 , a2 and b2 can be the first and second parameters of the click function, y2 is the click volume, and x is the estimated delivery cost; the consumption function can be expressed as: y3 = a3*x + b3, or y3 = e a3*x+b3 , a3 and b3 can be the first and second parameters corresponding to the consumption function, y3 is the consumption, and x is the estimated cost. The parameters (a1, b1), (a2, b2), and (a3, b3) can be the same or different.

[0064] The weight function can be a piecewise function used to determine the delivery effect obtained through the advertisement delivery function. For example, when the delivery cost is low, the first piece of the weight function can be expressed as Among them, f is the weight information, max is the preset maximum consumption, and x is the delivery cost. When the delivery cost is high, the second part of the weight function can be expressed as Among them, f is the weight information, max is the preset maximum consumption, c is the preset parameter, and x is the delivery cost. Obviously, the first function is different from the second function. The weight function parameters at this time can include a third parameter c for limiting the upper limit of the weight.

[0065] Since the advertising delivery function includes delivery function parameters that need to be determined (for example, a and b), and the weight function includes weight function parameters that need to be determined (for example, c), in order to determine the delivery effect of the advertising delivery plan before the advertising delivery plan is delivered, after obtaining the plan identifier and the estimated delivery cost of the advertising delivery plan, the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function can be determined based on the plan identifier and the estimated delivery cost. In some instances, the delivery function parameters and the weight function parameters can be obtained through a pre-trained machine learning model or neural network model. At this time, based on the plan identifier and the estimated delivery cost, determining the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function can include: obtaining a pre-trained machine learning model or neural network model, inputting the plan identifier and the planned delivery cost into the machine learning model or neural network model, and obtaining the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function output by the machine learning model or neural network model.

[0066] In other instances, the delivery function parameters and weight function parameters can be obtained not only through a pre-trained machine learning model or neural network model, but also through offline features corresponding to the advertising delivery plan. At this time, based on the plan identifier and the estimated delivery cost, determining the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function may include: determining the offline features corresponding to the advertising delivery plan based on the plan identifier, the offline features include: plan attributes, plan historical effects, and user attributes; determining the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function based on the estimated delivery cost and the offline features.

[0067] Specifically, for advertising delivery plans, different advertising delivery plans may correspond to different plan characteristics, for example: different advertising delivery plans correspond to different advertiser identity types, different advertising delivery plans correspond to different delivery user groups, different advertising delivery plans correspond to different plan types, etc. Since the plan characteristics corresponding to different advertising delivery plans can have different effects on the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function, in order to accurately determine the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function, after obtaining the plan identifier, the offline characteristics corresponding to the advertising delivery plan can be determined based on the plan identifier. The offline characteristics may include plan attributes, plan historical effects, and user attributes. In some instances, the plan attributes may include at least one of the following: plan type, bid type, number of products, and number of keywords. The above-mentioned plan types may include: new product plan, hot product plan, ordinary product plan, keyword plan, etc., and the bid types may include: industry smart bidding, merchant manual bidding, keyword bidding, target cost bidding, etc.

[0068] As for the historical effects of the plan, it may include plan effect data and category effect data. The above-mentioned plan effect data may include at least one of the following: the number of exposures in the past 7 days, the number of clicks in the past 7 days, the number of clicks by preset type users in the past 7 days, the number of consumption in the past 7 days, etc. in the historical data. The category effect data may include at least one of the following: the average number of exposures of products in the second-level category, the average number of consumption of products in the second-level category, the average number of exposures of products in the third-level category, the average number of consumption of products in the third-level category, etc. In addition, user attributes may include the advertiser's registration years, the advertiser's star rating, the advertiser level, etc. The above-mentioned user attributes may be obtained through the advertiser's identity identifier corresponding to the advertising delivery plan. Specifically, during or after the process of obtaining the advertising delivery plan, the advertiser's identity identifier may be first obtained; and the user attributes may be determined based on the advertiser's identity identifier.

[0069] After obtaining the estimated delivery cost and offline features, the estimated delivery cost and offline features can be analyzed and processed to determine delivery function parameters in the advertisement delivery function and weight function parameters in the weight function. In some instances, the analysis and processing of the estimated delivery cost and offline features can be implemented using a pre-trained neural network model. In this case, determining the delivery function parameters in the advertisement delivery function and weight function parameters in the weight function based on the estimated delivery cost and offline features can include: obtaining a pre-trained neural network model; and using the neural network model to process the estimated delivery cost and offline features to obtain the delivery function parameters in the advertisement delivery function and weight function parameters in the weight function.

[0070] In some other instances, before obtaining the pre-trained neural network model, the present embodiment may further include a training process of the neural network model. At this time, the method in this embodiment may further include: obtaining historical delivery information corresponding to the historical advertising delivery plan and the historical delivery effect corresponding to the historical delivery information; adjusting the historical delivery information to obtain adjusted delivery information. Specifically, the historical delivery information may be adjusted down and up to obtain the reduced delivery information and the increased delivery information. After obtaining the adjusted delivery information, the adjusted delivery information may be analyzed and processed to determine the simulated delivery effect corresponding to the adjusted delivery information; and then a model training operation may be performed based on the historical delivery information, the historical delivery effect, the adjusted delivery information and the simulated delivery effect, so as to obtain a neural network model for determining the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function. In some instances, the obtained neural network model is a multi-task learning model.

[0071] Step S203: Before the advertisement delivery plan is delivered, based on delivery function parameters, weight function parameters, advertisement delivery function and weight function, the advertisement delivery effects corresponding to different delivery costs are determined, where the different delivery costs at least include estimated delivery costs.

[0072] After obtaining the delivery function parameters and weight function parameters, the delivery function parameters, weight function parameters, advertising delivery function and weight function can be analyzed and processed before the advertising delivery plan is delivered, so as to determine the advertising delivery effects corresponding to different delivery costs. It should be noted that different delivery costs at least include estimated delivery costs. For example, the estimated delivery cost included in the advertising delivery plan is 1 million. By analyzing and processing the estimated delivery cost and the plan identifier, it is possible to predict the advertising delivery effect corresponding to the delivery of a promotion budget of 1 million. In other instances, different delivery costs may also include: estimated delivery costs and other costs different from the estimated delivery costs. Other costs may include at least one of the following: a first type of cost that is greater than the preset delivery cost, a second type of cost that is less than the estimated delivery cost. For example, the estimated delivery cost included in the advertising delivery plan is 1 million. By analyzing and processing the estimated delivery cost and the plan identifier, it is possible to predict the advertising delivery effect corresponding to the delivery of a promotion budget of 1 million. The advertising effect of a promotion budget of 2 million can be predicted, as well as the advertising effect of a promotion budget of 2 million, the advertising effect of a promotion budget of 3 million, and so on; or, the advertising effect of a promotion budget of 1 million can be predicted, as well as the advertising effect of a promotion budget of 500,000, the advertising effect of a promotion budget of 1.5 million, the advertising effect of a promotion budget of 2 million, and so on; or, the advertising effect of a promotion budget of 1 million can be predicted, as well as the advertising effect of a promotion budget of 500,000, the advertising effect of a promotion budget of 800,000, the advertising effect of a promotion budget of 900,000, and so on. Since there is a positive correlation between the advertising cost and the advertising effect, when the advertising effect corresponding to the first type of cost and the advertising effect corresponding to the estimated advertising cost can be predicted and determined, the advertising effect corresponding to the first type of cost is greater than the advertising effect corresponding to the estimated advertising cost; when the advertising effect corresponding to the estimated advertising cost and the advertising effect corresponding to the second type of cost can be predicted and determined, the advertising effect corresponding to the estimated advertising cost is greater than the advertising effect corresponding to the second type of cost.

