Advertisement putting method and system based on multi-objective optimization algorithm

Abstract

The invention discloses an advertisement putting method and system based on a multi-objective optimization algorithm, and relates to the technical field of advertisement putting, and the method comprises the steps: setting an optimization objective of each stage, distributing a preliminary weight for the optimization objective, dividing an advertisement putting period according to the preliminary weight, and carrying out the resource distribution; according to the optimization target and the preliminary weight, a preliminary advertisement putting strategy is generated and executed; real-time performance data and resource consumption conditions in the preliminary advertisement putting process are collected in real time, and the advertisement putting effect of the previous stage is analyzed; according to the analysis result, dynamically adjusting the initial weight of the optimization target in the next stage; and optimizing the preliminary advertisement putting strategy based on the adjusted weight of the optimization target. According to the method, the optimization target of each stage is set and the preliminary weight is allocated, so that reasonable division of an advertisement putting period and accurate allocation of resources are realized, the advertisement targets such as exposure, click rate and conversion rate of different stages can be fully concerned, and waste of resources is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of advertisement delivery, and in particular to an advertisement delivery method and system based on a multi-objective optimization algorithm. Background Art

[0002] With the rapid development of the Internet advertising market, the complexity and diversity of advertising delivery are increasing. Traditional single-objective optimization methods can no longer effectively cope with the needs of multi-scenario and multi-objective advertising delivery. Advertisers not only want to maximize the exposure of advertisements at each stage of advertising delivery, but also want to adjust advertising strategies according to different time periods, market environments, and user behaviors to maximize click-through rates and conversion rates. Therefore, multi-objective optimization algorithms have gradually become a research hotspot in the field of advertising delivery. In recent years, advertising delivery methods based on multi-objective optimization have been gradually introduced. By setting multiple optimization goals and comprehensively considering the performance of advertisements at different stages, they strive to achieve better optimization effects in multiple dimensions such as exposure, clicks, and conversions. This type of method not only improves the flexibility of advertising delivery, but also provides advertisers with more refined delivery strategies, and therefore has received widespread attention.

[0003] However, the existing advertising delivery technologies based on multi-objective optimization algorithms still have some shortcomings in practical applications. First, these technologies often lack flexibility in resource allocation and fail to fully consider the dynamic demand changes in each stage of the advertising delivery cycle. Specifically, the existing technologies usually adopt a method of evenly allocating resources when dividing the delivery cycle. This strategy ignores the differences in market environment, user behavior and stage goals, resulting in resource waste or improper allocation. Secondly, the existing advertising delivery strategies have a lag in weight adjustment. They usually execute the established weight allocation within a fixed period and fail to dynamically adjust the strategies of subsequent stages according to the real-time advertising delivery effects, making it difficult to fully respond to the rapid changes in the market environment and the immediate feedback of user behavior. These shortcomings have, to some extent, limited the flexibility and intelligence level of advertising delivery strategies. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an advertisement delivery method based on a multi-objective optimization algorithm to solve the problems of lack of flexibility in resource allocation and lag in weight adjustment in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an advertising delivery method based on a multi-objective optimization algorithm, which includes setting optimization goals for each stage, assigning preliminary weights to the optimization goals, dividing the advertising delivery cycle according to the preliminary weights and allocating resources; generating and executing a preliminary advertising delivery strategy according to the optimization goals and the preliminary weights; collecting real-time performance data and resource consumption during the preliminary advertising delivery process, and analyzing the advertising delivery effect of the previous stage; dynamically adjusting the preliminary weights of the optimization goals for the next stage according to the analysis results; and optimizing the preliminary advertising delivery strategy based on the adjusted weights of the optimization goals.

[0008] As a preferred solution of the advertising delivery method based on the multi-objective optimization algorithm of the present invention, wherein: the optimization target of each stage is set, and a preliminary weight is assigned to the optimization target. The specific steps are as follows:

[0009] Determine the total advertising cycle and total advertising resources based on business needs and marketing plans;

[0010] According to the total advertising cycle, the advertising cycle is divided into the warm-up stage, the main promotion stage and the sprint stage according to uneven time;

[0011] In the warm-up phase, maximizing exposure is defined as the optimization goal;

[0012] In the main promotion stage, define maximizing click-through rate as the optimization goal;

[0013] In the sprint phase, define maximizing conversion rate as the optimization goal;

[0014] By performing exponential and sinusoidal processing and difference adjustment on the information entropy of each target, a preliminary weight is assigned to the optimization target. The expression is:

[0015]

[0016] in, It is The initial weights of the optimization objectives, No. The information entropy value of the optimization target is is the total number of optimization objectives, is the index variable of the optimization target, is the adjustment coefficient for adjusting the weight distribution difference of the information entropy value of the optimization target, It is the adjustment coefficient that controls the weakening strength of the weight of the high entropy target. It is the maximum value of the information entropy of all optimization targets.

