Advertisement design assisting method and system based on directional requirements

Abstract

The invention relates to the field of advertisement design, in particular to an advertisement design assisting method and system based on a directional demand, and the method comprises the steps: obtaining historical advertisement data and historical behavior data of a target user when a user side is detected to meet an advertisement triggering condition; according to the historical advertisement data and the historical behavior data, predicting current advertisement demand data of the target user; according to the advertisement demand data, generating an initial advertisement design, and judging whether a demand of a target user is met; when the initial advertisement design cannot meet the demand of the target user, behavior data and scene data of the target user are acquired, and demand change parameters of the target user are analyzed according to the behavior data and the scene data; determining a directional demand adjustment label of the target user according to the demand change parameter; adjusting the initial advertisement design according to the directional demand adjustment label to obtain an updated advertisement design; and obtaining an updated advertisement design based on a result of adjusting the initial advertisement design. And the advertisement design or delivery meets the directional requirements of the user.

Description

Technical Field

[0001] The present application relates to the technical field of advertisement design, and in particular to an advertisement design auxiliary method and system based on targeted demand. Background Art

[0002] Targeted demand advertising design is a strategy for pushing precise advertising based on user needs, interests and behavior data. This advertising design method pushes the most relevant and most in line with the user's needs by analyzing the user's personalized data, thereby improving the effectiveness and conversion rate of advertising.

[0003] In the prior art, the demand forecast and advertising recommendation are mainly based on the user's historical click, browse, purchase and advertising exposure data, so as to improve the click-through rate and conversion rate. However, in terms of occasion analysis, the prior art usually only performs coarse-grained matching through simple occasions, resulting in a lack of in-depth understanding of the dynamics of the scene and user needs. For example, in a high-risk, high-concentration scenario such as driving, the advertising push system does not fully consider the user's attention allocation and safety needs in a complex environment, and generates dynamic map ads, ads that require continuous interaction, or pop-up ads, which can easily lead to frequent interruptions of the user's attention while driving, requiring the user to stay or click, making the user's experience in this environment poor, and may even bring danger. Secondly, the prior art pursues the real-time nature of advertising, hoping to complete the advertising update at the moment when the user's behavior changes, so as to maximize the advertising effect. However, high-frequency real-time adjustments may cause frequent jumps in advertising content, making it difficult for users to form stable cognition. In addition, ads adjusted at high frequencies may contain noise, and the excessive sensitivity of the system can easily lead to advertising adjustments deviating from the real needs of users.

[0004] Therefore, the prior art has defects and needs to be improved. Summary of the invention

[0005] In order to solve one or several problems in the prior art, the main purpose of this application is to provide an advertising design assistance method and system based on targeted needs.

[0006] In order to achieve the above-mentioned invention object, the present application proposes an advertisement design auxiliary method based on targeted demand, the method comprising:

[0007] When it is detected that the user terminal meets the advertising triggering conditions, the historical advertising data and historical behavior data of the target user are obtained;

[0008] Predicting the current advertising demand data of the target user based on the historical advertising data and historical behavior data of the target user;

[0009] Generate an initial advertisement design based on the advertisement demand data, receive feedback data from the user end, and determine whether the needs of the target user are met based on the feedback data;

[0010] When the initial advertisement design cannot meet the needs of the target user, the behavior data and scenario data of the target user are obtained, and the demand change parameters of the target user are analyzed according to the behavior data and scenario data;

[0011] Determining the directional demand adjustment label of the target user according to the demand change parameter;

[0012] The initial advertisement design is adjusted by using the directional demand adjustment tag to obtain an updated advertisement design;

[0013] Based on the result of adjusting the initial advertisement design, an updated advertisement design is obtained.

[0014] The embodiment of the present application also provides an advertisement design assistance system based on targeted demand, including:

[0015] The first acquisition module is used to acquire the historical advertising data and historical behavior data of the target user when it is detected that the user terminal meets the advertisement triggering condition;

[0016] A prediction module, used to predict the current advertising demand data of the target user based on the historical advertising data and historical behavior data of the target user;

[0017] A judgment module, used to generate an initial advertisement design according to the advertisement demand data, receive feedback data from the user end, and judge whether the demand of the target user is met according to the feedback data;

[0018] A second acquisition module is used to acquire the behavior data and scenario data of the target user when the initial advertisement design cannot meet the needs of the target user, and analyze the demand change parameters of the target user according to the behavior data and scenario data;

[0019] A label module, used to determine the directional demand adjustment label of the target user according to the demand change parameter;

[0020] An adjustment module, configured to adjust the initial advertisement design by using the directional demand adjustment tag to obtain an updated advertisement design;

[0021] The updating module is used to obtain an updated advertisement design based on the result of adjusting the initial advertisement design.

