An advertisement management and distribution system and method based on the Internet of Things

Through an Internet of Things-based advertising management and distribution system, using market trends and consumer behavior data to generate creative advertising drafts, conduct compliance and audience analysis, and monitor advertising status in real time, solving the speed of advertising content updates and target audiences in the existing technology. Analyzing insufficient problems has enabled efficient personalization and precise delivery of advertisements.

CN118608209BActive Publication Date: 2024-12-03ZUNCHUANG TECH GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411047386.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-12-03
Estimated Expiration
2044-08-01

AI Technical Summary

Technical Problem

The existing advertising management and distribution systems cannot meet the rapid changes in the market in terms of personalization and update speed of advertising content, resulting in a decline in advertising effectiveness, and relying on manual review efficiency, which is susceptible to subjective factors, and the target audience analysis lacks dynamic and real-time. It is difficult to accurately capture changes in consumer behavior, resulting in insufficient accuracy and timeliness of advertising delivery.

Method used

Adopting an Internet of Things-based advertising management and distribution system, through the advertising content creation module, extract key data points from market trends, and generate creative advertising drafts based on consumer purchasing behaviors. The authenticity verification module uses text analysis tools and convolutional neural network to check compliance , The audience analysis module analyzes consumer behavior patterns, the advertising positioning module determines the delivery platform and time, the publishing execution module monitors the advertising status in real time, and the effect monitoring module collects user interaction data for optimization.

Benefits of technology

Realize highly personalized and dynamic updates of advertising content, improve advertising appeal and user engagement, ensure advertising compliance, enhance advertising targeting and delivery efficiency, and make the advertising delivery process more efficient and predictable through real-time monitoring and data analysis. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118608209B_ABST
    Figure CN118608209B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of electronic advertising technology, specifically to an Internet of Things-based advertising management and distribution system and method, wherein the system includes an advertising content creation module, an authenticity verification module, an audience analysis module, an advertising positioning module, a publishing execution module, and an effect monitoring module. In the present invention, by extracting key data points from market trends and combining with target consumer purchase behavior records, the advertising content is personalized and dynamically updated, accurately reflects consumer interests, improves attractiveness and participation, uses design software to draw a draft of the advertisement, combines historical cases for iterative modification, improves the quality of advertising creativity, uses text analysis tools and image source inspections to ensure content compliance, reduces legal risks, and improves brand reputation, conducts in-depth audience analysis to accurately select target groups, optimizes resource allocation, and evaluates advertising effects in real time through real-time monitoring and user interaction data analysis, providing data support for future strategies, making advertising delivery more efficient.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electronic advertisements, and in particular to an advertisement management and distribution system and method based on the Internet of Things. Background Art

[0002] The field of electronic advertising technology involves the creation, management, optimization and distribution of advertisements through digital and network technologies. The field uses the Internet, social media platforms, mobile devices and the Internet of Things to achieve efficient and accurate advertising target audience matching. Electronic advertising technology includes automated personalization of advertising content, the use of data analysis and machine learning to optimize advertising effects, and systems for real-time tracking and evaluation of advertising performance. The development of this field has promoted the growth of the advertising economy, while improving the return on investment (ROI) of advertising costs and providing consumers with more relevant and valuable advertising content.

[0003] Among them, the IoT-based advertising management and distribution system is a system that uses IoT technology to optimize and control the distribution of advertising content. The system achieves accurate positioning and timeliness of advertising by intelligently pushing advertising content to specific IoT devices (such as smart billboards, mobile phones, smart home devices, etc.). Uses include analyzing data from IoT devices to better understand consumer behavior and preferences, thereby making advertising more accurate and improving the attractiveness and effectiveness of advertising. Such systems are particularly suitable for scenarios that require highly personalized and dynamic advertising content updates, such as retail, entertainment, and transportation industries.

[0004] Although the existing advertising management and distribution systems have made progress in automation and data analysis, they still face some key deficiencies in actual operation. The existing technology cannot meet the rapid changes in the market in terms of personalization and update speed of advertising content. The long innovation cycle of advertising content and the limited ability to respond to market dynamics have led to a decline in advertising effectiveness. The existing system mainly relies on manual review for authenticity verification, which is inefficient and easily affected by subjective factors, increasing the risk of misleading advertising content. The existing technology uses static market research data for target audience analysis, which lacks dynamics and real-time, and it is difficult to accurately capture the latest changes in consumer behavior, which limits the accuracy and timeliness of advertising delivery. The lack of automation in advertising positioning and publishing leads to waste of resources and low delivery efficiency. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an advertising management and distribution system and method based on the Internet of Things.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: An advertising management and distribution system based on the Internet of Things comprises:

[0007] The advertising content creation module extracts key data points from market trends, combines them with the purchase behavior records of target consumers, compares them with historical successful cases, makes iterative modifications, and generates a creative advertising draft;

[0008] The authenticity verification module uses text analysis tools to perform semantic analysis based on the creative advertisement draft, identifies misleading and false statements, checks the image source to determine the copyright ownership, and obtains the advertisement compliance review result;

[0009] The audience analysis module analyzes the behavior patterns and preference settings in the consumer database according to the advertising compliance review results, selects the age, region and purchasing power indicators of the target group, and constructs the target audience analysis results;

[0010] The advertisement positioning module uses the target audience analysis results to determine the advertisement delivery platform and optimal display time, sets delivery parameters including frequency and location, and obtains advertisement delivery strategy results;

[0011] The publishing execution module sets the timing task of advertising publishing according to the advertising delivery strategy results, adjusts the advertising display parameters of the IoT device, monitors the advertising delivery status and display frequency in real time, and establishes the advertising publishing execution results;

[0012] The effect monitoring module collects user interaction data from the advertising publishing execution results, analyzes the user interaction data, optimizes advertising distribution, and generates advertising effect monitoring results.