[0017] As a preferred solution of the advertising delivery method based on the multi-objective optimization algorithm of the present invention, the advertising delivery cycle is divided according to the preliminary weights and resources are allocated. The specific steps are as follows:

[0018] The advertising resources of each stage divided by non-uniform time are allocated non-uniformly according to the market demand and user behavior changes in each stage. The expression is:

[0019]

[0020] in, It is The amount of advertising resources in each stage, Total advertising inventory, It is The market activity at each stage, It is in Behavioral characteristics of users at each stage, It is the index variable of the ad serving stage.

[0021] As a preferred solution of the advertisement delivery method based on the multi-objective optimization algorithm described in the present invention, the preliminary advertisement delivery strategy includes advertisement channel selection, advertisement material design, advertisement targeting setting, budget and frequency.

[0022] As a preferred solution of the advertising delivery method based on the multi-objective optimization algorithm described in the present invention, the real-time performance data during the advertising delivery process includes exposure, click volume, conversion volume, click rate and conversion rate;

[0023] The resource consumption includes advertising budget consumption, click cost, display cost and conversion cost in each time period;

[0024] The specific steps of analyzing the advertising effect in the pre-stage are as follows:

[0025] Through the relationship between exposure, clicks, conversions and budget consumption, logarithmic transformation is used to weaken the maximum impact of exposure and resource consumption. At the same time, the click-through rate and conversion rate are used to measure the advertising effect. The expression is:

[0026]

[0027] in, It is Stages at a time point Exposure, It is Stages at a time point of clicks, It is Stages at a time point The amount of conversion, It is Stages at a time point The resource consumption, is a small positive number that prevents the denominator from being zero, It is Stages at a time point The advertising effectiveness index of the stage, Indicates Stages at a time point The amount of advertising resources invested.

[0028] As a preferred solution of the advertising delivery method based on the multi-objective optimization algorithm of the present invention, the specific steps of dynamically adjusting the initial weight of the optimization target of the next stage according to the analysis results are as follows:

[0029] Through the effect index of the current stage and the effect threshold of each optimization target, the hyperbolic tangent function is used to smooth the difference between the effect index and the threshold, and the initial weight of the optimization target is dynamically adjusted. The expression is:

[0030]

[0031] in, For the The optimization goal is The weight after dynamic adjustment in the stage, is the adjustment coefficient that controls the initial weight adjustment range of the optimization target. It is The effect threshold corresponding to the optimization goal, Indicates The optimization goal is at the time point The initial weight of .

[0032] As a preferred solution of the advertising delivery method based on the multi-objective optimization algorithm described in the present invention, wherein: the initial advertising delivery strategy is optimized based on the weight of the adjusted optimization target, and the specific steps are as follows:

[0033] Weights based on the adjusted optimization goal , reallocate the advertising resources in each stage;

[0034] According to the adjusted The amount of advertising inventory in each stage , optimize the initial advertising strategy.

[0035] In the second aspect, the present invention provides an advertising delivery system based on a multi-objective optimization algorithm, including a resource allocation module, a strategy generation module, an effect analysis module, a weight optimization module and a strategy optimization module; the resource allocation module is used to set the optimization target for each stage, assign preliminary weights to the optimization targets, divide the advertising delivery cycle according to the preliminary weights and allocate resources; the strategy generation module is used to generate and execute a preliminary advertising delivery strategy according to the optimization targets and preliminary weights; the effect analysis module is used to collect real-time performance data and resource consumption during the preliminary advertising delivery process, and analyze the advertising delivery effect of the previous stage; the weight optimization module is used to dynamically adjust the preliminary weights of the optimization targets of the next stage according to the analysis results; the strategy optimization module is used to optimize the preliminary advertising delivery strategy based on the weights of the adjusted optimization targets.