[0022] The present application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0023] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0024] The advertising design auxiliary method and system based on targeted demand in the embodiment of the present application, by comprehensively analyzing the historical advertising data, behavior data and scenario data of the target users, effectively solves and improves the advertising design and delivery to meet the targeted needs of users. By predicting the advertising demand data of the target users and combining the historical behavior data of the users, the method can accurately capture the changes in user needs. This makes the advertising design more in line with the interests and needs of the users and improves the accuracy of advertising delivery. In the case that the initial advertising design cannot meet the needs of the users, the method can adjust the advertising design in time by analyzing the user's behavior data and scenario data. This dynamic adjustment mechanism can ensure that the advertising content is consistent with the current needs of the users, thereby effectively improving the click-through rate and conversion rate of the advertisements. By adjusting the labels according to the targeted needs of the target users, the advertising design can be optimized in the context of the users, avoiding excessive interference and irrelevant content display, thereby improving the user's advertising experience and satisfaction, and reducing the negative impact of advertising on the users. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flowchart of an advertisement design assistance method based on targeted demand according to an embodiment of the present application;

[0026] Figure 2 A flowchart of an advertisement design assistance method based on targeted demand according to an embodiment of the present application;

[0027] Figure 3 This is a schematic block diagram of the structure of an advertisement design assistance system based on targeted demand according to an embodiment of the present application;

[0028] Figure 4 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0029] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application 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 application and are not used to limit the present application.

[0031] Reference Figure 1 In an embodiment of the present application, a method for assisting advertisement design based on targeted demand is provided, and the method comprises:

[0032] S1. When receiving an advertisement demand instruction from a user, obtain the historical advertisement data and historical behavior data of the target user;

[0033] S2. predicting the current advertising demand data of the target user based on the historical advertising data and historical behavior data of the target user;

[0034] S3, generating an initial advertisement design according to the advertisement demand data, receiving feedback data from the user end, and determining whether the demand of the target user is met according to the feedback data;

[0035] S4. When the initial advertisement design cannot meet the needs of the target user, obtain the behavior data and scenario data of the target user, and analyze the target user's demand change parameters based on the behavior data and scenario data;

[0036] S5. Determine the directional demand adjustment tag of the target user according to the demand change parameter;

[0037] S6, adjusting the initial advertisement design by using the directional demand adjustment tag to obtain an updated advertisement design;

[0038] S7. Obtain an updated advertisement design based on the result of adjusting the initial advertisement design.

[0039] As described in the above steps S1-S4, when it is detected that the user terminal meets the advertising triggering conditions, the system needs to obtain its relevant historical data. Historical advertising data reflects which advertisements the user has been exposed to in the past, while historical behavior data can show the user's behavior pattern, interest tendency, consumption habits, etc. By analyzing the user's past behavior and advertising interaction, the system can understand the user's basic needs and provide a basis for subsequent advertising design. This is to extract the user's interest preferences from the data source and predict their possible advertising needs. By analyzing historical data (for example, using machine learning models such as collaborative filtering, decision trees or other prediction algorithms), predict the user's possible advertising needs at the current moment. This step is to make targeted demand predictions through pattern recognition of historical data. Historical advertising data and behavioral data are the main driving factors of advertising demand. Predicting user needs helps to generate an advertising design that initially meets their preferences. Through this prediction, the "ineffectiveness" of advertising can be minimized and the relevance of advertising can be improved. Based on the predicted advertising demand data mentioned above, the advertising design system generates a preliminary advertising plan. This preliminary design is intelligently generated based on the user's historical preferences, purchasing behavior, interests and other data, and may include visual design, text content, recommended products and other content. The preliminary ad design helps to quickly reflect the system's understanding of user needs and conduct the first round of screening to see if the ad meets user expectations. If the initial design can meet the needs, the next step will be simpler; otherwise, further optimization is required. If the initial ad design fails to effectively meet user needs, more data is needed to supplement it. At this point, the system will collect the target user's behavioral data (for example, real-time clicks, browsing, and purchasing behaviors) and scenario data (such as current time, geographic location, device type, etc.). These scenario data and behavioral data will help the system more accurately judge the user's immediate needs. User needs are dynamically changing, and relying solely on historical data may not be accurate enough. By obtaining behavioral data and scenario data in real time, it can be ensured that the ad design can be flexibly adjusted to meet current changes in demand.

