Internet-based network advertisement promotion method and system

Abstract

The invention relates to the technical field of network advertisement promotion, in particular to a network advertisement promotion method and system based on the Internet, and the method comprises the following steps: obtaining user behavior data, analyzing a browsing track, a staying duration, a click frequency and an interactive behavior, calculating the activity of a user in real time, and recognizing the interest point of the user. And updating user tags in real time, classifying user groups, and generating a user tag data set. According to the method, the interest point of the user is identified, the user label is updated in real time, it is ensured that personalized recommendation of the advertisement conforms to the real-time behavior of the user, the active time period of the user is analyzed and predicted, resource waste caused by putting in a fixed time period is avoided, budget allocation is dynamically adjusted according to the adaptation degree between the behavior of the user and the platform, and the user experience is improved. The advertisement putting efficiency is improved, user behavior changes before and after advertisement display are compared, the advertisement putting effect is accurately evaluated, data support is provided for adjustment of advertisement strategies, and the advertisement putting effect and resource configuration are optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of network advertising promotion, and particularly to a network advertising promotion method and system based on the Internet. Background Art

[0002] The technical field of network advertising promotion includes various technical methods for advertising release and promotion through Internet platforms. With the rapid development of the Internet, network advertising has become an important part of modern business. This field mainly focuses on efficiently delivering advertising information to target audiences through digital means, including search engine advertising, social media advertising, and email advertising, covering advertising positioning, placement, management, and effect analysis. Through user behavior analysis, advertising content recommendation, bidding ranking algorithms, and placement strategy optimization, the effect and placement efficiency of advertisements are optimized to achieve precision marketing and optimal allocation of resources.

[0003] Among them, the network advertising promotion method based on the Internet refers to achieving precise push and promotion of advertisements through various technical means using Internet platforms, covering advertising placement strategies and implementation methods. Specifically, it includes recommending and displaying personalized advertisements based on users' browsing behaviors, interests, and various relevant data. By analyzing users' historical data and combining with the target audience groups of advertisers, various push algorithms are adopted to determine the display method and time of advertising content, improving the placement effect of advertisements. Combining data tracking and effect analysis after advertisement display, by collecting and processing user feedback information, the advertising promotion strategy is further optimized.

[0004] The network advertising promotion method relies on static data models and preset placement strategies and cannot respond to changes in user behavior and market environment in real time. It pushes advertisements through user tags but lacks the ability to update in real time, resulting in lag in advertisement recommendations and being unable to accurately reflect users' latest needs, limiting the advertisement push effect when users' interests change significantly over time. Traditional advertisement placement often arranges pushes according to fixed time periods, ignoring the changes in user activity at different times, causing waste of advertising resources and inefficient placement. The evaluation of the adaptability between the platform and users is based on outdated behavioral data or assumptions, lacking comprehensive analysis of multi-platform and real-time interaction data, resulting in blind spots in advertising resource allocation and platform selection, making the accuracy and effect of advertisement placement unable to reach the optimal state and affecting the input-output ratio of advertisements. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, embodiments of the present invention provide a network advertising promotion method and system based on the Internet. The technical solution is as follows: To achieve the above object, the present invention adopts the following technical solutions. A method for promoting network advertisements based on the Internet includes the following steps: S1: Obtain user behavior data. By analyzing browsing trajectories, dwell times, click frequencies, and interaction behaviors, calculate the activity of users in real time, identify the interest points of users, update user tags in real time, classify user groups, and generate a user tag data set; S2: Invoke the user tag data set. By analyzing the activity of users in multiple time periods, identify the behavior patterns of users, analyze the active time periods of multiple user groups, and generate user active time period information; S3: Invoke the user active time period information. By analyzing the interaction data of users on multiple platforms, evaluate the attractiveness of multiple platforms to user groups, calculate the fitness between the platform and users, and generate an advertisement platform fitness value; S4: Utilize the advertisement platform fitness value to analyze advertisement content, identify the target user group, combine the user fitness of the platform, the active time period of the target user group, and the investment cost, calculate and adjust the budget allocation ratio, and generate an advertisement budget allocation result; S5: Utilize the advertisement budget allocation result. By comparing and analyzing the changes in user behavior before and after advertisement display, calculate and predict the advertisement delivery effect, and generate delivery effect evaluation information.

[0006] As a further solution of the present invention, the user tag data set includes user interest tags, user behavior patterns, and user activity information. The user active time period information includes the activity in multiple time periods, user behavior patterns, and the active time periods of multiple user groups. The advertisement platform fitness value includes platform attractiveness scores, platform conversion rates, and platform interaction frequencies. The advertisement budget allocation result includes advertisement delivery time periods, platform delivery priorities, and advertisement delivery user groups. The delivery effect evaluation information includes user conversion rates, advertisement interaction degrees, and delivery return rates.

[0007] As a further solution of the present invention, the steps of obtaining user behavior data, calculating the activity of users in real time by analyzing browsing trajectories, dwell times, click frequencies, and interaction behaviors, identifying the interest points of users, updating user tags in real time, and classifying user groups to generate a user tag data set are specifically as follows: S101: Obtain user behavior data. Utilize the browsing trajectories, dwell times, click frequencies, and interaction behavior data of users to calculate the activity of each user in real time, and obtain user activity data; S102: Based on the user activity data, by comparing the activity of users on multiple pages, identify the interest preferences of each user, and obtain an interest point identification result; S103: According to the POI recognition result, calculate the interest tag weights of each user in real time and update them, classify users into multiple user groups, and generate a user tag data set.