[0013] As a further solution of the present invention, the creative advertising draft includes creative concepts, content layout, and design style; the advertising compliance review results include text authenticity, image authorization, and compliance rating; the target audience analysis results include consumer behavior, interest classification, and reaction prediction; the advertising delivery strategy results include the selected platform, set time point, and frequency adjustment; the advertising release execution results include task scheduling, parameter adjustment, and monitoring implementation; and the advertising effect monitoring results include data collection, effect evaluation, and optimization measures.

[0014] As a further solution of the present invention, the advertisement content creation module includes:

[0015] The market analysis submodule identifies key trends based on market results and real-time data, uses statistical tools to quantify changes in consumer preferences, analyzes the development potential of emerging markets, and adjusts market segmentation strategies based on indicator results to generate market trend results;

[0016] The consumer behavior analysis submodule extracts key data points from the market trend results, analyzes consumer purchase history and behavior data, screens key behaviors including purchase frequency and price sensitivity, segments consumer groups, and adjusts advertising targeting based on behavior patterns to obtain purchase behavior analysis results;

[0017] The advertising design iteration submodule sets the advertising theme and core information according to the purchase behavior analysis results, uses design tools to make a preliminary draft of the advertisement, optimizes the visuals and copy based on preliminary feedback, compares historical successful cases and adjusts the content, and establishes a creative advertising draft.

[0018] As a further solution of the present invention, the authenticity verification module includes:

[0019] The semantic review submodule uses natural language processing technology to parse the words and phrases in the advertisement text based on the creative advertisement draft, identifies potential misleading and false claims according to the preset vocabulary, and performs semantic consistency scoring, analyzes the logical relationship between differentiated semantic elements, adjusts semantic parsing parameters and matches differentiated advertisement contexts, and generates advertisement authenticity evaluation results;

[0020] Based on the advertisement authenticity evaluation result, the copyright checking submodule collects the features of the image elements in the advertisement through an interface call with the global copyright database, matches them with the copyright information in the database, analyzes the image sources with high matching degree, adjusts the matching algorithm, and obtains the copyright ownership determination result;

[0021] The compliance review submodule determines the copyright ownership based on the results and applies the convolutional neural network algorithm to check whether the draft advertisement complies with the laws and regulations of the target market. By comparing the advertisement content with the regulatory requirements one by one, adjusting the regulatory matching parameters and covering the compliance check, the advertising compliance review results are obtained.

[0022] As a further solution of the present invention, the formula of the convolutional neural network algorithm is as follows:

[0023] ;

[0024] in, is the weight of the convolution kernel, For input advertising image or text data, is the bias, is the activation function, is the feature extraction result, is the normalization coefficient of the input data, is the dimension of the data, is the dimension weight coefficient, is the learning rate, is the error rate.

[0025] As a further solution of the present invention, the audience analysis module includes:

[0026] The behavior pattern analysis submodule uses transaction records and response data in the consumer database based on the advertising compliance review results, determines the repetitive pattern of purchase behavior through time series analysis, adjusts the data analysis frequency and sample size, and obtains the behavior pattern description;

[0027] The preference setting analysis submodule analyzes the consumer's purchase data based on the behavior pattern description, identifies key factors of consumer preference, including product type and price sensitivity, determines key preferences through comparative analysis, and adjusts classification criteria for key preferences to obtain preference mapping results;

[0028] The target group selection submodule uses the preference mapping results to identify consumer groups with similar purchasing power, geographic location and age, and optimizes the accuracy of the target group by adjusting the screening criteria and parameter settings to obtain the target audience analysis results.

[0029] As a further solution of the present invention, the advertisement positioning module includes:

[0030] The platform selection submodule analyzes the user coverage and interaction data of the advertising platform based on the target audience analysis results, evaluates the advertising response rate and user engagement on the platform, selects the advertising platform that matches the target audience characteristics, and generates a list of selected platforms;

[0031] The time optimization submodule uses the selected platform list to analyze the user active time data of multiple platforms, determine the time period when the target audience is online, adjust the time configuration of the advertisement display, and obtain the optimal display period;

[0032] The parameter setting submodule sets the frequency and location of advertisement delivery based on the optimal display period, the geographic distribution and behavior patterns of the target audience, adjusts parameters, optimizes coverage effects and avoids advertisement fatigue, and establishes advertisement delivery strategy results.

[0033] As a further solution of the present invention, the publishing execution module includes:

[0034] The scheduled task setting submodule initializes the scheduled advertisement release plan based on the advertising delivery strategy results, inputs the target market, expected release time and repetition frequency of the advertising campaign, optimizes the release plan according to the time zone of the differentiated market, adjusts the time point and frequency of task execution, and generates a scheduled task advertisement release plan;

[0035] The advertisement display adjustment submodule uses the time arrangement in the scheduled task advertisement publishing plan to set the advertisement display parameters for the connected IoT devices, including adjusting the display duration, optimizing the resolution, and setting the display frequency, and adjusts the parameters for differentiated types of advertisement content to obtain the display parameter setting results;

[0036] The status monitoring submodule adopts the display parameter setting results to set up a real-time monitoring mechanism for advertising display, and implements continuous tracking of the advertising delivery status, including monitoring the display frequency of advertisements and audience interaction. By adjusting the accuracy of data collection and the monitoring frequency, the advertising display strategy is adjusted and market feedback is responded to, thereby obtaining the advertising release execution results.