[0040] As described in the above steps S5-S7, the system will analyze these new behaviors and scenario data to extract the parameters of demand changes. For example, the user's geographical location and occasion have changed, which may mean that their purchasing needs are different from before; or the user has browsed a specific product, indicating that their interests have changed. These parameters can reflect the changes in advertising demand. User needs change with time, environment, situation and other factors. Analyzing these change parameters can help the system adjust the advertising content in time to avoid fixed advertising strategies from being unable to keep up with changes in user needs. Based on the demand change parameters obtained by the above analysis, the system determines targeted demand adjustment tags for the target user. These tags are marks for demand changes, such as "preferred time period is evening", "interested in healthy food", "recent purchase intention", etc. Targeted demand adjustment tags are the core of personalized advertising adjustment. Through these tags, the user's current needs can be accurately locked, and advertising delivery can be further optimized to make it more in line with the user's immediate needs. According to the obtained targeted demand adjustment tags, the advertising system optimizes the initial advertising design. This may include adjusting the advertising content, display time, advertising format, etc., so as to better meet the user's current needs. By flexibly adjusting the ad design, we can ensure that the ad content is more personalized and accurate, improve the relevance of the ad and the user's acceptance. Users are more likely to be interested in and participate in ads that meet their needs, improving the effectiveness of the ad. Finally, the ad system generates an updated ad plan based on the adjusted design and prepares to push it to the target users. Through continuous adjustment and optimization, the ad design will meet the needs of the target users to the greatest extent, improve the conversion rate and effectiveness of the ad. Ensure that the final result of the ad delivery can meet the user's targeted needs and generate higher returns.

[0041] Reference Figure 2 In one embodiment, the method of analyzing the target user's demand change parameters based on the behavior data and scenario data includes:

[0042] S41, obtaining historical revenue data of the historical advertising data;

[0043] S42, analyzing the revenue conversion rate of the advertisement design according to the historical revenue data;

[0044] S43, obtaining scene data corresponding to historical advertising data;

[0045] S44, analyzing the coupling relationship between the scene characteristics and the revenue conversion rate according to the revenue conversion rate and the scene data corresponding to the historical advertising data, and determining the influencing characteristics of the revenue conversion rate according to the analysis results;

[0046] S45. Construct a demand analysis model based on the analysis results;

[0047] S46, acquiring the behavior data and scenario data of the target user in real time, inputting the behavior data and scenario data into the demand analysis model, and outputting the analysis result through the demand analysis model to obtain the demand change vector;

[0048] S47: Determine a demand change parameter of the target user based on the demand change vector.

[0049] As described in the above steps, collect and use revenue data from past advertising. These historical revenue data may include key indicators such as the click-through rate (CTR), conversion rate (CR), and ROI (return on investment) of the advertisement. With this data, we can evaluate the effectiveness of advertising and understand which advertisements performed better under past conditions. For example, some advertisements may have higher conversion rates at specific times, locations, or for specific groups of people. Analyzing historical data can provide data support for subsequent decisions. Historical data provides a basis for the model to help evaluate the performance of past advertisements. The revenue conversion rate of advertising design refers to the proportion of viewers converted into actual purchases or other business goals after the advertisement is released. Advertising forms with high revenue conversion rates can be used preferentially in future delivery. Revenue conversion rate is the core indicator of advertising effectiveness. Analyzing this parameter can help identify the key factors that affect the success of advertising. Scenario data refers to the environment or situational information where the advertisement is placed, including time, location, user device, weather and other factors. Scenario data provides a multi-dimensional perspective on the background information of the advertisement. Every scene of advertising will have an impact on the performance of the advertisement, so obtaining scenario data is a necessary step in analyzing the effectiveness of the advertisement. Through scene data, we can understand the background of advertising, which is crucial to understand why different ads perform differently under different conditions. For example, an ad is more popular in the prime time in the afternoon, but less effective in the evening. Scene data can provide data support for optimizing advertising delivery strategies. The effectiveness of advertising is not only affected by the design of the advertisement itself, but also by the scene background (such as time period, location, etc.). Therefore, collecting scene data can provide necessary information for a comprehensive analysis of advertising effectiveness. In this step, the core task is to analyze the relationship between different scene factors and advertising revenue conversion rate. By using data analysis or machine learning methods, we can find out the impact of scene characteristics (such as specific time period, user device type, etc.) on advertising conversion rate. Through the coupling analysis of historical advertising data and scene data, the goal is to determine the key features that affect revenue conversion rate. This step is to summarize and refine the analysis results to find the most influential factors, such as certain user characteristics, specific advertising design elements, or a certain delivery time period. This analysis result helps determine the optimization direction of advertising strategy and which factors are the most critical and can significantly improve conversion rate. After determining these influencing features, advertising delivery can focus more on these powerful factors, thereby improving advertising effectiveness. Based on the results of the previous analysis, a demand analysis model is constructed to evaluate and predict the changes in the needs of target users in real time. The model will combine the relationship between historical data, scenario characteristics and revenue conversion rate, and predict the potential needs of target users through machine learning or statistical modeling methods. This model can automatically adjust its understanding of user needs based on the ever-changing user behavior and scenario information, and then provide accurate demand forecasts and advertising delivery recommendations for the advertising system. The demand change vector indicates the direction and degree of change in user demand.The demand change vector helps to accurately identify the changing trend of user demand, thereby providing data support for advertising. This vector is a summary and prediction of the current demand status of users. Through the demand change vector, the fluctuation of user demand can be reflected from a quantitative perspective, providing precise guidance for the decision-making of the advertising system. Based on the demand change vector, the specific demand change parameters of the user are determined. For example, the demand change parameters can include how much the user's interest in a certain type of product has increased, or how the responsiveness of a certain advertising content has changed. Determining the demand change parameters is a key step for the advertising system to respond and adjust quickly, ensuring a high degree of match between advertising and user-oriented needs.