[0036] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the advertising delivery method based on a multi-objective optimization algorithm as described in the first aspect of the present invention.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the advertising delivery method based on a multi-objective optimization algorithm as described in the first aspect of the present invention.

[0038] The beneficial effects of the present invention are as follows: by setting the optimization goals for each stage and assigning preliminary weights, a reasonable division of the advertising delivery cycle and precise allocation of resources are achieved, ensuring that advertising goals at different stages such as exposure, click-through rate, and conversion rate can receive sufficient attention, thus avoiding waste of resources; during the advertising delivery process, advertising performance data and resource consumption are collected in real time, the effect of the previous stage is analyzed, and the optimization target weights for the next stage are dynamically adjusted based on the analysis results, so that advertising strategies can flexibly respond to changes in the market and user behavior, ultimately improving the overall effect of advertising delivery and resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0040] Figure 1 This is a flow chart of the advertising delivery method based on the multi-objective optimization algorithm in Example 1.

[0041] Figure 2This is a schematic diagram of an advertisement delivery system based on a multi-objective optimization algorithm in Example 1. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0044] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0045] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an advertisement delivery method based on a multi-objective optimization algorithm, comprising the following steps:

[0046] S1: Set optimization goals for each stage, assign preliminary weights to the optimization goals, divide the advertising delivery cycle according to the preliminary weights, and allocate resources.

[0047] S1.1: Determine the total advertising cycle and total advertising resources based on business needs and marketing plans;

[0048] For example, a 30-day promotion campaign with a total advertising budget of 1 million yuan is determined. Then, the delivery cycle is divided into the warm-up stage (the first 5 days), the main promotion stage (the next 15 days), and the sprint stage (the last 10 days), and advertising resources are reasonably allocated according to the goals of each stage: for example, in the warm-up stage, 20% of the budget is allocated to maximize exposure; in the main promotion stage, 50% of the budget is allocated to increase click-through rate; in the sprint stage, the remaining 30% of the budget is allocated to increase conversion rate.

[0049] S1.2: Based on the total advertising cycle, the advertising cycle is divided into the warm-up phase, the main promotion phase and the sprint phase according to non-uniform time;

[0050] In the warm-up phase, maximizing exposure is defined as the optimization goal;

[0051] In the main promotion stage, define maximizing click-through rate as the optimization goal;

[0052] In the sprint phase, define maximizing conversion rate as the optimization goal;

[0053] Specifically: Stage division example:

[0054] It can also be divided according to market activities, for example:

[0055] Phase 1: The first 5 days are the warm-up phase.

[0056] Phase 2: The next 15 days are the main promotion phase.

[0057] Phase 3: The last 10 days are the sprint phase.

[0058] S1.3: By performing exponential, sinusoidal processing and difference adjustment on the information entropy of each target, a preliminary weight is assigned to the optimization target, which is expressed as:

[0059]

[0060] in, It is The initial weights of the optimization objectives, No. The information entropy value of the optimization target is is the total number of optimization objectives, is the index variable of the optimization target, is the adjustment coefficient for adjusting the weight distribution difference of the information entropy value of the optimization target, It is the adjustment coefficient that controls the weakening strength of the weight of the high entropy target. It is the maximum value of the information entropy of all optimization targets.

[0061] Furthermore, the information entropy value of the optimization target is expressed as:

[0062]

[0063] in, is the total number of ad delivery stages, It is Optimization goal of each stage The proportion of It is the index variable of the ad serving stage.

[0064] It should also be noted that this process performs complex mathematical processing on each optimization target, makes adjustments based on the differences between the targets, and reasonably allocates the initial weights of each optimization target. This weight allocation method ensures that resources can be allocated according to the priority of different targets during the advertising process, balancing the needs of each stage and ultimately optimizing the overall advertising effect.

[0065] S1.4: The advertising resources of each stage divided according to the non-uniform time are allocated non-uniformly according to the market demand and user behavior changes in each stage. The expression is:

[0066]

[0067] in, It is The amount of advertising resources in each stage, Total advertising inventory, It is The market activity at each stage, It is in Behavioral characteristics of users at each stage, It is the index variable of the ad serving stage.