[0037] As a further solution of the present invention, the effect monitoring module includes:

[0038] The user interaction analysis submodule identifies and records the number of user clicks and viewing duration based on the data of the advertising publishing execution result, analyzes the data points to calculate the viewing completion rate and return visit rate of the advertisement, and obtains the advertising viewing analysis result;

[0039] The audience response evaluation submodule uses the advertisement viewing analysis results to aggregate the positive and negative feedback data of users, analyze the number of comments and likes left by users, quantify the popularity of the advertisement content and the feedback quality, and generate the audience feedback quantitative analysis results;

[0040] The advertising strategy adjustment submodule utilizes the audience feedback quantitative analysis results to review and adjust the advertising content, including modifying key information points and visual elements, adjusting the delivery time and frequency according to the analysis results, matching the target audience's behavior patterns, and establishing advertising effect monitoring results.

[0041] An Internet of Things-based advertising management and distribution method, the Internet of Things-based advertising management and distribution method is performed based on the Internet of Things-based advertising management and distribution system, and includes the following steps:

[0042] S1: Extract key data points from market trends, analyze data, determine the core message and theme of the advertisement, use design tools to adjust content parameters, optimize the visual and copy effects of the advertisement, and generate a draft advertisement;

[0043] S2: Use text analysis tools to analyze the language used in the draft advertisement, identify potential misleading statements, conduct image copyright checks, verify the legal right to use the images, and obtain the advertising review results;

[0044] S3: extracting consumer behavior data matching the advertising target from the consumer database through the advertising review results, analyzing the consumer behavior data to define the age, region and economic ability of the target group, and constructing audience analysis results;

[0045] S4: Using the audience analysis results, select a matching advertising delivery platform and optimal display time, adjust advertising parameters including display frequency and location, optimize advertising coverage and interaction, and form an advertising delivery strategy;

[0046] S5: According to the advertising delivery strategy, set the advertising display parameters of the IoT device, perform scheduled advertising and status monitoring, collect user interaction data in real time, analyze user interaction data and evaluate advertising reach effects, and obtain advertising effect monitoring results.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, by extracting key data points from market trends and combining them with the purchase behavior records of target consumers, highly personalized and dynamically updated advertising content is achieved, allowing advertising creativity to more accurately reflect the current interests and needs of consumers, thereby improving the attractiveness of advertising and user engagement. By using design software to draw a draft of the advertisement and iteratively modifying it in combination with historical successful cases, the creative quality of the advertisement is significantly improved, ensuring the innovation and attractiveness of the advertising content. In the authenticity verification stage, text analysis tools and image source checks are applied to ensure the compliance of advertising content, reduce legal risks and enhance brand reputation. In-depth execution of audience analysis allows accurate selection of target groups, enhances the targeting of advertising, and accurate settings in the advertising positioning stage optimize resource allocation and improve the cost-effectiveness of advertising delivery. Through real-time monitoring and user interaction data analysis, advertising effects are evaluated in real time, providing data support for future advertising strategies, making the advertising delivery process more efficient and predictable. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a system flow chart of the present invention;

[0050] Figure 2 It is a schematic diagram of the system framework of the present invention;

[0051] Figure 3 A flowchart of an advertisement content creation module in the present invention;

[0052] Figure 4 It is a flow chart of the authenticity verification module in the present invention;

[0053] Figure 5 This is a flow chart of the audience analysis module in the present invention;

[0054] Figure 6 This is a flow chart of the advertisement positioning module in the present invention;

[0055] Figure 7 A flowchart of the release execution module in the present invention;

[0056] Figure 8 This is a flow chart of the effect monitoring module in the present invention;

[0057] Fig. 9 It is a schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0060] Embodiment 1

[0061] See also Figure 1 , 2 The present invention provides a technical solution: an advertising management and distribution system based on the Internet of Things includes:

[0062] The advertising content creation module extracts key data points from market trends, combines them with the purchase behavior records of target consumers, conducts advertising management, determines advertising themes and messages, uses design software to draw a preliminary draft, and iterates and modifies based on advertising distribution efficiency and historical success cases to generate a creative advertising draft;

[0063] The authenticity verification module applies text analysis tools to manage advertisements, performs semantic analysis on creative advertisement drafts, identifies misleading and false claims, simultaneously checks image sources and attributes to determine copyright ownership, prepares for advertisement distribution, and obtains advertisement compliance review results;

[0064] The audience analysis module analyzes the behavior patterns and preference settings in the consumer database based on the advertising content in the advertising compliance review results, selects the age, region and purchasing power indicators of the target group, and constructs the target audience analysis results;

[0065] The advertising positioning module uses the target audience analysis results to determine the advertising delivery platform and optimal display time, set delivery parameters including frequency and location, and obtain advertising delivery strategy results;

[0066] The publishing execution module sets the scheduled tasks for advertising release according to the results of the advertising delivery strategy, adjusts the advertising display parameters of IoT devices, distributes advertisements, monitors the advertising delivery status and display frequency in real time, automatically publishes advertisements according to the plan, and establishes the advertising release execution results;

[0067] The effect monitoring module collects user interaction data from the results of advertising publishing, analyzes the user interaction data and evaluates the advertising reach and audience response, uses the feedback to adjust the advertising management strategy in the future time period, optimizes advertising distribution, and generates advertising effect monitoring results.

[0068] The creative advertising draft includes creative concept, content layout, and design style. The advertising compliance review results include text authenticity, image authorization, and compliance rating. The target audience analysis results include consumer behavior, interest classification, and response prediction. The advertising delivery strategy results include the selected platform, set time point, and frequency adjustment. The advertising release execution results include task scheduling, parameter adjustment, and monitoring implementation. The advertising effectiveness monitoring results include data collection, effectiveness evaluation, and optimization measures.