[0008] As a further solution of the present invention, the steps of calling the user tag data set, analyzing the activity of users in multiple time periods to identify the behavior patterns of users, analyzing the active time periods of multiple user groups, and generating user active time period information are specifically as follows: S201: Call the user tag data set, extract the behavior characteristics of users by analyzing the activity data of users in multiple time periods, and obtain user behavior characteristic data; S202: Based on the user behavior characteristic data, identify the behavior patterns of users, predict the behavior trends and active patterns of users in multiple time periods, and obtain user behavior pattern data; S203: According to the user behavior pattern data, identify the active time periods of multiple user groups by analyzing the behavior patterns of multiple users, and generate user active time period information.

[0009] As a further solution of the present invention, the steps of calling the user active time period information, analyzing the interaction data of users on multiple platforms, evaluating the attractiveness of multiple platforms to user groups, calculating the fitness between the platform and users, and generating an advertising platform fitness value are specifically as follows: S301: Call the user active time period information, obtain the interaction data of users on multiple platforms, calculate the interaction intensity of users on multiple platforms, and generate platform-user interaction intensity data; S302: Based on the platform-user interaction intensity data, analyze and calculate the attractiveness of multiple platforms to each user group, and generate platform attractiveness scores; S303: According to the platform attractiveness scores, combined with the matching degree between the active time period of users and the audience of the platform, evaluate the fitness of the platform to the target user group, calculate the fitness between the platform and users, and generate an advertising platform fitness value.

[0010] As a further solution of the present invention, the steps of using the advertising platform fitness value, analyzing the advertising content, identifying the target user group, combining the user fitness of the platform, the active time period of the target user group, and the investment cost, calculating and adjusting the budget allocation ratio, and generating an advertising budget allocation result are specifically as follows: S401: Call the advertising platform fitness value, extract the key features of the advertising content, including the target audience, advertising type, and content form, compare with the interest points of multiple target user groups, analyze the matching situation between the advertising content and each user group, and obtain advertising target user group data; S402: Based on the data of the target user group for the advertisement, identify the active intervals of the target user group on each platform, and in combination with the placement cost, calculate the priority scores for multiple advertisement placement time periods to obtain the analysis result of the placement time periods; S403: According to the analysis result of the placement time periods, consider the platform adaptability, the user active time periods, and the budget cost, calculate and adjust the budget allocation ratios for multiple platforms, and generate the advertisement budget allocation result.

[0011] As a further solution of the present invention, the specific formula for calculating the priority scores for multiple advertisement placement time periods is: ; Calculate the priority scores; wherein, is the priority score for each advertisement placement time period , is the activity of the target user group in the time period , is the placement cost for this time period, is the total number of advertisement placement time periods, is the highest activity among all time periods, is the lowest placement cost among all time periods, is the index of the placement time period.

[0012] As a further solution of the present invention, the steps of using the advertisement budget allocation result to calculate and predict the advertisement placement effect by comparing and analyzing the changes in user behavior before and after the advertisement display and generating the placement effect evaluation information are specifically as follows: S501: Use the advertisement budget allocation result to obtain the behavior data of users before and after the advertisement display, including the number of views, click-through rate, and stay duration, analyze the changes in user behavior before and after the advertisement placement, calculate the activity change rates of users on multiple platforms before and after the advertisement placement, and obtain the user behavior change data; S502: Based on the user behavior change data, calculate the user conversion rates and engagement levels of multiple platforms by evaluating the differences in user behavior on multiple platforms before and after the advertisement placement to obtain the behavior difference data; S503: According to the behavior difference data, calculate and predict the advertisement placement effect, and adjust the user group, time period, and placement platform of the advertisement placement to generate the placement effect evaluation information.

[0013] As a further solution of the present invention, the specific formula for calculating and predicting the advertisement placement effect is: ; Calculate the advertisement placement effect; wherein, is the platform The advertising delivery effect For the platform During the time period The change in conversion rate For the platform During the time period The change in engagement For the platform During the time period The advertising cost Is the weight of the conversion rate Is the weight of the engagement Is the total number of time periods for advertising delivery Is the index of the advertising delivery platform Is the index of the advertising delivery time period

[0014] On the other hand, a network advertising promotion system based on the Internet is provided. This system is applied to a network advertising promotion method based on the Internet. The system includes: The behavior data analysis module obtains user behavior data, calculates the activity of each user in real time, identifies the user's interest points, classifies users based on the behavior data, and updates user tags to generate a user tag data set; The user group analysis module, based on the user tag data set, identifies the user's behavior patterns, analyzes the active time periods of multiple user groups, and generates user active time period information; The fitness evaluation module, based on the user active time period information, analyzes the interaction data of users on multiple platforms, calculates the fitness between the platform and the user, and generates an advertising platform fitness value; The allocation ratio calculation module, based on the advertising platform fitness value, analyzes the advertising content, combines the user fitness of the platform, the active time period of the target user group, and the advertising delivery cost, calculates the budget ratio, and generates an advertising budget allocation result; The advertising effect analysis module, based on the advertising budget allocation result, compares the user behavior changes before and after the advertising display, calculates the advertising delivery effect, and generates a delivery effect evaluation information.