[0068] Furthermore, user behavior characteristics are obtained by collecting the interaction data between users and advertisements in real time through the advertising platform, and analyzing and processing them. For example, the platform will record whether the user clicks on the advertisement, how long he stays on the advertisement page, and whether he makes further purchases or registrations. Taking an advertisement as an example, suppose that the user clicks on the link after seeing the advertisement, stays on the target page for 30 seconds, and then completes the purchase. The platform will extract and analyze the user's click behavior, stay time, and conversion behavior as user behavior characteristics, calculate the user's responsiveness and engagement with the advertisement, and thus provide a basis for the optimization of advertisements at this stage.

[0069] S2: Generate and execute a preliminary advertising delivery strategy based on the optimization goals and preliminary weights.

[0070] S2.1: The initial advertising strategy includes the selection of advertising channels, the design of advertising creatives, the setting of advertising targeting, and the budget and frequency.

[0071] Furthermore, based on the optimization goals and resource amounts at each stage, select advertising delivery channels;

[0072] For example, in the warm-up phase, choose display ads or video ads with high exposure; in the main promotion phase, choose search ads or social media ads that increase click-through rates; in the sprint phase, choose remarketing ads or promotional email ads with high conversion rates.

[0073] Design corresponding advertising materials according to the optimization goals of each stage;

[0074] For example, in the warm-up stage, advertising materials should focus on brand exposure and use pictures or videos with strong visual impact; in the main promotion stage, the materials should highlight product advantages and promotional information to encourage users to click; in the sprint stage, advertising materials should emphasize the sense of urgency and the strength of the discount to prompt users to complete the purchase as soon as possible.

[0075] Ad targeting settings and budget frequency control should also be adjusted according to the goals of each stage. In the warm-up stage, ad targeting can be broader to cover more potential users; in the main promotion stage, it should focus on user groups with higher click potential; in the sprint stage, targeting should be more precise to lock in users with purchasing intentions. Budget and frequency should be reasonably controlled according to resource allocation at each stage to ensure maximum advertising effect.

[0076] S3: Collect real-time performance data and resource consumption during the initial advertising process, and analyze the advertising effect of the previous stage.

[0077] S3.1: Real-time performance data during the advertising process includes impressions, clicks, conversions, click-through rates, and conversion rates;

[0078] Furthermore, real-time performance data during the advertising delivery process is automatically collected through the advertising platform's monitoring system. The platform records the user's interaction with the advertisement, such as the number of ad displays (exposures), user click behavior (clicks), and completed conversion actions (conversions), and calculates the click-through rate by calculating the ratio of clicks to exposures, and the conversion rate by calculating the ratio of conversions to clicks.

[0079] S3.2: Resource consumption includes advertising budget consumption, click cost, display cost and conversion cost in each time period;

[0080] Furthermore, the real-time resource consumption during the advertising delivery process is obtained through the billing system of the advertising platform. The platform automatically calculates and records the corresponding advertising budget consumption, the cost per click (click cost), the cost per display (display cost), and the cost per conversion (conversion cost) based on the advertising display, click, and conversion events in each time period.

[0081] S3.3: Analyze the advertising effect in the previous stage. The specific steps are as follows:

[0082] Through the relationship between exposure, clicks, conversions and budget consumption, logarithmic transformation is used to weaken the maximum impact of exposure and resource consumption. At the same time, the click-through rate and conversion rate are used to measure the advertising effect. The expression is:

[0083]

[0084] in, It is Stages at a time point Exposure, It is Stages at a time point of clicks, It is Stages at a time point The amount of conversion, It is Stages at a time point The resource consumption, is a small positive number that prevents the denominator from being zero, It is Stages at a time point The advertising effectiveness index of the stage, Indicates Stages at a time point The amount of advertising resources invested.

[0085] Furthermore, The higher the index, the better the effect, and the value is usually between 0 and 10. The specific value range is explained as follows:

[0086] : The stage effect is poor, and the weights of the optimization objectives need to be significantly adjusted.

[0087] : The stage effect is medium, and the weight of the optimization target should be adjusted appropriately.

[0088] : The stage effect is good, and the optimization target weights can be maintained or slightly adjusted.