[0069] Specifically, if Figure 2 , 3 As shown, the advertising content creation module includes:

[0070] The market analysis submodule identifies key trends based on market results and real-time data, uses statistical tools to quantify changes in consumer preferences, analyzes the development potential of emerging markets, and adjusts market segmentation strategies based on indicator results. The execution process for generating market trend results is as follows;

[0071] The market analysis submodule is based on market results and real-time data. First, the mean and standard deviation of the market results data are calculated to identify the basic trends of the market. Real-time data, including price index and consumer satisfaction, are collected. Through correlation analysis of the data, key changes in consumer preferences are determined. The calculated consumer preference change index is combined with the market potential index, and the market segmentation is adjusted using a custom weighting method. The weighting coefficient is obtained through a linear regression model of historical data trends. The market strategy is then adjusted based on the weighted results. Finally, the market trend results are generated using the formula:

[0072] ;

[0073] in, Represents the market trend results, represents the price index, Represents consumer satisfaction, Represents the market potential index, , represents the weight coefficient obtained from the regression model, and is the coefficient for adjusting the weight.

[0074] The consumer behavior analysis submodule extracts key data points from market trend results, analyzes consumer purchase history and behavior data, screens key behaviors including purchase frequency and price sensitivity, segments consumer groups, and adjusts advertising targeting based on behavior patterns. The execution process for obtaining purchase behavior analysis results is as follows;

[0075] The consumer behavior analysis submodule extracts key data points from market trend results, analyzes consumer purchase history and behavior data, and uses complex clustering algorithms to group consumers by purchase frequency and price sensitivity. The process involves calculating each consumer's sensitivity to price changes, which is quantified by the rate of change in purchase behavior before and after the price change. A multi-dimensional scoring model is applied to the grouping results. The model combines behavioral patterns and historical purchase data to generate grouping priorities, and then adjusts advertising targeting strategies for different groups. Finally, the purchase behavior analysis results are obtained using the formula:

[0076] ;

[0077] in, Represents the results of purchasing behavior analysis. Represents the purchase frequency, represents price sensitivity, , is the influence coefficient obtained from data analysis, is the adjustment coefficient used to balance the weights of different behavior patterns.

[0078] The advertising design iteration submodule sets the advertising theme and core information based on the results of the purchase behavior analysis, uses design tools to create a draft of the advertisement, optimizes the visuals and copy based on initial feedback, compares historical successful cases and adjusts the content, and establishes the execution process of the creative advertising draft as follows;

[0079] The advertising design iteration submodule sets the advertising theme and core information based on the results of the purchase behavior analysis, uses image and text editing tools to create a draft of the advertisement, and uses formulas to calculate the proportion of visual and copy elements that need to be improved based on the collected consumer feedback. It compares with historical successful cases to obtain the improvement index of each element and adjusts the advertising content accordingly. After completing the steps, the final draft of the creative advertisement is formed using the formula:

[0080] ;

[0081] in, Represents the score of the creative advertising draft, Represents a visual element, Represents a text element , is the weight obtained based on historical case analysis, It is the overall adjustment coefficient used to optimize the overall quality of the draft advertisement.

[0082] Specifically, if Figure 2 , 4 As shown, the authenticity verification module includes:

[0083] The semantic review submodule uses natural language processing technology based on the creative advertising draft to parse the words and phrases in the advertising text, identify potential misleading and false claims based on the preset vocabulary, and perform semantic consistency scoring, analyze the logical relationship between differentiated semantic elements, adjust semantic parsing parameters and match differentiated advertising contexts, and generate the advertising authenticity evaluation results. The execution process is as follows;

[0084] The semantic review submodule is based on the creative advertising draft. First, it uses natural language processing technology to deeply analyze the words and phrases in the advertising text. This module uses an extended preset word library, which includes common misleading and false statements, to scan and identify the advertising text. Each recognized word or phrase is evaluated for consistency based on its semantic relationship score with the surrounding text using a weighted logical relationship model. According to the specific context of the advertisement, the semantic analysis parameters are adjusted to enhance the adaptability and authenticity of the advertising language. Finally, the advertising authenticity evaluation result is generated using the formula:

[0085] ;

[0086] in, Represents the result of advertisement authenticity assessment. Representative The weight of a word or phrase in the preset vocabulary, For the The semantic consistency score of a word or phrase, is the number of words and phrases identified in the text, To adjust the parameters to control the influence of the advertising context.

[0087] The copyright check submodule collects the features of image elements in the advertisement based on the evaluation results of the authenticity of the advertisement, and matches them with the copyright information in the database through an interface call. It analyzes the image sources with a high degree of matching, adjusts the matching algorithm, and obtains the execution process of the copyright ownership determination result as follows;

[0088] The copyright check submodule is based on the advertisement authenticity assessment results and is connected to the global copyright database through a specially designed interface. The module first extracts key features of image elements from the advertisement, such as color, texture, and shape, and then performs a detailed match with the copyright information stored in the database. An improved similarity calculation method is used in the matching process to determine the original source of the image elements. According to the accuracy of the matching results, the sensitivity and precision of the matching algorithm are appropriately adjusted to finally obtain the copyright ownership determination result, using the formula:

[0089] ;

[0090] in, Represents the result of copyright ownership determination. For the The weight of the image features, Represents the degree of matching with the corresponding image features in the database, To adjust the coefficient, optimize the sensitivity of feature matching, is the total number of image features analyzed, is the function used to calculate the matching degree, adjusted according to feature similarity and sensitivity.