[0073] In some instances, the advertising delivery effects corresponding to different delivery costs can be obtained by analyzing and processing the delivery function parameters, weight function parameters, advertising delivery function and weight function through a pre-trained machine learning model. At this time, based on the delivery function parameters, weight function parameters, advertising delivery function and weight function, determining the advertising delivery effects corresponding to different delivery costs can include: obtaining a pre-trained neural network model, inputting the delivery function parameters, weight function parameters, advertising delivery function and weight function into the neural network model, and obtaining the advertising delivery effects corresponding to different delivery costs output by the neural network model, thereby effectively ensuring the accuracy and reliability of obtaining the advertising delivery effects corresponding to different delivery costs.

[0074] The method for predicting the effect of advertising delivery provided in this embodiment obtains a plan identifier and an estimated delivery cost corresponding to the advertising delivery plan, and then determines the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function based on the plan identifier and the estimated delivery cost. Before delivering the advertising delivery plan, the advertising delivery effects corresponding to different delivery costs are determined based on the delivery function parameters, the weight function parameters, the advertising delivery function and the weight function. This effectively achieves that before delivering the advertising delivery plan, the advertising delivery effects corresponding to different delivery costs can be directly determined. In this way, without the need for users to set more information such as target groups, more and clearer advertising delivery effects can be displayed to advertisers. The displayed advertising delivery effects corresponding to different delivery costs can not only assist advertisers in making promotion decisions and improve the advertisers' decision-making efficiency, but also help promote network activity and increase the revenue of the network platform, further ensuring the practicality of the method and facilitating market promotion and application.

[0075] FIG3 is a flow chart of determining the advertising delivery effects corresponding to different delivery costs based on delivery function parameters, weight function parameters, advertising delivery function, and weight function according to an embodiment of the present invention. Based on the above embodiment, with reference to FIG3 , the advertising delivery effects corresponding to different delivery costs can be obtained not only through a pre-trained machine learning model or neural network model, but also by directly analyzing and processing the delivery function parameters, the advertising delivery function, the weight function, and the weight function parameters to obtain the advertising delivery effects corresponding to different delivery costs. In this case, determining the advertising delivery effects corresponding to different delivery costs based on the delivery function parameters, the weight function parameters, the advertising delivery function, and the weight function may include:

[0076] Step S301: Based on the estimated delivery cost, a plurality of different delivery costs are determined.

[0077] Among them, since an advertising plan often corresponds to an estimated delivery cost, the estimated delivery cost is the advertising delivery cost or the estimated advertising delivery cost that the user needs to pay during the promotion operation. In order to obtain the advertising delivery effect corresponding to different delivery costs, after obtaining the estimated delivery cost, the estimated delivery cost can be analyzed and processed to determine multiple different delivery costs. In some examples, based on the estimated delivery cost, determining multiple different delivery costs can include: obtaining a magnitude parameter for adjusting the estimated delivery cost. The magnitude parameter can be a pre-configured default parameter or an adjustment parameter entered by the user, for example, the magnitude parameter can be 10%, 20%, 30%, etc. After obtaining the magnitude parameter, the estimated delivery cost can be increased or decreased based on the magnitude parameter, thereby obtaining multiple different delivery costs. It should be noted that the multiple different delivery costs can include not only the first category of costs greater than the estimated delivery cost and the second category of costs less than the estimated delivery cost, but can also include the estimated delivery cost.

[0078] Step S302: Based on the delivery function parameters and the advertisement delivery function, the delivery effects corresponding to different delivery costs are determined.

[0079] After obtaining the delivery function parameters and the advertising delivery function, the delivery function parameters and the advertising delivery function can be analyzed and processed, so that the delivery effects corresponding to different delivery costs can be determined. For example, when the advertising delivery function is y1=a1*x+b1, after obtaining the delivery function parameters (a1, b1), and after obtaining different delivery costs (x, x2, x3...), the delivery function parameters and the different delivery costs can be substituted into the advertising delivery function, so that the delivery effects y1 corresponding to different delivery costs can be determined, wherein the delivery effects y1 corresponding to different delivery costs can include: delivery effect y11 corresponding to x, delivery effect y12 corresponding to x2, delivery effect y13 corresponding to x3, etc., thereby effectively ensuring the accuracy and reliability of determining the delivery effects corresponding to different delivery costs.

[0080] Step S303: Based on the weight function parameters and the weight function, determine the weight information corresponding to different delivery costs.

[0081] After obtaining the weight function parameters and weight function, the weight function parameters and weight function can be analyzed and processed to determine the weight information corresponding to different delivery costs. For example, when the weight function is When obtaining the weight function parameter c, and after obtaining different delivery costs (x, x2, x3...) and the expected maximum consumption max, the weight function parameter, different delivery costs and maximum consumption max can be substituted into the weight function, so as to determine the weight information f corresponding to different delivery costs, wherein the weight information f corresponding to different delivery costs may include: the delivery effect f11 corresponding to x, the delivery effect f12 corresponding to x2, the delivery effect f13 corresponding to x3, and so on, thereby effectively ensuring the accuracy and reliability of the determination of the weight information corresponding to different delivery costs.

[0082] Step S304: Based on the delivery effect and weight information, determine the advertising delivery effects corresponding to different delivery costs.

[0083] After obtaining the delivery effects and weight information corresponding to different delivery costs, the delivery effects and weight information can be analyzed and processed to determine the advertising delivery effects corresponding to the different delivery costs. In some examples, determining the advertising delivery effects corresponding to the different delivery costs based on the delivery effects and weight information can include multiplying the delivery effects corresponding to the different delivery costs by the weight information to determine the advertising delivery effects corresponding to the different delivery costs.

[0084] For example, when the delivery effects corresponding to different delivery costs are y11, y12, and y13, and the weight information corresponding to different delivery costs is f11, f12, and f13, the product value between the delivery effects corresponding to different delivery costs and the weight information can be obtained. The product value can be: y11*f11, y12*f12, y13*f13, etc. After obtaining the above product value, the product value of the delivery effects corresponding to different delivery costs and the weight information can be directly determined as the advertising delivery effects corresponding to different delivery costs, thereby effectively ensuring the accuracy and reliability of the determination of the advertising delivery effect.