[0089] It should be noted that this expression comprehensively processes exposure, clicks, conversions and budget consumption, and uses logarithmic transformation to weaken the impact of the maximum values ​​in exposure and resource consumption, ensuring that the calculation process is not disturbed by abnormal values ​​of a single indicator. At the same time, the actual effect of the advertisement is further measured by the ratio of click-through rate and conversion rate. The algorithm calculates the relationship between exposure, clicks, conversions and resource consumption in a refined manner to obtain the advertising effect index. , in order to more accurately evaluate the advertising performance at each stage. It can dynamically and objectively reflect the effect of advertising, avoid the distortion of the overall effect by extreme data, and provide a reliable basis for subsequent strategy optimization.

[0090] S4: Dynamically adjust the preliminary weights of the next stage optimization objectives based on the analysis results.

[0091] S4.1: Based on the effect index of the current stage and the effect threshold of each optimization target, the hyperbolic tangent function is used to smooth the difference between the effect index and the threshold, and the initial weight of the optimization target is dynamically adjusted. The expression is:

[0092]

[0093] in, For the The optimization goal is The weight after dynamic adjustment in the stage, is the adjustment coefficient that controls the initial weight adjustment range of the optimization target. It is The effect threshold corresponding to the optimization goal, Indicates The optimization goal is at the time point The initial weight of .

[0094] Furthermore, It is defined based on historical data and business goals. The definition process first analyzes past advertising data and calculates the average effect level and fluctuation range of each optimization goal (such as exposure, click-through rate, conversion rate, etc.). Combined with specific business needs and market conditions, set a reasonable target benchmark. For example, by analyzing past advertising, it is determined that the historical average click-through rate is 2%, and it is set as the threshold according to the business growth goal. .

[0095] It should be noted that this expression combines the effect index of the current stage The effect threshold of each optimization goal The difference between Smooth the differences to avoid drastic fluctuations when adjusting weights. Dynamically adjust the coefficient based on this smoothed difference Control the adjustment range to ensure the flexibility and stability of weight adjustment. Ultimately, the weights of all targets will be redistributed through normalization (denominator), so that the weights of each optimization target can dynamically adapt according to the real-time effect during the advertising process, optimizing the allocation of advertising resources. The beneficial effect of this algorithm is that it avoids over-response to short-term fluctuations through smoothing, while ensuring that the advertising delivery strategy can be flexibly adjusted according to the actual effect.

[0096] S5: Optimize the initial advertising delivery strategy based on the adjusted weights of the optimization objectives.

[0097] S5.1: Weights based on adjusted optimization objectives , reallocate the advertising resources in each stage;

[0098] Specifically: First, according to the current weight adjustment results of each stage, calculate the priority of each optimization goal in advertising delivery. Then, reallocate the total advertising resources to each stage according to the new weight ratio to ensure that resource allocation more accurately matches the current optimization goal.

[0099] For example, by adjusting the optimization target weight The specific process of reallocating advertising resources at each stage is as follows:

[0100] Assume that the total advertising budget for the warm-up phase, the main promotion phase, and the sprint phase is 1 million yuan. In the initial resource allocation, the weights of the three phases are =0.3, =0.4, =0.3, so the initial amount of resources allocated is:

[0101] Preheating stage: 300,000 yuan

[0102] Main promotion stage: 400,000 yuan

[0103] Sprint stage: 300,000 yuan

[0104] After the advertisement was launched, the weight of the optimization target was recalculated based on the performance of each stage. The adjusted weight is =0.2, =0.5, =0.3.

[0105] When reallocating resources, according to the new weight ratio, the advertising resources will be reallocated as follows:

[0106] Preheating stage: 1 million yuan × 0.2 = 200,000 yuan

[0107] Main promotion stage: 1 million yuan × 0.5 = 500,000 yuan

[0108] Sprint stage: 1 million yuan × 0.3 = 300,000 yuan

[0109] Therefore, resource allocation has changed. The main promotion phase gets more advertising resources (from 400,000 yuan to 500,000 yuan) due to its increased weight, while the warm-up phase gets less resources (from 300,000 yuan to 200,000 yuan) due to its decreased importance. In this way, advertising resource allocation can dynamically adapt to the actual needs and target weight of each stage to ensure the maximum effect of advertising.

[0110] S5.2: Based on the adjusted The amount of advertising resources in each stage is used to optimize the initial advertising delivery strategy.

[0111] Furthermore, first of all, the reallocated advertising resources are used to review and adjust the advertising delivery strategy at this stage to ensure the effective use of resources.