[0015] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include: By identifying the user's interest points, updating user tags in real time, ensuring that the personalized recommendation of the advertisement conforms to the user's real-time behavior, analyzing and predicting the user's active time period, avoiding resource waste caused by fixed-time period delivery, dynamically adjusting the budget allocation according to the fitness between the user's behavior and the platform, improving the efficiency of advertising delivery, comparing the user behavior changes before and after the advertising display, accurately evaluating the advertising delivery effect, and providing data support for the adjustment of the advertising strategy, optimizing the advertising delivery effect and resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic diagram of the working process of the present invention; Figure 2 It is a detailed flowchart of S1 of the present invention; Figure 3 It is a detailed flowchart of S2 of the present invention; Figure 4 It is a detailed flowchart of S3 of the present invention; Figure 5 It is a detailed flowchart of S4 of the present invention; Figure 6 It is a detailed flowchart of S5 of the present invention; Figure 7 It is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following will describe the technical solutions in the present invention with reference to the drawings.

[0019] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Exactly, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0020] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when not emphasizing their differences, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when not emphasizing their differences, the meanings they express are the same.

[0021] In the embodiments of the present invention, sometimes subscripts such as W 1 may be written in a non-subscript form such as W1. When not emphasizing their differences, the meanings they express are the same.

[0022] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0023] Please refer to Figure 1 , the present invention provides a technical solution, a method for promoting network advertisements based on the Internet, including the following steps: S1: Obtain user behavior data. By analyzing browsing trajectories, stay durations, click frequencies, and interaction behaviors, calculate the activity of users in real time, identify the interest points of users, update user tags in real time and classify user groups, and generate a user tag data set; S2: Invoke the user tag data set. By analyzing the activity of users in multiple time periods, identify the behavior patterns of users, analyze the active time periods of multiple user groups, and generate user active time period information; S3: Invoke the user active time period information. By analyzing the interaction data of users on multiple platforms, evaluate the attractiveness of multiple platforms to user groups, calculate the fitness between the platform and users, and generate an advertisement platform fitness value; S4: Utilize the advertisement platform fitness value, analyze the advertisement content, identify the target user group, combine the user fitness of the platform, the active time period of the target user group, and the investment cost, calculate and adjust the budget allocation ratio, and generate an advertisement budget allocation result; S5: Utilize the advertisement budget allocation result. By comparing and analyzing the changes in user behavior before and after the advertisement display, calculate and predict the advertisement placement effect, and generate placement effect evaluation information.

[0024] The user tag data set includes user interest tags, user behavior patterns, and user activity information. The user active time period information includes the activity in multiple time periods, user behavior patterns, and the active time periods of multiple user groups. The advertisement platform fitness value includes platform attractiveness scores, platform conversion rates, and platform interaction frequencies. The advertisement budget allocation result includes advertisement placement time periods, platform placement priorities, and advertisement placement user groups. The placement effect evaluation information includes user conversion rates, advertisement interaction degrees, and investment return rates.

[0025] Please refer to Figure 2 , the steps of obtaining user behavior data, by analyzing browsing trajectories, stay durations, click frequencies, and interaction behaviors, calculating the activity of users in real time, identifying the interest points of users, updating user tags in real time and classifying user groups, and generating a user tag data set are specifically as follows: S101: Obtain user behavior data. Utilize the browsing trajectories, stay durations, click frequencies, and interaction behavior data of users to calculate the activity of each user in real time, and obtain user activity data; First, the system needs to collect the browsing behavior data of each user on the page, including the duration of stay, the number of clicks, and other interaction data (such as comments, likes, shares) when the user visits each page. In specific operations, the duration of stay is calculated by recording the time the user stays on the page. Usually, a threshold is set. For example, when the user stays on the page for more than 30 seconds, it is considered that the duration of stay on this page makes a greater contribution to the activity. The number of clicks counts each click behavior of the user on the page, usually including interactions such as clicking on page links, buttons, etc. Interaction behaviors (such as comments, likes) are also part of the activity. Usually, each interaction is counted as one active behavior. To obtain the total activity score, different weight coefficients need to be assigned to each behavior. For example, the weight of the duration of stay may be set to 0.3, the weight of the click frequency is 0.5, and the weight of the interaction behavior is 0.2. By multiplying the data of each behavior by the corresponding weight and summing them up, the activity score of each user is obtained. The activity calculation formula is as follows: ; where, is the activity score, is the duration of stay of the user on the page, is the number of clicks of the user on the page, is the number of interaction behaviors of the user on the page, are the weight coefficients of the duration of stay, click frequency, and interaction behavior respectively.

[0026] Suppose the user stays on page A for 60 seconds, clicks 5 times, makes 1 comment and 2 likes, and the weight coefficients are 0.3, 0.5, 0.2 respectively. Then the activity score of this user on page A is: ; This score represents the activity of this user on page A.

[0027] S102: Based on the user activity data, by comparing the activities of the user on multiple pages, identify the interest bias of each user and obtain the interest point recognition result; First, by comparing the activity scores of the user on multiple pages, infer the user's interests in different pages. If the user's activity is higher on some pages and lower on other pages, then it is determined that the user has a stronger interest in the former. For example, suppose the user's activity on page A is 70 and on page B is 30. Then it is inferred that the user is more interested in the content of page A. To further accurately identify the interest, set an interest threshold. For example, if the activity score of a certain page is greater than 50, it is considered that this page has a strong attraction to the user. According to this standard, by comparing the activity scores on multiple pages, the interest bias of the user is obtained. The interest bias calculation formula is as follows: ; Among them, is the interest preference ratio of the user on Page 1, is the activity score of the user on Page 1, is the activity score of the user on Page 2.

[0028] Assume that the activity of the user on Page 1 is 70 and the activity on Page 2 is 30, calculate the interest preference of this user for Page A: ; This result indicates that the interest preference degree of this user for Page 1 is 70%.