[0050] In one embodiment, before the step of analyzing the demand change parameters of the target user according to the behavior data and the scenario data, the method further includes:

[0051] identifying the type of scenario data and elements of an initial advertisement design;

[0052] Based on the recognition result, determining whether the elements of the initial advertisement design conflict with the type of the scene data;

[0053] When there is a conflict between the elements of the initial advertisement design and the type of the scene data;

[0054] Identifying the conflict type between the initial advertisement design and the scenario data;

[0055] An advertisement mode adjustment strategy is generated according to the conflict type.

[0056] As mentioned above, the system needs to identify the type of scene the user is currently in and the key elements of the initial ad design. Scene data usually includes the user's real-time environment (such as driving, resting, working, etc.), while ad design elements include the interactive mode of the ad (such as video, dynamic content, click requirements, etc.), display format, content category, etc. The system determines the user's current scene by collecting the user's behavioral data (such as geographic location, activity status, device sensors, etc.). At the same time, the nature of the ad is determined by analyzing the initial design elements of the ad (such as the dynamics, interactivity, information density, etc. of the ad). Ensure that the ad matches the user's current behavior or environment. Based on the identified scene type and ad design elements, determine whether the ad will interfere with the user's current needs or safety. For example, if the user is in driving mode and the ad requires the user to interact or click, it is obvious that the ad conflicts with the scene. This judgment is based on the comparative analysis of scene data and ad elements. The system will apply certain rules (such as prohibiting interactive ads while driving, avoiding overly entertaining ads while working, etc.) to evaluate whether the ad meets the needs of the scene. Through this judgment, the system can accurately identify the conflicts that may be caused by advertising, thereby reducing the negative impact of user experience, such as interference, distraction or irrelevant advertising content. When the system finds that there is a conflict between the advertising design and the scene data, measures must be taken to adjust it. Conflict types include the advertising format not meeting the scene requirements (such as dynamic advertising while driving), advertising information overload (in busy or high-pressure scenes), and the interactive requirements of the advertisement are inappropriate (such as requiring clicks or inputs in a work environment). The identification of conflict types relies on in-depth analysis of scenes and advertising designs, combined with artificial intelligence, machine learning and other technologies, and judging the relationship between advertisements and scenes through historical data and behavior prediction. Identifying conflict types can help the system accurately understand the root cause of advertising interference, thereby providing a basis for generating more effective adjustment strategies. After identifying the conflict type, the system will generate corresponding advertising adjustment strategies based on the specific conflict type. These strategies can include changing the display format of the advertisement (such as changing dynamic ads to static ads), or adjusting the interactive requirements of the advertisement (such as disabling all ads that require clicks while driving). The generation of adjustment strategies is based on in-depth analysis of conflict types, combined with machine learning models and intelligent recommendation algorithms, to automatically generate optimization plans. For example, if the conflict type is "high interaction requirements while driving", the system may choose to convert the ad into a non-interactive ad or delay the display of the ad. This adjustment of the ad model can minimize the interference of ads to users, ensure that ads are highly matched with users' actual needs and scenarios, improve users' experience, and reduce potential safety risks or discomfort.