[0112] Specifically, the optimization strategies include: Adjust advertising channels. According to changes in resources, choose advertising channels that are more suitable for the current budget. For example, when the budget is increased, choose channels with high conversion rates. When the budget is reduced, give priority to low-cost exposure channels.

[0113] Optimize advertising materials to ensure that the design of advertising materials matches the goals of the current stage and increase user clicks and conversion rates;

[0114] For example, in the main promotion stage, the goal is to increase the click-through rate and increase the advertising inventory to 500,000 yuan. In order to attract more users to click, the creative can highlight the unique selling points of the product and limited-time discount information. If the promotion is a smart watch, the creative can be designed to emphasize its core functions (such as "real-time heart rate monitoring" and "all-weather waterproof"), and add the promotional information of "limited-time 50% discount, only today" in the copy. Such a design can attract users to click and increase the click-through rate.

[0115] Optimize targeted settings by analyzing user behavior data to adjust the accuracy of the target audience and lock in higher-value user groups;

[0116] For example, in the sprint phase, the goal is to increase conversion rates, and the advertising inventory remains at 300,000 yuan. By analyzing user behavior data, it is found that some users (such as users who have visited the product page but have not completed the purchase) have higher conversion potential. Therefore, the ad targeting settings can be adjusted to deliver remarketing ads specifically for these user groups. For example, personalized promotional ads (such as "The items in your shopping cart are now enjoying an extra discount") are displayed to these users, thereby effectively improving the conversion rate.

[0117] Budget and frequency control: reasonably arrange daily budget and advertising exposure frequency according to the new resource amount to avoid resource waste or insufficient exposure, and ensure the maximum effect of continuous advertising delivery.

[0118] For example, in the warm-up phase, the goal is to increase brand exposure, and the amount of advertising resources is reduced to 200,000 yuan. In order to avoid wasting resources, the advertising budget and exposure frequency need to be reasonably controlled. Assuming the daily budget is 20,000 yuan, if the advertising frequency is too high (the same user sees the ad multiple times in one day), it may cause user fatigue and lead to reduced effectiveness. Therefore, an upper limit on the advertising frequency can be set, for example, each user can see the ad up to 3 times a day, which can ensure wide exposure of the ad while avoiding excessive display to the same user, improving resource utilization efficiency.

[0119] The present embodiment also provides an advertising delivery system based on a multi-objective optimization algorithm, including: a resource allocation module, a strategy generation module, an effect analysis module, a weight optimization module and a strategy optimization module; the resource allocation module is used to set the optimization target of each stage, assign preliminary weights to the optimization targets, divide the advertising delivery cycle according to the preliminary weights and allocate resources; the strategy generation module is used to generate and execute a preliminary advertising delivery strategy according to the optimization targets and preliminary weights; the effect analysis module is used to collect real-time performance data and resource consumption during the preliminary advertising delivery process in real time, and analyze the advertising delivery effect of the previous stage; the weight optimization module is used to dynamically adjust the preliminary weight of the optimization target of the next stage according to the analysis results; the strategy optimization module is used to optimize the preliminary advertising delivery strategy based on the weight of the adjusted optimization target.

[0120] This embodiment also provides a computer device, which is suitable for the case of an advertising delivery method based on a multi-objective optimization algorithm, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the advertising delivery method based on a multi-objective optimization algorithm as proposed in the above embodiment.

[0121] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0122] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for implementing advertisement delivery based on a multi-objective optimization algorithm as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0123] In summary, the present invention achieves a reasonable division of the advertising delivery cycle and accurate allocation of resources by: setting optimization goals for each stage and assigning preliminary weights, ensuring that advertising goals at different stages such as exposure, click-through rate, and conversion rate can receive sufficient attention and avoid waste of resources; during the advertising delivery process, real-time collection of advertising performance data and resource consumption, analysis of the effect of the previous stage, and dynamic adjustment of the optimization target weights for the next stage based on the analysis results, so that advertising strategies can flexibly respond to changes in the market and user behavior, ultimately improving the overall effect of advertising delivery and resource utilization efficiency.

[0124] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of an advertisement delivery method based on a multi-objective optimization algorithm is provided.