[0029] S103: According to the interest point recognition result, calculate and update the interest label weight of each user in real time, classify the users into multiple user groups, and generate a user label data set; During the operation process, first calculate the weight of each interest label of the user according to the activity of the user on different pages. For example, assume that user A has a high activity on the sports page and a low activity on the entertainment page. Then, the weight of the "sports" label is high, and the weight of the "entertainment" label is low. This weight is obtained by calculating the proportion of the user's activity on each page. Specifically, calculate the interest label weight through the following formula: ; Among them, is the weight of the "sports" interest label, is the activity score of the user on the sports page, is the activity score of the user on the entertainment page.

[0030] Assume that the activity score of the user on the sports page is 70 and the activity score on the entertainment page is 40. Then, the weight of the "sports" label is: ; At this time, the weight of the "sports" interest label is 0.636, indicating that this user has a strong interest in sports content. Based on this weight, user A is classified into the "sports enthusiast" group.

[0031] Please refer to Figure 3 , call the user label data set, and by analyzing the activity of the user in multiple time periods, identify the behavior pattern of the user, and analyze the active time periods of multiple user groups. The steps to generate the user active time period information are specifically as follows: S201: Call the user label data set, extract the behavior characteristics of the user by analyzing the activity data of the user in multiple time periods, and obtain the user behavior characteristic data; First, the system needs to obtain the activity data of the user over multiple time periods. Usually, the activity data is obtained based on the user's behavior activities at different times (such as browsing time, click times, interaction behaviors, etc.). The system needs to collect data for each time period of the user and summarize these data. Then, the system will analyze these data, especially extracting the behavior data that can reflect the user's characteristics. For example, a certain user has a longer stay time in the morning time period, while has more click behaviors in the evening time period. When analyzing, it is necessary to calculate the activity score for each time period, and by comparing the activity changes in different time periods, extract the user's behavior characteristics. The extraction formula for the behavior characteristic data is as follows: ; where, is the user behavior characteristic score, is the activity score of the user in time period , is the total number of time periods.

[0032] Suppose the activity scores of the user in the three time periods of morning, afternoon, and evening are 50, 70, and 90 respectively, then the user's behavior characteristic score is: ; This score represents the average activity of the user and serves as the basis for subsequent behavior pattern analysis.

[0033] S202: Based on the user behavior characteristic data, identify the user's behavior pattern, predict the user's behavior trend and activity pattern over multiple time periods, and obtain the user behavior pattern data; First, by analyzing the behavior data of each user over multiple time periods, identify the user's behavior pattern. For example, a certain user may mainly show browsing behavior in the morning time period, and is more inclined to perform interaction behaviors (such as liking, commenting, etc.) in the afternoon and evening. The system needs to identify the user's behavior pattern according to the user's behavior performance at different times. For example, by comparing the activity characteristics of the user in different time periods, predict the user's active trend in some future time periods, such as whether the user will continue to browse in the morning, or whether the user will interact more in the evening. In order to predict these behavior patterns, the system needs to compare the activity changes in multiple time periods and adjust the user's behavior prediction based on these changes. For example, by calculating the change trend of the user's behavior characteristics in each time period and predicting the future trend, the system predicts the user's behavior pattern. The behavior trend prediction formula is as follows: ; where, is the behavior trend score, is the activity score of the user in time period , The activity score of the user during time period, is the total number of time periods.

[0034] Assume that the activity scores of the user in the three time periods of morning, afternoon, and evening are 50, 70, and 90 respectively. Then the activity change in each time period is as follows: ; At this time, the predicted behavior trend score is 20, indicating that the user's activity trend is upward.

[0035] S203: According to the user behavior pattern data, by analyzing the behavior patterns of multiple users, identify the active time periods of multiple user groups, and generate user active time period information; First of all, the system needs to analyze the behavior patterns of multiple users to identify which time periods are the active time periods of multiple users. For example, by summarizing the activity data of different users in different time periods, the system calculates which time periods have higher activity, and based on this information, identifies the active time periods of user groups. In order to identify the active time periods of multiple user groups, it is necessary to aggregate the activity data of all users in each time period. By comparing the activity distributions in each time period, the system obtains the active time periods of multiple groups. For example, if the activity of multiple user groups is relatively high during the period from 7 pm to 9 pm, then this period is considered as the common active time period of multiple user groups. The formula for generating active time period information is as follows: ; Among them, is the average active time period score of the user group, is the activity score of the th user in this time period, is the total number of users.

[0036] Suppose there are three users, and their activity scores in a certain time period are 60, 80, and 90 respectively. The generated active time period score of the user group is: ; This score represents the average activity level of multiple user groups in this time period, and identifies the most representative active time period.

[0037] Please refer to Figure 4 , call the user active time period information, and by analyzing the interaction data of the user on multiple platforms, evaluate the attractiveness of multiple platforms to the user group, calculate the compatibility between the platform and the user, and the specific steps for generating the advertising platform compatibility value are as follows: S301: Call the user active time period information, obtain the interaction data of the user on multiple platforms, calculate the interaction intensity of the user on multiple platforms, and generate platform-user interaction intensity data; First, by calling the user's active period information, the system can identify the active time periods of the user on each platform. For example, the user may have different interaction frequencies on each platform in the morning, afternoon, or evening. The system will collect and summarize the interaction data of the user on each platform, such as likes, comments, shares, etc., based on the user's behavior records during these time periods. These behaviors are further converted into interaction intensity values, which are obtained by calculating the ratio of the number of behaviors in each time period to the total duration of the platform. Generally, the time periods with higher interaction intensity show more frequent user behaviors. For example, if the user interacts 20 times in the morning on Platform A and 15 times in the morning on Platform B, then the system will calculate the interaction intensity of the two platforms during this time period and obtain the interaction intensity data of Platform A and Platform B. The calculation formula for the interaction intensity is as follows: ; Among them, is the interaction intensity of platform , is the number of behaviors of the user during the time period on platform , is the total number of time periods.