[0057] In one embodiment, the method of generating an advertisement mode adjustment strategy according to the conflict type includes:

[0058] When the conflict type is a security conflict, adjusting the dynamic elements of the initial advertisement design to a static element mode;

[0059] Delaying the interactive elements of the initial advertisement design so as to trigger the interactive elements only when the security conflict is resolved, and recording the process of the security conflict;

[0060] Based on the adjustment results, determine the advertising mode adjustment strategy when there is a security conflict.

[0061] As described above, based on real-time monitoring of user scenarios (e.g., determining whether the user is driving or in other scenarios that require concentration), the system automatically adjusts dynamic advertising elements to static forms. Static ads are usually presented in the form of images or displays that do not require interaction, reducing interference to users. This adjustment can ensure that the ads can be displayed while avoiding the distraction risks that may be caused by dynamic elements. In this way, ads can continue to be displayed during high-risk activities of users (e.g., driving) without interfering with their attention to the surrounding environment, thereby improving the safety of ads. When a safety conflict is detected, the system adjusts the interactive elements in the ad (e.g., buttons, links, sliders, etc.) to a delayed triggering mode. That is, the interactive elements will not appear immediately, but will be activated only after the safety conflict is resolved. The principle of delayed triggering of interactive elements is based on changes in scene data. For example, if the user is driving or in a high-risk activity, the system will temporarily disable the interactive functions in the ad (e.g., click or slide) until the system detects that the safety conflict has been resolved (e.g., driving ends or enters a safe area). This process involves continuous monitoring of user activities and the application of contextual awareness technology. Delayed triggering of interactive elements can effectively reduce potential dangers caused by users performing interactive operations when it is unsafe. For example, when driving, the interactive requirements of the ad will be postponed until the end of the drive, thus ensuring the safety of the user. In addition, the system will record this safety conflict process in order to optimize the ad adjustment strategy in the future. During the process of adjusting the ad, the system will record the specific situation in which the safety conflict occurred, including the time of the conflict, the conditions that triggered it, and the behavior after the conflict was resolved. This process can help the system understand the root cause of the conflict and its frequency. The system continuously monitors the user's behavior and environmental information, combined with the changes in the ad elements, to record the specific process of each safety conflict. The records include user activity status, changes in ad dynamics, and the activation and disabling of interactive elements. By analyzing these records, the system can discover potential patterns or problems and further improve the ad adjustment mechanism. For example, if it is found that the frequency of safety conflicts in a certain scenario is high, the system can automatically adjust the ad design to better adapt to these high-risk scenarios, thereby improving the effectiveness of the ad and the user experience. By analyzing the above adjustment results, the system will develop a set of ad model adjustment strategies for safety conflicts. These strategies will be adjusted according to different conflict situations to ensure that ad display does not interfere with user safety. The system identifies the most effective adjustment method by analyzing the collected data (such as feedback after dynamic elements are converted to static, the effect of delayed triggering of interactive elements, etc.). The formulation of this strategy not only relies on technical judgment, but also includes user feedback and optimization of advertising effects.

[0062] In one embodiment, before the step of obtaining an updated advertisement design based on the result of adjusting the initial advertisement design, the method includes:

[0063] obtaining an updated advertisement design, and analyzing the complexity level of the advertisement content according to the advertisement design;

[0064] Obtaining historical behavior data and corresponding historical scenario data of the target user;

[0065] Analyzing the average interaction frequency of the target user according to the historical behavior data and the corresponding historical scenario data;

[0066] Based on the analysis results, a frequency analysis model is constructed to analyze the advertisement design update frequency acceptable to the target user based on the initial advertisement design;

[0067] Acquire the behavior data and scenario data of the target user in real time, input the advertisement design, behavior data and scenario data into the frequency analysis model, and output the advertisement design update frequency of the target user through the frequency analysis model;

[0068] The advertisement design is updated based on the advertisement design update frequency.