[0125] The total advertising cycle is 30 days, and the advertising budget is 1 million yuan. According to market promotion needs, the advertising cycle is divided into three stages: warm-up stage (first 5 days), main promotion stage (next 15 days), sprint stage (last 10 days). The optimization goals of each stage are: maximizing exposure in the warm-up stage, maximizing click-through rate in the main promotion stage, and maximizing conversion rate in the sprint stage. The allocation ratio of advertising resources is: 20% in the warm-up stage, 50% in the main promotion stage, and 30% in the sprint stage. The optimization goals are weighted as follows:

[0126] =0.8, =0.7, =0.9, =0.5, =2, =0.9, =0.1,;

[0127] The above data The expression is as follows (only shown here ):

[0128]

[0129] The calculation results are shown in Table 1 below:

[0130] Table 1 Preliminary weight distribution table of optimization objectives

[0131]

[0132] First, this experiment divides advertising into three stages according to the overall advertising cycle and market promotion needs: warm-up stage, main promotion stage and sprint stage. The optimization goals of each stage are exposure, click-through rate and conversion rate. The advertising budget is initially allocated according to the needs of different stages, as follows:

[0133] R = 1 million yuan, =0.6, =0.8, =0.5, =0.4, =0.7, =0.9;

[0134] Substituting the above data into the expression is as follows (only the ):

[0135]

[0136] The calculation results are shown in Table 2 below:

[0137] Table 2 Advertising resource allocation table

[0138]

[0139] Secondly, based on information entropy calculation and user behavior feature analysis, the advertising resource allocation weights at each stage are dynamically adjusted. By analyzing the user clicks, dwell time, and conversion behaviors collected in real time by the advertising platform, resource allocation is further optimized to make advertising delivery more accurate and effective, as follows:

[0140] =0.0685, =0.075, =0.082, =0.05, =0.04, =0.06;

[0141] Substituting the above data into the expression is as follows (only the ):

[0142]

[0143] The calculation results are shown in Table 3 below:

[0144] Table 3 Optimization target preliminary weight update results

[0145]

[0146] Finally, in order to verify the effectiveness of the optimization strategy proposed in the present invention, this embodiment conducted a comparative experiment to test the effects of the traditional advertising delivery strategy and the optimization strategy proposed in the present invention. The traditional advertising delivery strategy adopts a method of evenly allocating resources in a fixed ratio, and does not consider the differences in market demand and user behavior characteristics in each stage during the entire delivery cycle. Specifically, the traditional strategy simply divides the advertising cycle into a warm-up stage, a main push stage, and a sprint stage, and allocates an advertising budget of 1 million yuan to each stage at a ratio of 20%, 50%, and 30%, without dynamic adjustment. This method lacks pertinence and cannot optimize advertising effects based on real-time feedback. The main parameters of the comparative experiment include exposure, click-through rate, conversion rate, and advertising budget consumption.

[0147] The details are shown in Table 4 below:

[0148] Table 4 Advertising effect comparison table

[0149]

[0150] Through the data analysis of the above table, it can be clearly seen that the advertising effect of the strategy of the present invention is significantly better than that of the traditional strategy at each stage. The present invention achieves higher advertising effects with the same or lower budget consumption by improving the click-through rate and conversion rate. For example, in the sprint stage, the click-through rate of the strategy of the present invention is 1.85%, which is much higher than the 1.12% of the traditional strategy; at the same time, the conversion rate reaches 2.47%, which significantly exceeds the 1.98% of the traditional strategy. In addition, the click cost and conversion cost of the strategy of the present invention are also lower than those of the traditional strategy, further demonstrating its cost-effectiveness advantage.

[0151] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An advertisement delivery method based on a multi-objective optimization algorithm, characterized in that: include, Set optimization goals for each stage, assign preliminary weights to the optimization goals, divide the advertising delivery cycle according to the preliminary weights, and allocate resources; Generate and execute preliminary advertising delivery strategies based on optimization goals and preliminary weights; Collect real-time performance data and resource consumption during the initial advertising process, and analyze the advertising effects of the previous stage; Dynamically adjust the initial weights of the next stage optimization objectives based on the analysis results; Optimize the initial advertising delivery strategy based on the adjusted initial weights of the optimization objectives.