[0085] In some other instances, not only can the advertising delivery effects corresponding to different delivery costs be determined by the delivery effect and weight information, but the advertising delivery effects can also be determined in combination with other auxiliary parameters. At this time, based on the delivery effect and weight information, determining the advertising delivery effects corresponding to different delivery costs can include: obtaining delivery auxiliary parameters corresponding to the advertising delivery plan, the delivery auxiliary parameters including at least one of the following: delivery time parameters, delivery area parameters, delivery population parameters; determining the product value of the delivery effect, weight information and delivery auxiliary parameters corresponding to different delivery costs as the advertising delivery effect corresponding to different delivery costs.

[0086] Specifically, in order to accurately obtain the advertising delivery effects corresponding to different delivery costs, delivery auxiliary parameters corresponding to the advertising delivery plan can be obtained. The above delivery auxiliary parameters can be stored in a preset device or a preset area. At this time, the delivery auxiliary parameters corresponding to the advertising delivery plan can be obtained by accessing the preset device or the preset area. Among them, the delivery auxiliary parameters include at least one of the following: delivery time parameters, delivery area parameters, and delivery population parameters. In some instances, the delivery auxiliary parameters can be one-dimensional parameters. For example, when the delivery auxiliary parameters are delivery time parameters, they can be expressed as The above t1, t2, t3, and tn are used to identify different time points or time periods; when the delivery auxiliary parameter is the delivery area parameter, it can be expressed as The above c1, c2, c3, and cn are used to identify different countries or regions. When the delivery auxiliary parameter is the delivery population parameter, it can be expressed as The above p1, p2, p3, and pn are used to identify different types of people.

[0087] After obtaining the delivery effects, weight information and delivery auxiliary parameters corresponding to different delivery costs, the product values ​​of the delivery effects, weight information and delivery auxiliary parameters corresponding to different delivery costs can be obtained, and then the above product values ​​can be determined as the advertising delivery effects corresponding to different delivery costs.

[0088] For example, the delivery effects corresponding to different delivery costs are y11, y12, and y13, the weight information corresponding to different delivery costs is f11, f12, and f13, and the delivery auxiliary parameters are When you use the product value between the delivery effect, weight information and delivery auxiliary parameters corresponding to different delivery costs, you can obtain the product value, which may include: And so on. After obtaining the above product value, the above product value can be directly determined as the advertising delivery effect corresponding to different delivery costs, thereby effectively ensuring the flexibility and reliability of determining the advertising delivery effect.

[0089] After obtaining the advertising effect, the advertising effect can be displayed in a more granular manner in dimensions such as country, time period, and population. For example, if the total number of exposures of the advertising plan is estimated to be 100 times a day, and the time distribution is 30% in the morning, 40% in the afternoon, and 30% in the evening, it can be known that the advertising plan has 30 exposures in the morning, 40 exposures in the afternoon, and 30 exposures in the evening. This allows advertisers to have a clearer understanding of the advertising effect in each dimension.

[0090] In this embodiment, multiple different delivery costs are determined by estimating the delivery cost, the delivery effects corresponding to different delivery costs are determined based on the delivery function parameters and the advertising delivery function, and the weight information corresponding to different delivery costs is determined based on the weight function parameters and the weight function. Then, the advertising delivery effects corresponding to different delivery costs are determined based on the delivery effects and the weight information, thereby effectively ensuring the stable reliability of determining the advertising delivery effects, and ensuring the flexible reliability of determining the advertising delivery effects.

[0091] FIG4 is a flow chart of another method for predicting the effect of advertising provided by an embodiment of the present invention. Based on the above embodiment, with reference to FIG4 , the weight function in this embodiment is a piecewise function, which may have different representations based on different advertising costs. Specifically, the method in this embodiment may further include:

[0092] Step S401: Obtain an estimated consumption upper limit value corresponding to the advertising delivery plan.

[0093] For the weight function, the expression of the weight function corresponding to different levels of delivery costs is different. In order to accurately determine the specific expression of the weight function, we can first obtain the estimated consumption upper limit value used to analyze and process the delivery cost. The above-mentioned estimated consumption upper limit value is used to identify the upper limit value of the estimated consumption. The estimated consumption is the estimated actual delivery consumption cost. For example, the delivery cost may include the delivery budget and the delivery bid, where the delivery budget can be 10,000 / day and the delivery bid is 10 yuan / time. By analyzing and processing historical advertising delivery plans, it can be determined that the estimated consumption upper limit value can be 8,000 / day.

[0094] Specifically, for the estimated consumption upper limit value, different methods can be used to obtain the estimated consumption upper limit value in different application scenarios. In some instances, the advertising delivery plan can include the estimated consumption upper limit value. Specifically, after obtaining the advertising delivery plan, information extraction operations can be performed on the advertising delivery plan to obtain the estimated consumption upper limit value corresponding to the advertising delivery plan.

[0095] In other instances, the advertising delivery plan may not include the estimated consumption upper limit value. In this case, the estimated consumption upper limit value can be obtained through the consumption function. Specifically, obtaining the estimated consumption upper limit value corresponding to the advertising delivery plan may include: obtaining the consumption function corresponding to the advertising delivery plan and the function parameters corresponding to the consumption function; based on the consumption function, the function parameters and the estimated delivery cost, determining the estimated consumption upper limit value corresponding to the advertising delivery plan.

[0096] Since the estimated consumption upper limit value is related to the consumption function, in order to accurately obtain the estimated consumption upper limit value, the consumption function corresponding to the advertising delivery plan and the function parameters corresponding to the consumption function can be obtained. After obtaining the consumption function and function parameters, the estimated delivery cost obtained in the above embodiment can be combined to determine the estimated consumption upper limit value corresponding to the advertising delivery plan. For example, when the consumption function is Among them, y_cost is the estimated consumption, a and b are function parameters corresponding to the consumption function, and x is the estimated delivery cost. Through the method steps in the above embodiment, multiple function parameters corresponding to the consumption function can be determined, for example: (a1, b1), (a2, b2), (a3, b3)... After obtaining the above multiple function parameters, the multiple function parameters and the estimated delivery cost can be substituted into the consumption function, so as to obtain multiple estimated consumptions, for example: y_cost1 corresponding to (a1, b1), y_cost2 corresponding to (a2, b2), y_cost3 corresponding to (a3, b3)..., and then the multiple estimated consumptions can be analyzed and compared to obtain the upper limit value of the estimated consumption, thereby effectively ensuring the accuracy and reliability of obtaining the upper limit value of the estimated consumption.

[0097] Step S402: When the estimated delivery cost is less than or equal to the upper limit of the estimated consumption, the weight function is determined to be a first monotonic function for indicating that there is a positive correlation between the delivery cost and the weight information.