[0038] Suppose the number of interactions of the user on Platforms A and B in the three time periods of morning, afternoon, and evening are as follows: Platform A: 20 times in the morning, 10 times in the afternoon, and 15 times in the evening; Platform B: 15 times in the morning, 5 times in the afternoon, and 10 times in the evening.

[0039] Calculate the interaction intensity of Platform A: ; Calculate the interaction intensity of Platform B: ; Finally, the interaction intensity data of Platforms A and B are 15 and 10 respectively, reflecting the user interaction levels of each platform.

[0040] S302: Based on the platform user interaction intensity data, analyze and calculate the attractiveness of multiple platforms to each user group, and generate platform attractiveness scores; First, the system will evaluate the attractiveness of each platform to the user group according to the interaction intensity data of each user group. For example, if a certain user group has a high interaction frequency on Platform A and a low interaction frequency on Platform B, it is speculated that Platform A has a stronger attraction to this user group. To calculate the attractiveness of the platform, the system will evaluate by combining the interaction intensity of the user on each platform through methods such as weighted average. The calculation formula for platform attractiveness is as follows: ; Among them, For the platform 's attraction score, is the th user's interaction intensity on the platform , and is the total number of the user group.

[0041] Suppose there are three users with interaction intensities as follows: For platform A, user 1 is 20, user 2 is 10, and user 3 is 15; for platform B, user 1 is 15, user 2 is 5, and user 3 is 10. Then the attraction score of platform A is: ; while the attraction score of platform B is: ; This indicates that the attraction of platform A is higher than that of platform B.

[0042] S303: According to the platform attraction score, combined with the matching degree between the user's active time period and the platform's audience, evaluate the suitability of the platform for the target user group, calculate the suitability between the platform and the user, and generate the advertising platform suitability value; First, the system will match the user's active time period with the platform's audience group. For example, if the main active time period of a certain platform coincides with the user's active time period, then the suitability of this platform for this user group is relatively high. In addition, the platform attraction score will also affect the suitability. The platform with a higher attraction score has a higher suitability for the target group. The calculation of the suitability value combines the platform attraction score and the matching degree of the user's active time period, and obtains the final suitability value through methods such as weighted average. The formula for calculating the suitability is as follows: ; Among them, is the suitability between the platform and the user group, is the attraction score of the platform , is the matching degree between the platform and the user's active time period.

[0043] Suppose the attraction score of platform A is 15 and the matching degree between the platform and the user's active time period is 0.8. Then the suitability between platform A and this user group is: ; If the attraction score of platform B is 10 and the matching degree between the platform and the user's active time period is 0.6, then the suitability between platform B and this user group is: ; The result shows that the suitability between platform A and this user group is relatively high, indicating that platform A is more suitable for this group.

[0044] Please refer to Figure 5 , the steps of analyzing the advertisement content, identifying the target user group, combining the user adaptability of the platform, the active time period of the target user group and the placement cost, calculating and adjusting the budget allocation ratio, and generating the advertisement budget allocation result by using the advertisement platform adaptability value are specifically as follows: S401: Invoke the advertisement platform adaptability value, extract the key features of the advertisement content, including the target audience, advertisement type, and content form, compare through the interest points of multiple target user groups, analyze the matching situation between the advertisement content and each user group, and obtain the advertisement target user group data; First, the system matches the platform with the active time periods of different user groups by invoking the advertisement platform adaptability value. Then, according to the key features of the advertisement, such as the target audience, advertisement type, content form, etc., the system analyzes each user group. The features of the advertisement content include the advertisement type (such as product advertisement, brand advertisement), the advertisement content form (such as picture, video, text, etc.), and the target audience of the advertisement (such as age group, gender, interest points, etc.). Through the analysis of these features and combining the interest points of each user group, the system further analyzes the matching situation between the advertisement content and the user group. For example, if the content of an advertisement is about the promotion of a sports brand and the target audience is men aged 18 - 30, and the interest points of the user group mainly focus on sports content, then the matching degree of this advertisement with this user group is relatively high. By comparing the interest points of multiple target user groups, the system obtains the advertisement target user group data. The specific matching analysis formula is as follows: ; where is the matching degree between the advertisement and the user group, is the interest point matching degree between the th user group and the advertisement, is the total number of user groups.

[0045] Suppose the target audience of the advertisement is men aged 18 - 30, the advertisement content is sports goods, and the interest points of user groups A and B are sports and entertainment respectively. Suppose the matching degree between the interest points of user group A and the advertisement is 0.8, and the matching degree of user group B is 0.3. Then the matching degree of the advertisement with these two groups is: ; This means that the matching degree of the advertisement with these two user groups is 55%.

[0046] S402: Based on the advertisement target user group data, identify the active intervals of the target user group on each platform, combine the placement cost, calculate the priority scores of multiple advertisement placement time periods, and obtain the placement time period analysis result; The specific formula for calculating the priority scores of multiple advertising placement periods is as follows: ; Calculate the priority score; where is the priority score for each advertising placement period , is the activity level of the target user group in period , is the placement cost for this period, is the total number of advertising placement periods, is the highest activity level among all periods, is the lowest placement cost among all periods, is the index of the placement period.