[0091] The compliance review submodule determines the result based on the copyright ownership and applies the convolutional neural network algorithm to check whether the draft advertisement complies with the laws and regulations of the target market. By comparing the advertisement content with the regulatory requirements one by one, adjusting the regulatory matching parameters and covering the compliance check, the execution process of obtaining the advertisement compliance review result is as follows;

[0092] The compliance review submodule determines the result based on the copyright ownership and uses a custom rule matching method to check the compliance of the draft advertisement with laws and regulations. This module uses an updated regulatory database to compare the advertisement content with the laws and regulations of the target market one by one and calculate the compliance score of each advertisement content. By adjusting the regulatory matching parameters, different types of advertisements and markets are covered to ensure the comprehensive compliance of the advertisement content, thus obtaining the advertisement compliance review results.

[0093] The formula of the convolutional neural network algorithm is as follows:

[0094] ;

[0095] in, is the weight of the convolution kernel, For input advertising image or text data, is the bias, is the activation function, is the feature extraction result, is the normalization coefficient of the input data, is the dimension of the data, is the dimension weight coefficient, is the learning rate, is the error rate.

[0096] The execution process is as follows:

[0097] Input Data With weight Perform convolution operation and add bias , get the preliminary feature map, and then multiply the preliminary feature map by the normalization coefficient , used to adjust the scale of the data to ensure the consistency of data processing at different input levels, plus the dimension Multiply it by its corresponding weight coefficient , to emphasize the importance of data dimension, the learning rate and error rate The multiplication result is added to the feature map, which helps to adjust the effect of feature extraction according to the error in the training process. Process the composite feature map to generate the final feature extraction result , weight coefficient The confirmation method is to gradually adjust during the training process through the back-propagation algorithm to optimize the performance of the model.

[0098] Specifically, if Figure 2 , 5 As shown, the audience analysis module includes:

[0099] The behavior pattern analysis submodule is based on the advertising compliance review results, uses the transaction records and response data in the consumer database, determines the repetitive patterns of purchase behavior through time series analysis, adjusts the data analysis frequency and sample size, and obtains the execution process of the behavior pattern description as follows;

[0100] The behavior pattern analysis submodule is based on the results of the advertising compliance review. First, the transaction records and response data are extracted from the consumer database. Through time series analysis technology, the periodicity and repetitive patterns in consumer purchase behavior are determined. During the analysis process, the frequency of data analysis is adjusted according to the seasonal fluctuations and trend changes of the data. At the same time, the representativeness of the sample and the integrity of the data are considered to select the appropriate sample size. The analysis results will be compiled into a behavior pattern description to provide a clear view of the repetitive pattern of purchase behavior. The formula is:

[0101] ;

[0102] in, Represents the behavior pattern description, For at time point Purchase behavior data, is the total time period for analysis, is the attenuation factor, which is used to adjust the impact of old data on the current model. is the normalization coefficient to ensure the statistical validity of the description.

[0103] The preference setting analysis submodule analyzes the consumer's purchase data based on the behavior pattern description, identifies the key factors of consumer preferences, including product type and price sensitivity, determines the key preferences through comparative analysis, and adjusts the classification criteria for the key. The execution process of obtaining the preference mapping results is as follows;

[0104] The preference setting analysis submodule analyzes consumer purchase data based on behavioral pattern descriptions, paying special attention to product types and price sensitivity. By using advanced statistical models to compare and analyze various types of consumer data, the key factors in consumer purchase preferences are identified. The factors are then used to adjust the classification criteria to more accurately map consumers' real preferences and generate preference mapping results to provide a basis for subsequent marketing strategies. The formula is:

[0105] ;

[0106] in, represents the preference mapping result, For product type The purchase frequency, Price sensitivity for product type The average response value of is a weight factor, and the impact of each product type is determined based on historical data. The number of product types analyzed.

[0107] The target group selection submodule uses the preference mapping results to identify consumer groups with similar purchasing power, geographic location, and age. By adjusting the screening criteria and parameter settings, the accuracy of the target group is optimized. The execution process of obtaining the target audience analysis results is as follows;

[0108] The target group selection submodule uses the preference mapping results to conduct a detailed analysis of consumer groups, focusing on identifying similar consumers in terms of purchasing power, geographic location and age. Through advanced data segmentation technology and multivariate analysis methods, the screening criteria and parameter settings are adjusted to optimize the selection accuracy of the target group. The strategy helps ensure that the analysis results of the target audience are not only accurate but also operational. The formula is used:

[0109] ;

[0110] in, Represents the target audience analysis results, for group characteristics (such as purchasing power, geographic location, age), is the total number of features, is the importance weight of the feature, is the matching function, based on the group characteristics Target group characteristics The degree of proximity is scored.

[0111] Specifically, if Figure 2 , 6 As shown, the advertisement positioning module includes:

[0112] The platform selection submodule analyzes the user coverage and interaction data of the advertising platform based on the target audience analysis results, evaluates the advertising response rate and user engagement on the platform, selects the advertising platform that matches the target audience characteristics, and generates the selected platform list. The execution process is as follows;

[0113] The platform selection submodule is based on the target audience analysis results. First, user coverage and interaction data are collected from multiple advertising platforms. The data includes indicators such as the total number of users, daily active user ratio, click-through rate, and user engagement. By evaluating the match between the data and the target audience characteristics, a quantitative model is used to calculate the adaptability score of each platform. Based on the score, the platform that can best achieve the advertising delivery goal is selected and a list of selected platforms is generated. The formula is:

[0114] ;

[0115] in, Represents the comprehensive score of the selected platform, is the user coverage of platform s, is the interaction data score of platform s, is the weight coefficient adjusted according to the characteristics of the target audience. is the total number of platforms evaluated, and is a coefficient that weighs the importance of coverage and interaction.