[0098] Step S403: when the estimated delivery cost is greater than the upper limit of the estimated consumption, the weight function is determined to be a second monotonic function for indicating a positive correlation between the delivery cost and the weight information, and the first monotonic function is different from the second monotonic function.

[0099] After obtaining the estimated upper limit of consumption, the estimated delivery cost corresponding to the advertising delivery plan can be analyzed and compared with the estimated upper limit of consumption. When the estimated delivery cost is less than or equal to the estimated upper limit of consumption, it means that the estimated delivery cost at this time is relatively small, that is, there is still a large room for increase in the delivery cost. At this time, the advertising delivery effect (weight information) can increase significantly with the increase in the delivery cost. Therefore, the weight function can be determined as the first monotonic function used to identify the positive correlation between the delivery cost and the delivery weight.

[0100] Correspondingly, when the expected delivery cost is greater than the upper limit of the estimated consumption, it means that there is limited room for the delivery cost to increase. However, if the user continues to increase the expected delivery cost, the advertising delivery effect will increase slowly relative to the change program of the advertising delivery effect in the first monotonic function, and the weight function can be determined as the second monotonic function for identifying a positive correlation between the delivery cost and the weight information.

[0101] It should be noted that the first monotonic function is different from the second monotonic function. Specifically, the degree of change corresponding to the first monotonic function is greater than the degree of change corresponding to the second monotonic function. For example, the weight function can be expressed as the following formula:

[0102] Among them, f is the weight information, x is the estimated delivery cost, max_cost is the estimated consumption upper limit, and c is the preset function parameter. When the estimated delivery cost x increases to the same extent, the first monotonic function The degree of increase in the weight information obtained is p1, which is obtained by the second monotonic function The degree of increase in the obtained weight information is p2, and the above-mentioned p1 is greater than p2.

[0103] In this embodiment, by obtaining the estimated consumption upper limit value corresponding to the advertising delivery plan, when the estimated delivery cost is less than or equal to the estimated consumption upper limit value, the weight function can be determined as a first monotonic function for identifying that there is a positive correlation between the delivery cost and the weight information; when the estimated delivery cost is greater than the estimated consumption upper limit value, the weight function can be determined as a second monotonic function for identifying that there is a positive correlation between the delivery cost and the weight information. This effectively realizes that different weight functions can be determined in different application scenarios, and then the weight function can be used to make a stable prediction of the advertising delivery effect, further ensuring the accuracy and rationality of the prediction of the advertising delivery effect.

[0104] FIG5 is a flow chart of another method for predicting advertising delivery effects provided by an embodiment of the present invention. Based on any of the above embodiments, with reference to FIG5 , after determining the advertising delivery effects corresponding to different delivery costs, this embodiment may further include a technical solution for determining whether the advertising delivery effects can be achieved. Specifically, the method may include:

[0105] Step S501: Obtain the bid lower limit value corresponding to the advertisement delivery plan.

[0106] Regarding the advertising effects corresponding to different delivery costs, since the advertising effects may not be achieved due to a small delivery bid, or may be achieved due to a large delivery bid, in order to accurately determine whether the advertising effects can be achieved, the bid floor value corresponding to the advertising delivery plan can be obtained. Regarding the bid floor value, different methods can be used to obtain the bid floor value in different application scenarios. In some instances, the advertising delivery plan may include the bid floor value. In this case, after obtaining the advertising delivery plan, information extraction operations can be performed on the advertising delivery plan to obtain the bid floor value corresponding to the advertising delivery plan.

[0107] In other instances, the advertising delivery plan may not include a lower bid limit value. In this case, the lower bid limit value can be obtained by analyzing and processing the exposure lower limit parameters and historical click-through rates corresponding to the products to be promoted. In this case, obtaining the lower bid limit value corresponding to the advertising delivery plan may include: obtaining the exposure lower limit parameters and historical click-through rates corresponding to the products to be promoted through the product exposure log; and determining the lower bid limit value corresponding to the advertising delivery plan based on the exposure lower limit parameters and historical click-through rates.

[0108] Specifically, the bid lower limit can be estimated through historical data. The historical data may include historical click-through rates and historical exposure parameters. In order to accurately determine the bid lower limit, the product exposure log can be obtained first, and then the exposure parameters and historical click-through rates of the product to be promoted within a period of time can be counted through the product exposure log. Since the exposure parameters corresponding to different time points in a period of time are different, the number of exposure parameters included in the product exposure log may be multiple. In order to obtain the bid lower limit, the multiple exposure parameters can be analyzed and compared to obtain the exposure lower limit parameter among the multiple exposure parameters. The exposure lower limit parameter is used to identify the minimum exposure value when the product to be promoted is promoted.

[0109] After obtaining the exposure lower limit parameter and the historical click-through rate, the exposure lower limit parameter and the historical click-through rate can be analyzed and processed to obtain the bid lower limit value. In some instances, the exposure lower limit parameter and the historical click-through rate can be analyzed and processed using a pre-trained machine learning model or neural network model, thereby obtaining the bid lower limit value corresponding to the advertising delivery plan output by the machine learning model or neural network model. In other instances, determining the bid lower limit value corresponding to the advertising delivery plan based on the exposure lower limit parameter and the historical click-through rate may include: determining the bid lower limit value corresponding to the advertising delivery plan as the ratio of the exposure lower limit parameter to the historical click-through rate. For example, when the exposure lower limit parameter is min_rankscore and the historical click-through rate is ctr, the bid lower limit value can be obtained by min_bid = min_rankscore / ctr, where min_bid is the bid lower limit value, thereby effectively ensuring the accuracy and reliability of the bid lower limit value determination.

[0110] Step S502: Determine the delivery bids corresponding to different delivery costs.

[0111] Since the obtained advertising delivery effect corresponds to different delivery costs, different delivery costs may include different delivery bids. In order to accurately judge whether the advertising delivery effect can be obtained, the delivery bids corresponding to different delivery costs can be obtained. In some instances, different delivery costs include delivery bids. At this time, the delivery bids can be obtained by performing information extraction operations on the delivery costs.

[0112] Step S503: When the delivery bid is greater than or equal to the bid lower limit, a first identifier corresponding to the advertisement delivery effect is determined, where the first identifier is used to identify that the advertisement delivery effect can be obtained.

[0113] Step S504: when the delivery input information is less than the bid lower limit, a second identifier corresponding to the advertisement delivery effect is determined, and the second identifier is used to indicate that the advertisement delivery effect cannot be obtained.

[0114] After obtaining the delivery bid and the bid lower limit value, the delivery bid can be analyzed and compared with the bid lower limit value. When the delivery bid is greater than or equal to the bid lower limit value, it means that the delivery bid is relatively large. At this time, the advertising delivery plan can be delivered normally, and the advertising delivery effect corresponding to the delivery cost can be obtained. That is, the advertising delivery effect can be obtained at this time, and then the first identifier corresponding to the advertising delivery effect can be determined. The first identifier is used to identify that the advertising delivery effect can be obtained. Specifically, the first identifier can be "0" or "1".