[0047] Formula: ; Detailed explanation of the formula and the derivation process of formula calculation: The formula is used to calculate the priority scores of multiple advertising placement periods, helping to determine the most suitable period for advertising display and optimizing budget allocation.

[0048] Meaning and setting values of parameters: is the priority score for the advertising placement period , reflecting the importance of this period among all advertising placement periods; is the activity level of the target user group in period , reflecting the activity level of the target group during this period; is the placement cost for this period, reflecting the budget investment of the advertisement in this period; is the maximum activity level among all periods, representing the highest activity level of users in a certain period; is the lowest placement cost among all periods, representing the lowest value of the advertisement budget among all periods; is the total number of advertising placement periods.

[0049] Suppose the activity levels and placement costs of the user group in 5 advertising placement periods ( ) are as follows: For period 1: , , for period 2: , , for period 3: , , Time period 4: , , Time period 5: , , that is , ; Substitute the parameters into the formula for calculation: ; ; ; It shows that the priority score of the advertisement in time period 1 is 0.221, which means that among all advertisement placement time periods, the advertisement in this time period has a relatively low priority. Although it has a high activity level, due to the high placement cost and the more prominent activity levels in other time periods, the priority is low. The priority score is used to adjust the time period selection in the advertisement display strategy.

[0050] S403: According to the analysis result of the placement time period, considering the platform adaptability, the user active time period, and the budget cost, calculate and adjust the budget allocation ratio of multiple platforms to generate the advertisement budget allocation result; First of all, the system adjusts the budget allocation ratio of the advertisement according to the analysis result of the placement time period, combined with the platform adaptability, the user active time period, and the budget cost. The platform adaptability and the user active time period determine the placement priority of the advertisement, while the budget cost restricts the allocation of the advertisement budget. Based on these factors, the system calculates the budget allocation ratio of each platform and adjusts the advertisement budget of each platform. The calculation formula for the budget allocation ratio is as follows: ; Among them, is the budget allocation ratio of platform , is the placement time period priority score of platform , is the adaptability of platform , is the total number of platforms.

[0051] Suppose the priority score of platform A is 0.636, the adaptability is 0.8, the priority score of platform B is 0.364, the adaptability is 0.6, and the total budget is 10000. Then the budget allocation ratio of platform A is: ; Therefore, the budget allocation ratio of platform A is 70%, and the budget allocation ratio of platform B is 30%.

[0052] Please refer to Figure 6, using the advertising budget allocation result, by comparing and analyzing the changes in user behavior before and after the advertisement display, calculating and predicting the advertising delivery effect, the steps of generating the delivery effect evaluation information are specifically as follows: S501: Using the advertising budget allocation result, obtain the user behavior data before and after the advertisement display, including the number of views, click-through rate, and dwell time, analyze the changes in user behavior before and after the advertisement delivery, calculate the change rate of user activity on multiple platforms before and after the advertisement delivery, and obtain the user behavior change data; First, the system determines the advertising delivery period according to the advertising budget allocation result and compares it with the user behavior data before and after this period. Before and after the advertisement display, the system needs to collect relevant data on multiple platforms, mainly including the number of views, click-through rate, and dwell time, etc. For each user group, the system separately counts these behavior data of them on each platform before and after the advertisement display. For example, before the advertisement display, a certain user's number of views on platform A is 100, the click-through rate is 5%, and the dwell time is 30 seconds; after the advertisement display, the number of views on platform A increases to 120, the click-through rate rises to 6%, and the dwell time increases to 35 seconds. The system will calculate the change rate of user activity on multiple platforms through these data changes. The specific calculation formula is as follows: ; Among them, is the change rate of user activity on platform , is the activity after the advertisement display, is the activity before the advertisement display.

[0053] Suppose the number of views on platform A before the advertisement display is 100 and the number of views after the advertisement display is 120, calculate the change rate of activity: ; This means that after the advertisement delivery, the number of user views on platform A has increased by 20%.

[0054] S502: Based on the user behavior change data, by evaluating the differences in user behavior on multiple platforms before and after the advertisement delivery, calculate the user conversion rate and engagement on multiple platforms, and obtain the behavior difference data; First, the system evaluates the user conversion rate and engagement on each platform according to the user behavior change data before and after the advertisement delivery. The conversion rate is obtained by calculating the changes in the actual purchase or other target behaviors of users before and after the advertisement display, and the engagement is measured by the behaviors of users such as clicks and interactions. The system will compare these changes on multiple platforms to calculate the conversion rate and engagement. The calculation formulas for the conversion rate and engagement are as follows: ; Among them, is the platform The conversion rate, The conversion behavior after the ad is displayed. Refers to the conversion behavior before the ad is displayed.

[0055] ; in, For the platform The participation rate, The interactive behavior after the ad is displayed. It refers to the interactive behavior before the ad is displayed.

[0056] Assuming that the number of conversions on platform A before the ad was 50 and the number of conversions after the ad was 60, the conversion rate is: ; If on platform A, the number of interactions before the ad was 200 and the number of interactions after the ad was 220, then the engagement is: ; Thus, Platform A has a conversion rate of 20% and an engagement rate of 10%.

[0057] S503: Calculate and predict the advertising effect based on the behavior difference data, adjust the user group, time period, and delivery platform for advertising delivery, and generate delivery effect evaluation information; The specific formula for calculating and predicting the effectiveness of advertising is: ; Calculate the effectiveness of advertising; in, For the platform The advertising effect, For the platform In the period The change in conversion rate, For the platform In the period Changes in participation, For the platform In the period advertising costs, is the weight of conversion rate, is the weight of participation, is the total number of time periods during which the advertisement is served. The index of the advertising platform. The index of the time period during which the ad is served.