[0116] The time optimization submodule uses the selected platform list to analyze the user active time data of multiple platforms, determine the time period when the target audience is online, adjust the time configuration of advertising display, and obtain the execution process of the optimal display period as follows;

[0117] The time optimization submodule uses the selected platform list to collect user active time data from the platform, such as the peak time of daily active users, the average online time of users, etc. Through statistical analysis, the target audience is most frequently active on each platform. The information is used to adjust the time configuration of advertising display to ensure that the advertisement is displayed within the time that users see it, so as to obtain the optimal display time, using the formula:

[0118] ;

[0119] in, Represents the optimal display period, is a set of time periods, For time period User activity on platform s, is the number of selected platforms, is the importance weight of each platform.

[0120] The parameter setting submodule sets the frequency and location of advertisements based on the optimal display period, the geographic distribution and behavior patterns of the target audience, adjusts parameters, optimizes coverage and avoids advertisement fatigue, and establishes the execution process of advertisement delivery strategy results as follows;

[0121] The parameter setting submodule sets the frequency and location of advertisements based on the optimal display period, the geographic distribution and behavior patterns of the target audience, and formulates specific delivery strategies by analyzing geographic distribution data and user behavior patterns to maximize coverage while avoiding potential advertising fatigue. The adjustment of advertisement frequency and location is based on an optimization model that takes into account the density of user distribution and the frequency of advertisement exposure, using the formula:

[0122] ;

[0123] in, Represents the effectiveness of the advertising strategy. is the user density at geographic location q, Score the behavior pattern. is the total number of target ad delivery locations. is the importance weight of the geographical location q, and are coefficients for adjusting for geographic and behavioral factors.

[0124] Specifically, if Figure 2 , 7 As shown, the release execution module includes:

[0125] The scheduled task setting submodule initializes the scheduled advertising release plan based on the advertising delivery strategy results, inputs the target market, expected release time and repetition frequency of the advertising campaign, optimizes the release plan according to the time zone of the differentiated market, adjusts the time point and frequency of task execution, and generates the execution process of the scheduled task advertising release plan as follows;

[0126] The scheduled task setting submodule is based on the results of the advertising delivery strategy. First, the scheduled release plan of the advertisement is initialized. This plan inputs the target market of the advertising campaign, the expected release time and the repetition frequency. In view of the time zone differences in different markets, a time optimization algorithm is used to calculate the best release time in each time zone. This algorithm considers the activity of the target market and the user's online mode to determine the most effective time point for advertising display. According to the time point, the specific time and frequency of task execution are adjusted to form a fully optimized scheduled task advertising release plan, using the formula:

[0127] ;

[0128] in, represents the efficiency of the scheduled task advertisement release plan, z represents different time zones, The best time to publish in this area. is the frequency factor adjusted according to market activity, Ng is the total number of regions in the market, An adjustment factor for each time zone.

[0129] The advertisement display adjustment submodule uses the time arrangement in the scheduled task advertisement publishing plan to set the advertisement display parameters for the connected IoT devices, including adjusting the display duration, optimizing the resolution, and setting the display frequency. It adjusts the parameters for differentiated advertisement contents. The execution process for obtaining the display parameter setting results is as follows;

[0130] The ad display adjustment submodule uses the time arrangement in the scheduled task ad publishing plan to set detailed ad display parameters for each connected IoT device, including adjusting the display duration, resolution and display frequency according to the ad content type and the performance of the target device. Through a dynamic adjustment algorithm, it optimizes the parameter settings for different types of ad content and the characteristics of viewing devices to achieve the best viewing effect. Finally, all the set parameters are summarized to form the display parameter setting results, using the formula:

[0131] ;

[0132] in, represents the total effect of display parameter settings, n represents different types of advertising content, , , are the adjustment values ​​of display duration, display frequency and resolution respectively, Ng is the number of types of advertising content, Optimize weights for different content types.

[0133] The status monitoring submodule uses the display parameter setting results to set up a real-time monitoring mechanism for advertising display, and implements continuous tracking of the advertising delivery status, including monitoring the display frequency of advertisements and audience interaction. By adjusting the accuracy of data collection and the monitoring frequency, the advertising display strategy is adjusted and market feedback is responded to. The execution process of obtaining the advertising release execution results is as follows;

[0134] The status monitoring submodule uses the display parameter setting results to set a real-time monitoring mechanism for advertising display. This mechanism implements continuous tracking of the status of advertising delivery, including monitoring the display frequency of advertisements and audience interaction. Through a high-precision data collection system, it collects and analyzes advertising effect data, and adjusts the monitoring frequency and data collection accuracy based on the data. This allows the module to dynamically adjust the advertising display strategy to respond to market feedback in real time, thereby obtaining the advertising release execution results. The formula is:

[0135] ;

[0136] in, Represents the effect of advertising execution. Represents different indicators for monitoring, is the variable value of the monitoring indicator, is the influence of this indicator, is the total number of monitored indicators, is the importance adjustment coefficient of each indicator.

[0137] Specifically, if Figure 2 , 8 As shown, the effect monitoring module includes:

[0138] The user interaction analysis submodule identifies and records the number of user clicks and viewing duration based on the data of the advertising publishing execution results, analyzes the data points and calculates the viewing completion rate and return visit rate of the advertisement. The execution process of obtaining the advertising viewing analysis results is as follows;

[0139] The user interaction analysis submodule is based on the data of the advertising execution results. First, it records each user's click and the specific duration of each viewing. By aggregating the data, it calculates the viewing completion rate of the advertisement, that is, the proportion of viewing time to the total advertising time, and the return visit rate, that is, the proportion of repeat viewing users to the total viewing users. The statistics will be used to measure the ability of the advertisement to attract and maintain user attention and form the advertising viewing analysis results. The formula is:

[0140] ;

[0141] in, Represents the advertising viewing analysis results. is the viewing time of user u, is the total duration of the ad, is the total number of viewing users, and r is the number of returning users.