[0069] As described above, an updated version of the ad design is received and its content is analyzed for complexity. The complexity of the ad design involves multiple levels such as the visual elements, interactive functions, and animation effects of the ad. The evaluation of complexity helps determine whether the ad content is suitable for the target user. By analyzing the complexity of the ad, the system can understand the user appeal and ease of use of the ad. Ads with high complexity may cause overstimulation or information overload, affecting the user experience, while ads with low complexity may lack appeal. Based on this analysis result, the ad design can be further adjusted to better attract the target user. The historical behavior data (such as clicks, browsing, interactions, etc.) and historical scenario data (such as time, location, device type, etc.) of the target user are collected. These data help to deeply understand the user's behavior patterns and preferences in different scenarios. By analyzing the historical behavior data and scenario data, the system can build a user's behavior profile, help identify the user's preferences, active time periods, interaction frequency, and other information, thereby providing a basis for personalized recommendations for ad updates. Based on the historical behavior data and scenario data, the system calculates the average interaction frequency of the target user. This frequency indicator can reveal how often users interact with ads and their response patterns in specific scenarios. By calculating the number of times a user interacts with an ad in different scenarios, an average interaction frequency metric can be obtained. This data can reveal whether a user interacts with an ad more frequently in certain scenarios, or whether they are more interested in the ad content. Understanding the user's interaction frequency helps optimize the way ad content is displayed. For example, users with a high interaction frequency may be more suitable for displaying ads with higher interactivity, while users with a low interaction frequency may need a simple ad design. In this way, ads can be more accurately customized to target users. Based on historical data and interaction frequency analysis, a frequency analysis model is constructed with the goal of predicting the ad update frequency that users can accept. This model takes into account different user preferences, behavior patterns, and the complexity of ad design. By collecting the target user's behavior data and scenario data in real time, these data are input into the established frequency analysis model. Through model calculation, the ad design update frequency for each user is output. Real-time data collection is achieved by tracking user behavior and scenarios. The system will instantly capture the user's ad interaction behavior and pass this data into the frequency analysis model, which will output the appropriate ad update frequency in real time based on the input data. Real-time acquisition of user behavior data and update frequency prediction ensures that ad updates are customized based on current user behavior. This can improve the accuracy of advertising, avoid too many or too few updates, and enhance the user experience and effectiveness of advertising.

[0070] In one embodiment, after the step of obtaining the historical advertising data and historical behavior data of the target user, the method further includes:

[0071] When the historical behavior data cannot predict the target user's demand data, identifying the data type missing from the historical behavior data;

[0072] According to the missing data type, inferring an alternative data source corresponding to the data type;

[0073] Based on the inference result, the alternative data source is fused with the historical behavior data;

[0074] The fused historical behavior data is used to re-predict the demand data of the target user.

[0075] As mentioned above, when the historical behavior data of the target user is insufficient or cannot effectively predict the needs, the system will automatically identify which data types are missing, which are necessary to predict the needs of the target user. The missing data types may be time, location, device, social interaction, etc. Through the data missing analysis algorithm, the key fields in the user behavior data are evaluated to be complete. If some necessary behavior data (for example, behavior data for a specific time period or interaction data in a specific scenario) is missing, the system can mark these missing types. It ensures that the system can identify the situation of missing data and prevent the prediction accuracy from being reduced due to insufficient data. At the same time, this provides a basis for subsequent speculation of alternative data sources and data fusion. Once the missing data types are identified, the system will speculate and find other data sources that can replace these missing data. For example, if the user's interaction data in a specific period is missing, the system may speculate to use the user's behavior data in similar scenarios instead. The process of speculating alternative data sources usually relies on data association rules and similarity analysis. For example, by analyzing other users or historical data with similar behaviors to the target user, the system can speculate possible alternative data sources. After speculating the appropriate alternative data sources, the system will fuse these alternative data with the existing historical behavior data. The fusion process aims to combine the advantages of different data sources to enhance the comprehensiveness and consistency of the data. Data fusion can be achieved through a variety of methods, including weighted averaging, principal component analysis (PCA), model fusion, etc. Based on the relevance and importance of the data, the system will select an appropriate fusion method to combine the alternative data with the historical behavior data. By fusing the alternative data source with the historical behavior data, the system can use this new data set to re-predict the target user's demand data. This process is the final prediction link and will accurately predict the user's needs and behaviors. The fused data can be used as input and predicted by machine learning models (such as regression models, decision trees, deep learning, etc.). These models will be trained and optimized based on the fused data to predict the user's possible needs or behaviors.