[0058] formula: ; Detailed explanation of the formula and the process of formula calculation and derivation: This formula is used to calculate the advertising placement effect on the platform, and the obtained result is used to evaluate the overall performance of the advertising placement on each platform; the calculation of the advertising placement effect takes into account the conversion rate change, engagement change, and advertising cost, and combines these factors to obtain a comprehensive effect indicator; Parameter meaning and set values: : The advertising placement effect on the platform, which reflects the overall effect of the advertising placement on this platform; : The platform The conversion rate change during the time period : The platform The engagement change during the time period : The weight coefficient of the conversion rate, which reflects the importance of the conversion rate in the evaluation of advertising effect; : The weight coefficient of the engagement, indicating the importance of the user's interactive engagement in the evaluation of advertising effect; : The platform The advertising cost during the time period : The total number of time periods for advertising placement, which reflects the number of different time periods involved in the advertising placement; Assume that the advertising placement involves two time periods. The conversion rate change of platform A is 0.2, the engagement change is 0.1, the advertising cost is $500, the weight coefficient is 0.7, is 0.3, and the total number of time periods for advertising placement is 2; Substitute the parameters into the formula for calculation: Calculate the advertising placement effect of platform A: ; ; ;

[0059] The result 249.915 indicates the advertising placement effect score of platform A during advertising placement. Since the changes in engagement and conversion rate before and after advertising placement are small and the advertising cost is high, the advertising effect score is low, indicating that the advertising placement cost of platform A is too high, resulting in a decline in its overall effect evaluation, and it is necessary to optimize the advertising placement strategy to improve the advertising effect.

[0059] Please refer to Figure 7 , an Internet-based network advertising promotion system. The Internet-based network advertising promotion system is used to execute the above-mentioned Internet-based network advertising promotion method. The system includes: The behavior data analysis module obtains user behavior data, calculates the activity of each user in real time, identifies the user's interest points, classifies users based on the behavior data, and updates the user tags to generate a user tag dataset; The user group analysis module identifies the behavior patterns of users based on the user tag dataset, analyzes the active time periods of multiple user groups, and generates user active period information; The adaptation degree evaluation module analyzes the interaction data of users on multiple platforms based on the user active period information, calculates the adaptation degree between the platform and the user, and generates an advertisement platform adaptation degree value; The allocation ratio calculation module analyzes the advertisement content based on the advertisement platform adaptation degree value, combines the user adaptation degree of the platform, the active time period of the target user group, and the advertisement placement cost, calculates the budget ratio, and generates an advertisement budget allocation result; The advertisement effect analysis module compares the changes in user behavior before and after the advertisement display based on the advertisement budget allocation result, calculates the placement effect of the advertisement, and generates placement effect evaluation information.

[0060] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or data center that includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0061] It should be understood that the term "and / or" in this text is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this text generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship. The specific meaning can be understood by referring to the context before and after.

[0062] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following items" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0063] It should be understood that in various embodiments of the present invention, the magnitudes of the serial numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0064] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0065] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0066] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other forms.

[0067] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0068] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, can exist separately physically for each unit, or two or more units can be integrated in one unit.

[0069] If the described function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs and other various media that can store program codes.

[0070] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A network advertising promotion method based on the Internet, characterized in that: The method comprises: S1: Obtain user behavior data, calculate user activity in real time by analyzing browsing trajectories, dwell time, click frequency, and interactive behavior, identify user interests, update user tags in real time, classify user groups, and generate user tag data sets; S2: calling the user tag data set, analyzing the user's activity in multiple time periods, identifying the user's behavior pattern, analyzing the active time periods of multiple user groups, and generating user active time period information; S3: calling the user active period information, analyzing the user's interaction data on multiple platforms, evaluating the attractiveness of multiple platforms to user groups, calculating the compatibility between the platform and the user, and generating an advertising platform compatibility value; S4: Analyze the advertisement content and identify the target user group by using the advertisement platform adaptability value, calculate and adjust the budget allocation ratio by combining the user adaptability of the platform, the active time period of the target user group and the delivery cost, and generate an advertisement budget allocation result; S5: Using the advertising budget allocation result, by comparing and analyzing the changes in user behavior before and after the advertisement display, the advertising delivery effect is calculated and predicted, and delivery effect evaluation information is generated.

2. The Internet-based network advertising promotion method according to claim 1, characterized in that: The user tag data set includes user interest tags, user behavior patterns, and user activity information; the user active period information includes the activity of multiple time periods, user behavior patterns, and active time periods of multiple user groups; the advertising platform adaptability value includes the platform attractiveness score, platform conversion rate, and platform interaction frequency; the advertising budget allocation result includes the advertising delivery period, platform delivery priority, and advertising delivery user group; the delivery effect evaluation information includes user conversion rate, advertising interactivity, and delivery return rate.

3. The Internet-based network advertising promotion method according to claim 1, characterized in that: Obtain user behavior data, calculate user activity in real time by analyzing browsing tracks, dwell time, click frequency, and interactive behavior, identify user interests, update user tags in real time, and classify user groups. The specific steps for generating a user tag data set are as follows: S101: Obtain user behavior data, calculate the activity of each user in real time using the user's browsing trajectory, stay time, click frequency and interactive behavior data, and obtain user activity data; S102: Based on the user activity data, by comparing the user's activity on multiple pages, identifying each user's interest preference, and obtaining an interest point identification result; S103: According to the interest point recognition result, the interest tag weight of each user is calculated and updated in real time, and the users are classified into multiple user groups to generate a user tag data set.