[0142] The audience response evaluation submodule uses the advertising viewing analysis results, summarizes the users’ positive and negative feedback data, analyzes the number of comments and likes left by users, quantifies the popularity of the advertising content and the quality of feedback, and generates the audience feedback quantitative analysis results. The execution process is as follows;

[0143] The audience response evaluation submodule uses the advertising viewing analysis results to summarize all user feedback data, including positive feedback (such as likes) and negative feedback (such as negative comments). By analyzing the comment content and the number of likes, the popularity of the advertising content is quantified, and the quality of the feedback is evaluated. The process includes calculating the ratio of positive feedback to total feedback, and the content analysis of negative comments. Finally, the quantitative analysis results of audience feedback are generated using the formula:

[0144] ;

[0145] in, Represents the quantitative analysis results of audience feedback, is the number of positive feedback (such as likes), is the number of negative feedback (such as negative comments), is the number of messages, is the number of comments, is the adjustment coefficient of feedback quality.

[0146] The advertising strategy adjustment submodule uses the quantitative analysis results of audience feedback to review and adjust the advertising content, including modifying key information points and visual elements, adjusting the delivery time and frequency according to the analysis results, and matching the behavior patterns of the target audience. The execution process of establishing the advertising effect monitoring results is as follows;

[0147] The advertising strategy adjustment submodule uses the quantitative analysis results of audience feedback to conduct in-depth review and adjustment of advertising content, including updating key information points and visual elements in the advertisement to better attract the target audience. Based on the feedback analysis results, the advertising delivery time and frequency are adjusted to maximize its influence, considering the behavior patterns of the target audience, and adjusting the advertising strategy to optimize its contact and interaction, so as to establish a more accurate advertising effect monitoring result, using the formula:

[0148] ;

[0149] in, Represents the advertising effect monitoring results, To view the analysis results, To provide quantitative feedback, and Adjust weights for vision and feedback, The influence coefficient for overall advertising adjustment effect.

[0150] See also Fig. 9 :An advertisement management and distribution method based on the Internet of Things, the advertisement management and distribution method based on the Internet of Things is performed based on the above-mentioned advertisement management and distribution system based on the Internet of Things, and includes the following steps:

[0151] S1: Extract key data points from market trends, analyze data and determine the core message and theme of the advertisement, use design tools to adjust content parameters based on the determined message and compare with historical advertising data, optimize the visual and copy effects of the advertisement, and generate a draft advertisement;

[0152] S2: Use text analysis tools to analyze the language used in the draft advertisement, identify potential misleading statements, exclude expressions that do not comply with regulations, conduct image copyright checks, verify the legal right to use images, and obtain advertising review results;

[0153] S3: Based on the advertising review results, extract the consumer behavior data that matches the advertising target from the consumer database, analyze the consumer behavior data to define the age, region and economic ability of the target group, determine the optimal consumer group, and construct the audience analysis results;

[0154] S4: Use the audience analysis results to select matching advertising platforms and optimal display time, adjust advertising parameters including display frequency and location, set according to audience characteristics and platform data, and optimize advertising coverage and interaction to form an advertising strategy;

[0155] S5: According to the advertising delivery strategy, set the advertising display parameters of IoT devices, conduct scheduled advertising release and status monitoring, collect user interaction data in real time, analyze user interaction data and evaluate the advertising reach effect, adjust the advertising parameters in the future time period based on feedback to optimize the advertising effect and obtain the advertising effect monitoring results.