[0115] Correspondingly, when the delivery bid is less than the bid lower limit, it means that the delivery bid is relatively small. At this time, it may not be possible to perform normal delivery operations on the advertising delivery plan, and the advertising delivery effect corresponding to the delivery cost cannot be obtained at this time, that is, the advertising delivery effect cannot be obtained at this time, and then a second identifier corresponding to the advertising delivery effect can be determined. The second identifier is used to indicate that the advertising delivery effect cannot be obtained. Specifically, the second identifier can be "1" or "0". It should be noted that the first identifier is different from the second identifier.

[0116] In this embodiment, by obtaining the bid lower limit value corresponding to the advertising delivery plan, the delivery bids corresponding to different delivery costs are determined. When the delivery bid is greater than or equal to the bid lower limit value, the first identifier corresponding to the advertising delivery effect is determined. When the delivery input information is less than the bid lower limit value, the second identifier corresponding to the advertising delivery effect is determined. This effectively enables the user to accurately and quickly determine whether the advertising delivery effect can be obtained through the obtained first identifier and second identifier. In addition, the obtained first identifier and second identifier are helpful in assisting users in making advertising promotion decisions, further improving the practicality of the method.

[0117] In specific applications, in order to solve the problems of advertisers' lack of confidence in advertising promotion plans and high trial and error costs in related technologies, this application embodiment provides a method for estimating advertising promotion effects. This method can directly display the advertising promotion effects corresponding to the advertising promotion plans after the advertisers set the advertising promotion plans and before the formal launch. The advertising promotion effects are the predicted future effects, which is helpful in assisting advertisers in making promotion decisions. This not only improves the efficiency of advertising promotion plans, but also helps promote website activity and increase platform revenue.

[0118] Referring to FIG6 , the method may include an offline network model training operation and an operation of determining the advertising promotion effect based on the network model. As an advertising function, Taking the weight function as an example, the training operation of the network model in this embodiment may include the following steps:

[0119] Step 1: Determine the advertising delivery function and weight function used to determine the effectiveness of advertising promotion.

[0120] For the advertisement delivery function and the weight function, the advertisement delivery function and the weight function can be determined based on manual experience or historical experience data, wherein the advertisement delivery function is used to define the correlation between the advertisement delivery bid and the advertisement delivery effect. In some examples, the advertisement delivery function can be Among them, y iThe advertising effect can include exposure, clicks, consumption, etc. Specifically, the exposure function can be The click delivery function can be The consumption delivery function can be The parameters corresponding to the above different advertising functions (a i , b i ) can be different, wherein the above parameter a i It can affect the expected maximum effect data, that is, the effect obtained when the advertising bid is the lowest. Parameter b i It can affect the slope of the function, that is, the degree to which the effect changes with the bid. When the ad bid is x i When it approaches 0, the effect that can be obtained is also very small; when the advertising bid x i As it gradually increases, the slope of the function becomes larger rapidly, and the effect that can be obtained when the unit bid is increased also increases rapidly. It should be noted that when the advertising bid continues to increase and it is considered to have achieved the top bid among similar plans, the speed of effect improvement will also decrease because there is no room for further competition.

[0121] In addition, for the weight function, the weight function can be determined based on manual experience and historical experience data. The weight function can be expressed as a piecewise function. Specifically, the piecewise function can be

[0122] Among them, f is the weight information, x is the expected delivery budget, and max_cost is the estimated consumption upper limit. In some instances, max_cost can be calculated by the preset formula c is the preset weight function parameter. From the above weight function, we can see that when the estimated delivery budget is less than or equal to the estimated consumption upper limit, the weight information will linearly affect the final effect. When the estimated delivery budget is greater than the estimated consumption upper limit, the weight information will slowly increase as the estimated delivery budget increases. This can not only reduce the impact of other promotion plans' reduced competitiveness due to premature completion, but also increase advertisers' enthusiasm for budget increases.

[0123] Step 2: Obtain training data, perform enhancement processing on the training data, and obtain enhanced data.

[0124] Among them, the training data obtained may include historical advertising delivery plans and historical advertising delivery effects corresponding to the historical advertising delivery plans. The above-mentioned historical advertising delivery plans may include historical delivery budgets and historical delivery bids. Since there are rarely price changes in the actual data of historical advertising delivery plans, the amount of training data obtained at this time is limited. When the machine learning model is trained based on a limited amount of training data, the training effect of the machine learning model cannot be guaranteed. The above-mentioned machine learning model is used to determine the delivery function parameters (a, b) in the advertising delivery function and the weight function parameter c in the weight function under different advertising delivery bids. Since the model training effect of the machine learning model cannot be guaranteed, it is impossible to accurately learn and analyze the delivery function parameters and weight function parameters corresponding to different advertising delivery bids.

[0125] In order to solve the above technical problems and ensure the training quality and effect of the machine learning model, after obtaining the training data, the training data can be enhanced. In some instances, log data is used to simulate the advertising effects corresponding to different advertising bids. Specifically, by simulating the modification of the advertising bids in the advertising plan, the corresponding exposure, click volume, consumption and other effect data under different advertising bids are obtained. That is, the simulation operation of different advertising bids and advertising effects based on log data is realized, the data enhancement processing is completed, and the enhanced data can be successfully obtained. The obtained enhanced data and training data can be unified as model training data, thereby effectively realizing the expansion operation of the model training data.

[0126] It should be noted that when simulating the modification of the advertising bids in the advertising plan, the modification range of the existing training data in different application scenarios is different. Specifically, when the promotion platform is large and there are many users, due to the diversity and personalization of the data, the modification range of the advertising bids in the existing training data can be determined as a finer modification parameter. This can ensure the learning quality and effect of the machine learning model. At this time, after the modification simulation operation, the amount of enhanced data obtained is large; when the promotion platform is small and there are fewer users, due to the limited diversity and personalization of the data, the modification range of the advertising bids in the existing training data can be determined as a coarser modification parameter. At this time, the amount of enhanced data obtained is small.

[0127] In addition, in order to ensure the quality and efficiency of model training data, the minimum ranking score that can be exposed can also be obtained through the results in the advertising product exposure log. The minimum ranking score can be min_rankscore = min(ctr*bid). The minimum exposure bid min_bid = min_rankscore / ctr can be determined through the above formula. It should be noted that the above minimum exposure bid can determine whether the advertising product corresponding to a certain advertising bid can be exposed. Specifically, when the advertising bid is less than or equal to the minimum exposure bid, it means that the advertising product corresponding to the advertising bid at this time cannot obtain this exposure, that is, the advertising promotion effect corresponding to the advertising bid can be obtained; when the advertising bid is greater than the minimum exposure bid, it means that the advertising product corresponding to the advertising bid at this time can obtain this exposure, that is, the advertising promotion effect corresponding to the advertising bid cannot be obtained.