4. The Internet-based network advertising promotion method according to claim 1, characterized in that: The steps of calling the user tag data set, analyzing the user's activity in multiple time periods, identifying the user's behavior pattern, analyzing the active time periods of multiple user groups, and generating the user's active time period information are as follows: S201: calling the user tag data set, extracting the user's behavior characteristics by analyzing the user's activity data in multiple time periods, and obtaining user behavior characteristic data; S202: Based on the user behavior feature data, identify the user's behavior pattern, predict the user's behavior trend and activity pattern in multiple time periods, and obtain user behavior pattern data; S203: According to the user behavior pattern data, by analyzing the behavior patterns of multiple users, active time periods of multiple user groups are identified, and user active time period information is generated.

5. The Internet-based network advertising promotion method according to claim 1, characterized in that: The steps of calling the user active time period information, analyzing the user's interaction data on multiple platforms, evaluating the attractiveness of multiple platforms to user groups, calculating the compatibility between the platform and the user, and generating the advertising platform compatibility value are as follows: S301: Calling the user active period information, obtaining the user's interaction data on multiple platforms, calculating the user's interaction intensity on multiple platforms, and generating platform user interaction intensity data; S302: Analyze and calculate the attractiveness of multiple platforms to each user group based on the platform user interaction intensity data, and generate a platform attractiveness score; S303: Based on the platform attractiveness score, combined with the user's active time period and the platform's audience matching, the platform's adaptability to the target user group is evaluated, the adaptability between the platform and the user is calculated, and the advertising platform adaptability value is generated.

6. The Internet-based network advertising promotion method according to claim 1, characterized in that: The steps of using the advertising platform adaptability value to analyze the advertising content, identify the target user group, and calculate and adjust the budget allocation ratio in combination with the platform's user adaptability, the active time period of the target user group, and the delivery cost to generate the advertising budget allocation result are as follows: S401: calling the advertising platform adaptability value, extracting key features of the advertising content, including target audience, advertising type, and content form, comparing the interest points of multiple target user groups, analyzing the matching between the advertising content and each user group, and obtaining advertising target user group data; S402: Based on the advertisement target user group data, identify the active interval of the target user group on each platform, calculate the priority scores of multiple advertisement delivery periods in combination with the delivery cost, and obtain delivery period analysis results; S403: According to the analysis result of the delivery period, the budget allocation ratios of multiple platforms are calculated and adjusted in consideration of platform adaptability, user active time period and budget cost, to generate an advertising budget allocation result.

7. The Internet-based network advertising promotion method according to claim 6, characterized in that: The specific formula for calculating the priority scores of multiple advertisement delivery periods is: ； Calculate priority scores; in, For each ad delivery period The priority score, For the target user group during the period activity, is the delivery cost for this period, is the total number of ad delivery periods. The highest activity level among all time periods. is the lowest delivery cost in all time periods. The index of the delivery period.

8. The Internet-based network advertising promotion method according to claim 1, characterized in that: The steps of calculating and predicting the advertising effect by using the advertising budget allocation result and comparing and analyzing the changes in user behavior before and after the advertising is displayed, and generating the advertising effect evaluation information are as follows: S501: Using the advertising budget allocation result, obtain the user behavior data before and after the advertisement is displayed, including the page views, click-through rate, and dwell time, analyze the user behavior changes before and after the advertisement is released, calculate the user activity change rate on multiple platforms before and after the advertisement is released, and obtain the user behavior change data; S502: Based on the user behavior change data, by evaluating the differences in user behaviors of multiple platforms before and after advertisement delivery, calculating user conversion rates and engagement of multiple platforms, and obtaining behavior difference data; S503: Calculate and predict the advertising delivery effect based on the behavior difference data, adjust the user group, time period, and delivery platform for advertising delivery, and generate delivery effect evaluation information.

9. The Internet-based network advertising promotion method according to claim 8, characterized in that: The specific formula for calculating and predicting the advertising delivery effect is: ； Calculate the effectiveness of advertising; in, For the platform The advertising effect, For the platform In the period The change in conversion rate, For the platform In the period Changes in participation, For the platform In the period advertising costs, is the weight of conversion rate, is the weight of participation, is the total number of time periods during which the advertisement is served. The index of the advertising platform. The index of the time period during which the ad is served.

10. An Internet-based network advertising promotion system, characterized in that: According to any one of claims 1 to 9, the Internet-based network advertising promotion method comprises: The behavior data analysis module obtains user behavior data, calculates the activity of each user in real time, identifies the user's points of interest, classifies users based on the behavior data, updates user tags, and generates a user tag data set; The user group analysis module identifies the user's behavior pattern based on the user tag data set, analyzes the active time periods of multiple user groups, and generates user active time period information; The adaptability evaluation module analyzes the user's interaction data on multiple platforms based on the user's active time period information, calculates the adaptability between the platform and the user, and generates an advertising platform adaptability value; The allocation ratio calculation module analyzes the advertisement content based on the advertisement platform adaptability value, calculates the budget ratio based on the platform user adaptability, the active time period of the target user group and the advertisement delivery cost, and generates an advertisement budget allocation result; The advertising effect analysis module compares the changes in user behavior before and after the advertisement display based on the advertisement budget allocation result, calculates the advertisement delivery effect, and generates delivery effect evaluation information.

Images