[0156] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An advertising management and distribution system based on the Internet of Things, characterized by: The system comprises: The advertising content creation module extracts key data points from market trends, combines them with the purchase behavior records of target consumers, compares them with historical successful cases, makes iterative modifications, and generates a creative advertising draft; The advertising content creation module includes: The market analysis submodule identifies key trends based on market results and real-time data, uses statistical tools to quantify changes in consumer preferences, analyzes the development potential of emerging markets, and adjusts market segmentation strategies based on indicator results to generate market trend results; The consumer behavior analysis submodule extracts key data points from the market trend results, analyzes consumer purchase history and behavior data, screens key behaviors including purchase frequency and price sensitivity, segments consumer groups, and adjusts advertising targeting based on behavior patterns to obtain purchase behavior analysis results; The advertising design iteration submodule sets the advertising theme and core information based on the purchase behavior analysis results, uses design tools to create a draft of the advertisement, optimizes the visuals and copy based on initial feedback, compares historical successful cases and adjusts the content, and establishes a creative advertising draft; The authenticity verification module uses text analysis tools to perform semantic analysis based on the creative advertisement draft, identifies misleading and false statements, checks the image source to determine the copyright ownership, and obtains the advertisement compliance review result; The authenticity verification module comprises: The semantic review submodule uses natural language processing technology to parse the words and phrases in the advertisement text based on the creative advertisement draft, identifies potential misleading and false claims according to the preset vocabulary, and performs semantic consistency scoring, analyzes the logical relationship between differentiated semantic elements, adjusts semantic parsing parameters and matches differentiated advertisement contexts, and generates advertisement authenticity evaluation results; Based on the advertisement authenticity evaluation result, the copyright checking submodule collects the features of the image elements in the advertisement through an interface call with the global copyright database, matches them with the copyright information in the database, analyzes the image sources with high matching degree, adjusts the matching algorithm, and obtains the copyright ownership determination result; The compliance review submodule applies the convolutional neural network algorithm based on the copyright ownership determination result to check whether the draft advertisement complies with the laws and regulations of the target market, and obtains the advertisement compliance review result by comparing the advertisement content with the regulatory requirements one by one, adjusting the regulatory matching parameters and covering the compliance check; The formula of the convolutional neural network algorithm is as follows: ; in, is the weight of the convolution kernel, For input advertising image or text data, is the bias, f is the activation function, is the feature extraction result, is the normalization coefficient of the input data, is the dimension of the data, is the dimension weight coefficient, is the learning rate, is the error rate; The audience analysis module analyzes the behavior patterns and preference settings in the consumer database according to the advertising compliance review results, selects the age, region and purchasing power indicators of the target group, and constructs the target audience analysis results; The audience analysis module includes: The behavior pattern analysis submodule uses transaction records and response data in the consumer database based on the advertising compliance review results, determines the repetitive pattern of purchase behavior through time series analysis, adjusts the data analysis frequency and sample size, and obtains the behavior pattern description; The preference setting analysis submodule analyzes the consumer's purchase data based on the behavior pattern description, identifies key factors of consumer preference, including product type and price sensitivity, determines key preferences through comparative analysis, and adjusts classification criteria for key preferences to obtain preference mapping results; The target group selection submodule uses the preference mapping results to identify consumer groups with similar purchasing power, geographical location and age, and optimizes the accuracy of the target group by adjusting the screening criteria and parameter settings to obtain the target audience analysis results; The advertisement positioning module uses the target audience analysis results to determine the advertisement delivery platform and optimal display time, sets delivery parameters including frequency and location, and obtains advertisement delivery strategy results; The advertisement positioning module comprises: The platform selection submodule analyzes the user coverage and interaction data of the advertising platform based on the target audience analysis results, evaluates the advertising response rate and user engagement on the platform, selects the advertising platform that matches the target audience characteristics, and generates a list of selected platforms; The time optimization submodule uses the selected platform list to analyze the user active time data of multiple platforms, determine the time period when the target audience is online, adjust the time configuration of the advertisement display, and obtain the optimal display period; The parameter setting submodule sets the frequency and location of advertisement delivery based on the optimal display period, the geographic distribution and behavior patterns of the target audience, adjusts the parameters, optimizes the coverage effect and avoids advertisement fatigue, and establishes the advertisement delivery strategy results; The publishing execution module sets the timing task of advertising publishing according to the advertising delivery strategy results, adjusts the advertising display parameters of the IoT device, monitors the advertising delivery status and display frequency in real time, and establishes the advertising publishing execution results; The publishing execution module includes: The scheduled task setting submodule initializes the scheduled advertisement release plan based on the advertising delivery strategy results, inputs the target market, expected release time and repetition frequency of the advertising campaign, optimizes the release plan according to the time zone of the differentiated market, adjusts the time point and frequency of task execution, and generates a scheduled task advertisement release plan; The advertisement display adjustment submodule uses the time arrangement in the scheduled task advertisement publishing plan to set the advertisement display parameters for the connected IoT devices, including adjusting the display duration, optimizing the resolution, and setting the display frequency, and adjusts the parameters for differentiated types of advertisement content to obtain the display parameter setting results; The status monitoring submodule adopts the display parameter setting results to set a real-time monitoring mechanism for advertising display, and implements continuous tracking of the advertising delivery status, including monitoring the display frequency of advertisements and audience interaction. By adjusting the accuracy of data collection and the monitoring frequency, the advertising display strategy is adjusted and market feedback is responded to, and the advertising release execution results are obtained; The effect monitoring module collects user interaction data from the advertising publishing execution results, analyzes the user interaction data, optimizes advertising distribution, and generates advertising effect monitoring results; The effect monitoring module comprises: The user interaction analysis submodule identifies and records the number of user clicks and viewing duration based on the data of the advertising publishing execution result, analyzes the data points to calculate the viewing completion rate and return visit rate of the advertisement, and obtains the advertising viewing analysis result; The audience response evaluation submodule uses the advertisement viewing analysis results to aggregate the positive and negative feedback data of users, analyze the number of comments and likes left by users, quantify the popularity of the advertisement content and the feedback quality, and generate the audience feedback quantitative analysis results; The advertising strategy adjustment submodule utilizes the audience feedback quantitative analysis results to review and adjust the advertising content, including modifying key information points and visual elements, adjusting the delivery time and frequency according to the analysis results, matching the target audience's behavior patterns, and establishing advertising effect monitoring results.

2. The Internet of Things-based advertising management and distribution system according to claim 1, characterized in that: The creative advertising draft includes creative concept, content layout, and design style; the advertising compliance review results include text authenticity, image authorization, and compliance rating; the target audience analysis results include consumer behavior, interest classification, and reaction prediction; the advertising delivery strategy results include the selected platform, set time point, and frequency adjustment; the advertising release execution results include task scheduling, parameter adjustment, and monitoring implementation; the advertising effect monitoring results include data collection, effect evaluation, and optimization measures.

3. An advertisement management and distribution method based on the Internet of Things, characterized in that: The Internet of Things-based advertising management and distribution system according to any one of claims 1 to 2 comprises the following steps: Extract key data points from market trends, analyze data, determine the core message and theme of the advertisement, use design tools to adjust content parameters, optimize the visual and copy effects of the advertisement, and generate a draft advertisement; Use text analysis tools to analyze the language used in the draft advertisement, identify potential misleading statements, conduct image copyright checks, verify the legal right to use images, and obtain advertising review results; Extracting consumer behavior data matching the advertising target from the consumer database through the advertising review results, analyzing the consumer behavior data to define the age, region and economic ability of the target group, and constructing audience analysis results; Using the audience analysis results, select matching advertising delivery platforms and optimal display time, adjust advertising parameters including display frequency and location, optimize advertising coverage and interaction, and form advertising delivery strategies; According to the advertising delivery strategy, the advertising display parameters of the IoT device are set, the advertising is released regularly and the status is monitored, the user interaction data is collected in real time, the user interaction data is analyzed and the advertising reach effect is evaluated, and the advertising effect monitoring results are obtained.