[0128] Step 3: Determine the training data and the enhanced data as model training data, and perform feature extraction operations based on the model training data to obtain model training features.

[0129] Specifically, the model training features may include four categories of features, which may include: plan basic data, plan effect data, category effect data, and merchant basic data. Referring to Figure 7, the plan basic data may include: plan type (new product plan, explosive product plan, ordinary product plan, keyword plan, etc.), bid type (industry smart bidding, merchant manual bidding, fixed bidding, keyword bidding, target cost bidding, etc.), number of products, number of keywords, etc. The plan effect data may include: number of exposures in the past 7 days, number of clicks in the past 7 days, number of clicks by preset type users in the past 7 days, consumption in the past 7 days, etc. Category effect data may include: average exposure number of products in the second-level category, average consumption of products in the second-level category; merchant basic data may include: merchant years, merchant star rating, merchant level, etc. By combining basic data features (plan basic data and merchant basic data) with performance data (plan performance data and category performance data), each advertiser can select different plan types, products, bidding methods, etc. according to their needs when creating an advertising promotion plan. Diverse results can be displayed for different advertising promotion plans. Historical performance data can also be used to improve the accuracy of parameter estimation operations performed by machine learning models.

[0130] Step 4: Perform model training operations based on the model training features and the corresponding historical performance data to obtain a machine learning model.

[0131] Among them, the obtained machine learning model can be a multi-task learning model (Multi-gate MoE, abbreviated as MMOE). The multi-task learning model can realize the training operation of multi-target results. Specifically, the delivery function parameters can be obtained through the machine learning model. The above-mentioned delivery function parameters may include: parameters of the advertising exposure function, parameters of the click function, parameters of the consumption function, and weight function parameters, etc. It should be noted that the parameter b in the delivery function parameters needs to be a positive number. Specifically, in order to ensure that the delivery function parameter b is a positive number, before outputting the delivery function parameter b, the activation function softplus can be used to process the delivery function parameter b, so as to ensure the rationality of the model output results.

[0132] By determining the MMOE model as a machine learning model, since the MMOE model allows multiple targets to share parameters during training, and since there is a correlation between multiple training tasks, that is, the expression of the advertising delivery functions corresponding to different effects is similar, when the machine learning model is trained, the delivery function parameters corresponding to the advertising delivery functions of different effects can be obtained at one time, that is, only one inference process is required to obtain multiple results. This has great advantages when deploying the machine learning model, and can reduce the computing resources required for data processing operations, and improve the quality and efficiency of data processing.

[0133] Furthermore, determining the advertising promotion effect based on the network model may include the following steps:

[0134] Step 11: Obtain the plan information corresponding to the advertising promotion plan input by the user.

[0135] Among them, the client or the parsing front-end includes an effectiveness prediction service for realizing the operation of estimating the effect of advertising promotion. The user can input plan information through the client or the parsing front-end. The plan information may include at least one of the following: merchant ID, plan ID, promotion product ID, advertising promotion bid, advertising promotion budget, etc. In order to accurately realize the operation of estimating the effect of advertising promotion, the plan information can be converted into information that can be recognized by the effectiveness prediction service, so that the effectiveness prediction service can analyze and process the plan information to determine the advertising promotion effect.

[0136] Step 12: Obtain offline features corresponding to the advertising promotion plan based on the plan information.

[0137] Among them, after obtaining the merchant ID and plan ID corresponding to the advertising promotion plan, the offline features corresponding to the advertising promotion plan can be queried based on information such as the merchant ID and plan ID. The offline features may include at least one of the following: merchant consumption data in the past 30 days, planned promotion days and other data. It should be noted that the offline features can be obtained by analyzing and processing the advertising promotion plan in an offline scenario. The processing method of offline features can reduce the amount of parameters required to be passed in when the client or parsing front-end performs advertising promotion effect determination operations, and further avoid overall service operation timeout, thereby ensuring the quality and efficiency of data processing.

[0138] Step 13: After obtaining the offline features and plan information, the pre-trained machine learning model can be used to analyze and process the offline features and plan information, so as to obtain the delivery function parameters and weight function parameters output by the machine learning model.

[0139] Specifically, after obtaining the plan information input by the client or parsing the front end and the offline features queried offline, the plan information and offline features can be input into the machine learning model to use the machine learning model to infer the plan information and offline features, so as to obtain a series of target parameter values ​​that need to be estimated, such as the delivery function parameters and weight function parameters output by the machine learning model. The above-mentioned delivery function parameters may include at least one of the following: parameters of the advertising exposure function, parameters of the click function, and parameters of the consumption function.

[0140] Step 14: Based on the delivery function parameters, the weight function parameters, the advertisement delivery function, and the weight function, determine the advertisement delivery effect corresponding to the advertisement promotion plan.

[0141] Among them, the estimated promotion budget and delivery function parameters in the advertising promotion plan are substituted into the advertising delivery function to obtain the promotion effect, and the estimated promotion budget and weight function parameters in the advertising promotion plan are substituted into the weight function to obtain the weight information corresponding to the promotion effect, and then the product value of the promotion effect and the weight information is determined as the advertising delivery effect corresponding to the advertising promotion plan.

[0142] In addition, after obtaining the estimated promotion budget, the estimated promotion budget can also be adjusted to obtain multiple different promotion budgets, and different promotion budgets and delivery function parameters can be substituted into the advertising delivery function to obtain promotion effects corresponding to different promotion budgets. Different promotion budgets and weight function parameters can be substituted into the weight function to obtain weight information corresponding to different promotion budgets, and then the product value of the promotion effect corresponding to different promotion budgets and the weight information can be determined as the advertising delivery effect corresponding to different promotion budgets.

[0143] After obtaining the advertising delivery effects corresponding to the advertising promotion plan and the advertising delivery effects corresponding to different promotion budgets, all advertising delivery effects can be packaged and displayed through the display module of the client or service front end, so that users can quickly and intuitively view all advertising delivery effects.

[0144] The technical solution provided by this application embodiment can not only provide advertisers with the function of estimating the effectiveness of advertising plans before they are launched, thereby increasing advertisers' confidence in their launch, but also, in order to ensure the rationality of the estimated results, it is necessary to ensure that the higher the advertising bid and the higher the budget, the better the corresponding effect. Specifically, in order to ensure the above principles, a monotonic prior function can be used as an analysis and processing function for determining the effectiveness of advertising promotion, and a model can be used to estimate the parameters in the prior function based on the characteristics of the advertising plan. This can ensure both the accuracy of the estimated results and the rationality of the results. Specifically, when estimating the promotion effect of an advertising promotion plan, it is only necessary to consider the characteristics of the advertising promotion plan itself to estimate the effectiveness function parameters. After obtaining the various function parameters, the promotion bid and promotion budget can be substituted into the function formula to calculate the advertising promotion effect. In some instances, during the promotion of the advertising promotion effect, the value range of the parameters in the formula can be limited, thereby ensuring that the advertising promotion effect is monotonic with the bid and budget. In addition, through the piecewise functional relationship between the advertising promotion budget and the advertising promotion effect, the rationality of the results can be effectively guaranteed when the budget increases, and then the total effect and the result distribution can be output independently, which is conducive to improving the scalability of the technical solution, further improving the practicality of the method, and facilitating market promotion and application.