[0076] In one embodiment, the conflict types include security conflict, experience conflict and emotional conflict. Security conflict occurs in links involving user security, user privacy, data protection, identity authentication, etc. It is manifested in that the system needs to ensure the security and confidentiality of user data while providing personalized services. For example, when collecting user historical behavior data, how to balance data collection and privacy protection is a security conflict. Experience conflict The degree of matching between the initial design elements of the advertisement (such as visual effects, recommended content, etc.) and the scene data type directly affects the user experience. For example, when the advertisement display content does not match the user's current scene (such as browsing a social media platform or shopping website), it will cause a sense of interference, affecting the user's interactive experience. The root cause of the experience conflict lies in whether the advertisement design can reasonably adapt to different scene data. For example, if the design elements of the advertisement placed on a mobile device are too complicated or do not meet the current needs of the user, it will lead to a decline in the user's experience. Advertisement design needs to consider the scene background, such as the user's emotional state, time, geographic location and other information, in order to provide the best display effect. Emotional conflict is usually reflected in the contradiction between the advertisement design and the user's emotional state. For example, the language, tone or style used in an advertisement may not match the user's emotional state in a specific scenario, causing the user to have emotional aversion or negative emotions. Emotional conflict occurs because the advertisement design fails to accurately identify and respond to the user's emotional state or current scenario. For example, when a user is in an anxious situation, showing a very lively or humorous advertisement may cause the user to feel uncomfortable. The advertisement design needs to identify the user's emotional state based on the scenario data and make corresponding adjustments.

[0077] In one embodiment, after the step of identifying the conflict type between the initial advertisement design and the scenario data, the method includes:

[0078] When the scene data is a driving scene, identifying dynamic elements, interactive elements, and visual complexity in the initial advertisement design;

[0079] According to the safety requirements of the driving scene, determine whether the dynamic elements, interactive elements and visual complexity pose a potential threat to driving safety;

[0080] When the dynamic element, interactive element or visual complexity poses a potential threat to driving safety, the conflict type is determined to be a driving safety conflict of a safety conflict.

[0081] As mentioned above, the driving scene is a special high-risk scene, and the user (driver) needs to focus highly on the driving task. Dynamic elements (such as animation, video), interactive elements (such as click, slide), and visual complexity (such as color contrast, information density) in advertising design may distract the driver and increase driving risks. Therefore, identifying these elements is the first step in judging whether the advertisement is suitable for the driving scene. By identifying the dynamic elements, interactive elements, and visual complexity in the advertising design, it is possible to identify the factors in the advertising design that may have a negative impact on driving safety, and provide basic data support for the subsequent conflict type judgment and adjustment strategy. The safety requirements of the driving scene mainly include reducing driver distraction, avoiding visual interference, and ensuring the priority of the driving task. By analyzing whether the dynamic elements, interactive elements, and visual complexity conflict with these safety requirements, it is possible to determine whether the advertising design poses a potential threat to driving safety. For example, dynamic elements may attract the driver's attention, interactive elements may require the driver to operate the device, and high visual complexity may increase the information processing burden. Through the judgment of safety requirements, it is possible to identify which elements in the advertising design may have a negative impact on driving safety, thereby providing a basis for the subsequent conflict type determination and adjustment strategy. This step ensures the safety of the advertising design in driving scenarios. When dynamic elements, interactive elements or visual complexity in the advertising design are judged to pose a potential threat to driving safety, these conflicts are classified as "driving safety conflicts." The determination of this conflict type is based on the particularity of the driving scenario, that is, any design element that may distract the driver's attention or increase the operating burden is considered a safety conflict. By clarifying the conflict type as "driving safety conflict", adjustment strategies can be generated in a targeted manner to ensure the safety of the advertising design in driving scenarios. At the same time, this classification also provides a clear guiding direction for subsequent adjustments to the advertising model.

[0082] In one embodiment, the step of generating an advertisement mode adjustment strategy according to the conflict type includes:

[0083] Based on the driving safety conflict, the dynamic elements in the initial advertisement design are adjusted to a static element mode, and the visual complexity is reduced;

[0084] Adjust the interactive elements in the initial advertisement design to a delayed trigger mode, which is triggered only when the vehicle stops or the driving environment is safe;

[0085] Adjusting the presentation of the advertisement content according to the real-time data of the driving scene, wherein the presentation includes voice broadcast or simplified visual information;

[0086] Real-time acquisition of user behavior data in driving scenarios, including driving speed, road conditions, and user attention distribution;

[0087] Analyze the user's acceptance of the advertising content and attention concentration in the driving scene based on the user behavior data;

[0088] Based on the analysis results, dynamically adjust the presentation duration, frequency and information density of the advertising content;

[0089] When an emergency situation is detected in a driving scenario, the presentation of the advertising content is paused, and the user behavior data in the emergency situation is recorded to adjust the emergency scenario adaptability of the advertising design.