2. The advertisement delivery method based on the multi-objective optimization algorithm according to claim 1, characterized in that: The optimization goal of each stage is set, and preliminary weights are assigned to the optimization goals. The specific steps are as follows: Determine the total advertising cycle and total advertising resources based on business needs and marketing plans; According to the total advertising cycle, the advertising cycle is divided into the warm-up stage, the main promotion stage and the sprint stage according to uneven time; In the warm-up phase, maximizing exposure is defined as the optimization goal; In the main promotion stage, define maximizing click-through rate as the optimization goal; In the sprint phase, define maximizing conversion rate as the optimization goal; By performing exponential and sinusoidal processing and difference adjustment on the information entropy of each target, a preliminary weight is assigned to the optimization target. The expression is: in, It is The initial weights of the optimization objectives, No. The information entropy value of the optimization target is is the total number of optimization objectives, is the index variable of the optimization target, is the adjustment coefficient for adjusting the weight distribution difference of the information entropy value of the optimization target, It is the adjustment coefficient that controls the weakening strength of the weight of the high entropy target. It is the maximum value of the information entropy of all optimization targets.

3. The advertisement delivery method based on the multi-objective optimization algorithm according to claim 2, characterized in that: The specific steps of dividing the advertising delivery cycle and allocating resources according to the preliminary weights are as follows: The advertising resources of each stage divided by non-uniform time are allocated non-uniformly according to the market demand and user behavior changes in each stage. The expression is: in, It is The amount of advertising resources in each stage, Total advertising inventory, It is The market activity at each stage, It is in Behavioral characteristics of users at each stage, It is the index variable of the ad serving stage.

4. The advertisement delivery method based on a multi-objective optimization algorithm according to claim 3, characterized in that: The preliminary advertising delivery strategy includes advertising channel selection, advertising creative design, advertising targeting setting, and budget and frequency.

5. The advertisement delivery method based on the multi-objective optimization algorithm according to claim 4, characterized in that: The real-time performance data during the advertising delivery process includes exposure, clicks, conversions, click-through rate and conversion rate; The resource consumption includes advertising budget consumption, click cost, display cost and conversion cost in each time period; The specific steps of analyzing the advertising effect in the pre-stage are as follows: Through the relationship between exposure, clicks, conversions and budget consumption, logarithmic transformation is used to weaken the maximum impact of exposure and resource consumption. At the same time, the click-through rate and conversion rate are used to measure the advertising effect. The expression is: in, It is Stages at a time point Exposure, It is Stages at a time point of clicks, It is Stages at a time point The amount of conversion, It is Stages at a time point The resource consumption, is a small positive number that prevents the denominator from being zero, It is Stages at a time point The advertising effectiveness index of the stage, Indicates Stages at a time point The amount of advertising resources invested.

6. The advertisement delivery method based on a multi-objective optimization algorithm according to claim 5, characterized in that: The specific steps of dynamically adjusting the initial weight of the optimization target in the next stage according to the analysis results are as follows: Through the effect index of the current stage and the effect threshold of each optimization target, the hyperbolic tangent function is used to smooth the difference between the effect index and the threshold, and the initial weight of the optimization target is dynamically adjusted. The expression is: in, For the The optimization goal is The weight after dynamic adjustment in the stage, is the adjustment coefficient that controls the initial weight adjustment range of the optimization target. It is The effect threshold corresponding to the optimization goal is Indicates The optimization goal is at the time point The initial weight of .

7. The advertisement delivery method based on a multi-objective optimization algorithm according to claim 6, characterized in that: The specific steps of optimizing the initial advertising delivery strategy based on the adjusted optimization target weight are as follows: Weights based on the adjusted optimization goal , reallocate the advertising resources in each stage; According to the adjusted The amount of advertising inventory in each stage , optimize the initial advertising strategy.

8. An advertisement delivery system based on a multi-objective optimization algorithm, based on the advertisement delivery method based on a multi-objective optimization algorithm according to any one of claims 1 to 7, characterized in that: Including resource allocation module, strategy generation module, effect analysis module, weight optimization module and strategy optimization module; Resource allocation module, which is used to set the optimization target for each stage, assign preliminary weights to the optimization targets, divide the advertising delivery cycle according to the preliminary weights, and allocate resources; A strategy generation module is used to generate and execute a preliminary advertising delivery strategy based on the optimization objectives and preliminary weights; The effect analysis module is used to collect real-time performance data and resource consumption during the initial advertising process and analyze the advertising effect of the previous stage; The weight optimization module is used to dynamically adjust the initial weight of the optimization target in the next stage according to the analysis results; The strategy optimization module is used to optimize the initial advertising delivery strategy based on the weights of the adjusted optimization objectives.

Images