[0145] FIG8 is a schematic diagram of the structure of an apparatus for predicting the effect of advertising provided by an embodiment of the present invention. Referring to FIG8 , this embodiment provides an apparatus for predicting the effect of advertising, which is used to execute the method for predicting the effect of advertising shown in FIG2 . Specifically, the apparatus for predicting the effect of advertising may include:

[0146] The first acquisition module 11 is used to obtain a plan identifier corresponding to the advertising delivery plan and an estimated delivery cost;

[0147] A first determining module 12 is configured to determine, based on the plan identifier and the estimated delivery cost, delivery function parameters in the advertisement delivery function and weight function parameters in the weight function, wherein the advertisement delivery function is configured to identify the relationship between the delivery cost and the delivery effect, and the weight function is configured to determine the weight of the delivery effect obtained by the advertisement delivery function;

[0148] The first processing module 13 is used to determine the advertising delivery effects corresponding to different delivery costs based on delivery function parameters, weight function parameters, advertising delivery function and weight function before delivering the advertising delivery plan, where the different delivery costs at least include estimated delivery costs.

[0149] In some instances, when the first determination module 12 determines the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function based on the plan identifier and the estimated delivery cost, the first determination module 12 is used to execute: determining the offline characteristics corresponding to the advertising delivery plan based on the plan identifier, the offline characteristics including: plan attributes, plan historical effects, and user attributes; determining the delivery function parameters in the advertising delivery function and the weight function parameters in the weight function based on the estimated delivery cost and the offline characteristics.

[0150] In some instances, when the first processing module 13 determines the advertising delivery effects corresponding to different delivery costs based on the delivery function parameters, the weight function parameters, the advertising delivery function and the weight function, the first processing module 13 is used to perform: determining multiple different delivery costs based on the estimated delivery cost; determining the delivery effects corresponding to different delivery costs based on the delivery function parameters and the advertising delivery function; determining the weight information corresponding to different delivery costs based on the weight function parameters and the weight function; and determining the advertising delivery effects corresponding to different delivery costs based on the delivery effects and the weight information.

[0151] In some instances, when the first processing module 13 determines the advertising delivery effects corresponding to different delivery costs based on the delivery effects and weight information, the first processing module 13 is used to execute: determining the product value of the delivery effects corresponding to different delivery costs and the weight information as the advertising delivery effects corresponding to different delivery costs.

[0152] In some instances, when the first processing module 13 determines the advertising delivery effects corresponding to different delivery costs based on the delivery effects and weight information, the first processing module 13 is used to execute: obtaining delivery auxiliary parameters corresponding to the advertising delivery plan, the delivery auxiliary parameters including at least one of the following: delivery time parameters, delivery area parameters, and delivery population parameters; and determining the product value between the delivery effects, weight information, and delivery auxiliary parameters corresponding to different delivery costs as the advertising delivery effects corresponding to different delivery costs.

[0153] In some instances, the advertisement delivery function is a monotonic function used to identify a positive correlation between delivery cost and delivery effect; the delivery cost includes the delivery budget; and the delivery effect includes at least one of the following: exposure, clicks, and consumption.

[0154] In some instances, the delivery function parameters include a first parameter for limiting an upper limit value of the delivery effect and a second parameter for limiting a rate of change of the advertisement delivery function; the weight function parameters include a third parameter for limiting an upper limit value of the weight.

[0155] In some examples, the first acquisition module 11 and the first processing module 13 in this embodiment are configured to perform the following steps:

[0156] The first acquisition module 11 is used to obtain an estimated consumption upper limit value corresponding to the advertising delivery plan;

[0157] The first processing module 13 is configured to determine, when the estimated delivery cost is less than or equal to the upper limit of the estimated consumption, that the weight function is a first monotonic function for indicating that a positive correlation exists between the delivery cost and the weight information; and, when the estimated delivery cost is greater than the upper limit of the estimated consumption, determine the weight function to be a second monotonic function for indicating that a positive correlation exists between the delivery cost and the weight information, wherein the first monotonic function and the second monotonic function are different.

[0158] In some instances, when the first acquisition module 11 obtains the estimated upper limit of consumption corresponding to the advertising delivery plan, the first acquisition module 11 is used to execute: obtaining the consumption function corresponding to the advertising delivery plan and the function parameters corresponding to the consumption function; and determining the estimated upper limit of consumption corresponding to the advertising delivery plan based on the consumption function, the function parameters and the estimated delivery cost.

[0159] In some examples, after determining the advertising delivery effects corresponding to different delivery costs, the first acquisition module 11, the first determination module 12, and the first processing module 13 in this embodiment are configured to perform the following steps:

[0160] The first acquisition module 11 is used to obtain a bid lower limit value corresponding to the advertising delivery plan;

[0161] The first determining module 12 is used to determine the delivery bids corresponding to different delivery costs;

[0162] The first processing module 13 is used to determine a first identifier corresponding to the advertising delivery effect when the delivery bid is greater than or equal to the bid lower limit value, and the first identifier is used to indicate that the advertising delivery effect can be obtained; when the delivery input information is less than the bid lower limit value, a second identifier corresponding to the advertising delivery effect is determined, and the second identifier is used to indicate that the advertising delivery effect cannot be obtained.

[0163] In some instances, when the first acquisition module 11 obtains the bid lower limit value corresponding to the advertising delivery plan, the first acquisition module 11 is used to execute: obtaining the exposure lower limit parameters and historical click-through rates corresponding to the product to be promoted through the product exposure log; and determining the bid lower limit value corresponding to the advertising delivery plan based on the exposure lower limit parameters and historical click-through rates.

[0164] The device shown in FIG8 can execute the method of the embodiment shown in FIG1-FIG7. For the parts not described in detail in this embodiment, please refer to the relevant description of the embodiment shown in FIG1-FIG7. The execution process and technical effects of this technical solution can be found in the description of the embodiment shown in FIG1-FIG7, and will not be repeated here.

[0165] In one possible design, the structure of the advertising delivery effect prediction device shown in Figure 8 can be implemented as an electronic device, which can be a controller, a personal computer, a server, or other device. As shown in Figure 9, the electronic device may include a first processor 21 and a first memory 22. The first memory 22 is used to store a program that enables the electronic device to execute the advertising delivery effect prediction method provided in the embodiments shown in Figures 1-7. The first processor 21 is configured to execute the program stored in the first memory 22.

[0166] The program includes one or more computer instructions, wherein the one or more computer instructions, when executed by the first processor 21, can implement the following steps: obtaining a plan identifier and an estimated delivery cost corresponding to the advertising delivery plan; determining delivery function parameters in the advertising delivery function and weight function parameters in the weight function based on the plan identifier and the estimated delivery cost, wherein the advertising delivery function is used to identify the relationship between the delivery cost and the delivery effect, and the weight function is used to determine the weight of the delivery effect obtained by the advertising delivery function; before delivering the advertising delivery plan, determining the advertising delivery effects corresponding to different delivery costs based on the delivery function parameters, the weight function parameters, the advertising delivery function and the weight function, and the different delivery costs at least include the estimated delivery cost.

[0167] Furthermore, the first processor 21 is also configured to execute all or part of the steps in the embodiments shown in the aforementioned FIG. 1 to FIG. 7 .

[0168] The structure of the electronic device may further include a first communication interface 23 for the electronic device to communicate with other devices or a communication network.

[0169] In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions used by electronic devices, which includes a program for executing the method for predicting the advertising delivery effect in the embodiments shown in Figures 1 to 7 above.

[0170] In addition, an embodiment of the present invention provides a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when the computer instructions are executed by one or more processors, causes the one or more processors to execute the steps of the method for predicting the advertising delivery effect in the method embodiments shown in Figures 1-7 above.

[0171] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0172] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by a combination of hardware and software. Based on this understanding, the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a computer product. The present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable device to produce a machine, so that the instructions executed by the processor of the computer or other programmable device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0174] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device that implements the functions specified in one or more processes of the flowchart and / or one or more blocks of the block diagram. These computer program instructions may also be loaded onto a computer or other programmable device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes of the flowchart and / or one or more blocks of the block diagram. In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory in the form of read-only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

[0175] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for predicting the effect of advertising, characterized in that: include: Obtaining a plan identifier corresponding to the advertising delivery plan and an estimated delivery cost; Based on the plan identifier and the estimated delivery cost, determine a delivery function parameter in an advertisement delivery function and a weight function parameter in a weight function, wherein the advertisement delivery function is used to identify the relationship between the delivery cost and the delivery effect, and the weight function is used to determine the weight of the delivery effect obtained by the advertisement delivery function; Before delivering the advertisement delivery plan, the advertisement delivery effects corresponding to different delivery costs are determined based on the delivery function parameters, the weight function parameters, the advertisement delivery function and the weight function, and the different delivery costs at least include the estimated delivery costs.

2. The method according to claim 1, characterized in that Based on the plan identifier and the estimated delivery cost, determining delivery function parameters in the advertisement delivery function and weight function parameters in the weight function includes: Determine offline features corresponding to the advertising delivery plan based on the plan identifier, the offline features including: plan attributes, plan historical effects, and user attributes; Based on the estimated delivery cost and the offline feature, delivery function parameters in the advertisement delivery function and weight function parameters in the weight function are determined.

3. The method according to claim 1, characterized in that Based on the delivery function parameters, the weight function parameters, the advertisement delivery function and the weight function, determining the advertisement delivery effects corresponding to different delivery costs, including: Based on the estimated delivery cost, determining a plurality of different delivery costs; Determine the delivery effects corresponding to different delivery costs based on the delivery function parameters and the advertisement delivery function; Based on the weight function parameters and the weight function, determining weight information corresponding to different delivery costs; Based on the delivery effect and the weight information, the advertisement delivery effects corresponding to different delivery costs are determined.

4. The method according to claim 3, characterized in that Based on the delivery effect and the weight information, determining the advertising delivery effects corresponding to different delivery costs, including: The product value of the delivery effect corresponding to different delivery costs and the weight information is determined as the advertising delivery effect corresponding to the different delivery costs.

5. The method according to claim 3, characterized in that: Based on the delivery effect and the weight information, determining the advertising delivery effects corresponding to different delivery costs, including: Acquire delivery auxiliary parameters corresponding to the advertisement delivery plan, wherein the delivery auxiliary parameters include at least one of the following: delivery time parameter, delivery area parameter, and delivery crowd parameter; The product value between the delivery effects corresponding to different delivery costs, the weight information and the delivery auxiliary parameters is determined as the advertisement delivery effects corresponding to different delivery costs.

6. The method according to claim 1, characterized in that The advertisement delivery function is a monotonic function used to identify that there is a positive correlation between delivery cost and delivery effect; the delivery cost includes a delivery budget; and the delivery effect includes at least one of the following: exposure, clicks, and consumption.

7. The method according to claim 1, characterized in that The delivery function parameters include a first parameter for limiting the upper limit of delivery effect and a second parameter for limiting the change rate of the advertisement delivery function; the weight function parameters include a third parameter for limiting the upper limit of weight.

8. The method according to claim 1, characterized in that The method further comprises: Obtaining an estimated consumption upper limit value corresponding to the advertising delivery plan; When the estimated delivery cost is less than or equal to the estimated consumption upper limit value, determining the weight function to be a first monotonic function for identifying a positive correlation between the delivery cost and the weight information; When the estimated delivery cost is greater than the estimated consumption upper limit, the weight function is determined to be a second monotonic function for identifying a positive correlation between the delivery cost and the weight information, and the first monotonic function is different from the second monotonic function.

9. The method according to claim 8, characterized in that Obtaining the estimated consumption upper limit value corresponding to the advertising delivery plan, including: Acquire a consumption function corresponding to the advertisement delivery plan and function parameters corresponding to the consumption function; Based on the consumption function, function parameters and estimated delivery cost, an estimated consumption upper limit value corresponding to the advertisement delivery plan is determined.

10. The method according to any one of claims 1 to 9, characterized in that: After determining the advertising delivery effects corresponding to different delivery costs, the method further includes: Obtaining a bid lower limit value corresponding to the advertising delivery plan; Determine the corresponding bids for different delivery costs; When the delivery bid is greater than or equal to the bid lower limit, a first identifier corresponding to the advertisement delivery effect is determined, where the first identifier is used to identify that the advertisement delivery effect can be obtained; When the delivery input information is less than the bid lower limit, a second identifier corresponding to the advertisement delivery effect is determined, and the second identifier is used to identify that the advertisement delivery effect cannot be obtained.

11. The method according to claim 10, characterized in that Get the bid lower limit value corresponding to the advertising delivery plan, including: Obtain the corresponding lower limit parameters and historical click-through rates of the products to be promoted through product exposure logs; Based on the exposure lower limit parameter and the historical click-through rate, a bid lower limit value corresponding to the advertisement delivery plan is determined.

12. An electronic device, characterized in that: include: A memory, a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method as described in any one of claims 1-11.

Images