[0090] As mentioned above, in driving scenes, dynamic elements (such as animations and videos) and high visual complexity (such as complex color contrast and dense information layout) can easily distract drivers and increase driving risks. By adjusting dynamic elements to static element mode and reducing visual complexity, visual interference to drivers can be reduced to ensure that their attention is focused on driving tasks. Interactive elements (such as clicking and sliding) require active operation by drivers, which significantly increases safety risks during driving. By adjusting interactive elements to delayed trigger mode, it can be ensured that interactive operations are only performed when the vehicle stops or the driving environment is safe, avoiding driver distraction during driving. In driving scenes, the processing of visual information may increase the cognitive burden of drivers, while voice broadcast is a safer way to present advertisements. By acquiring driving scene data (such as vehicle speed and road conditions) in real time, the presentation of advertising content can be dynamically adjusted, giving priority to voice broadcast or simplifying visual information to meet the special needs of driving scenes. Driving speed, road condition information and user attention distribution are important indicators reflecting the safety of driving scenes and user status. By acquiring these data in real time, the impact of advertising content on driving safety can be dynamically evaluated and data support can be provided for advertising adjustments. By real-time monitoring of driving scene data, timely adjustment of advertising content can be made to avoid negative impacts on driving safety. Dynamic adjustment of advertising content based on user behavior data ensures the applicability and effectiveness of advertising in driving scenarios. Through real-time data feedback, the decision-making process of advertising design can be optimized to improve the accuracy of advertising design. By analyzing user behavior data in driving scenarios (such as driving speed, road condition information, and attention distribution), the user's acceptance of advertising content and concentration can be evaluated. For example, when driving at high speeds or in complex road conditions, the user's concentration is low, and the advertising content should be more concise or delayed. Adjust the advertising content according to the user's acceptance and concentration to ensure that the advertisement is presented at the right time and in the right way. The advertising content is more in line with the user's actual needs and status, improving user satisfaction with the advertisement. Dynamic adjustment of advertising strategies through data analysis improves the intelligence level of advertising design. Based on the analysis results of user behavior data, the presentation duration, frequency, and information density of advertising content are dynamically adjusted to ensure the safety and effectiveness of advertising content in driving scenarios. For example, when driving at high speeds, shorten the advertisement presentation duration and reduce the information density to reduce interference to the driver. By dynamically adjusting the advertising content, the driver's attention is reduced and driving risks are reduced. Advertisement content is more in line with the needs of driving scenarios, ensuring that ad information can be effectively delivered. By dynamically adjusting strategies, the intelligence level of ad design and user experience can be improved. Emergency situations in driving scenarios (such as sudden braking and collision warnings) require the driver's full attention, and the presentation of ad content at this time may interfere with the driver's response. By pausing ad content and recording user behavior data in emergency situations, the adaptability of ad design in emergency scenarios can be optimized.Pause advertising content in emergency situations to ensure that drivers can focus on driving tasks. By recording user behavior data in emergency situations, the adaptability of advertising design in emergency scenarios can be optimized.

[0091] Reference Figure 3 In the embodiment of the present application, there is also provided an advertisement design assistance system based on targeted demand, including:

[0092] The first acquisition module 1 is used to acquire the historical advertising data and historical behavior data of the target user when it is detected that the user terminal meets the advertising triggering condition;

[0093] Prediction module 2, used to predict the current advertising demand data of the target user based on the historical advertising data and historical behavior data of the target user;

[0094] The judgment module 3 is used to generate an initial advertisement design according to the advertisement demand data, receive feedback data from the user end, and judge whether the demand of the target user is met according to the feedback data;

[0095] The second acquisition module 4 is used to acquire the behavior data and scenario data of the target user when the initial advertisement design cannot meet the needs of the target user, and analyze the demand change parameters of the target user according to the behavior data and scenario data;

[0096] Tag module 5, used to determine the directional demand adjustment tag of the target user according to the demand change parameter;

[0097] An adjustment module 6, configured to adjust the initial advertisement design by using the directional demand adjustment tag to obtain an updated advertisement design;

[0098] The updating module 7 is used to obtain an updated advertisement design based on the result of adjusting the initial advertisement design.

[0099] As described above, it can be understood that the various components of the advertising design assistance system based on targeted needs proposed in this application can realize the functions of any one of the advertising design assistance methods based on targeted needs described above, and the specific structure will not be repeated.

[0100] Reference Figure 4 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 4As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an advertising design assistance method based on targeted needs is implemented.

[0101] The above-mentioned processor executes the above-mentioned advertising design assistance method based on targeted demand, including: when it is detected that the user end meets the advertising triggering condition, obtaining the historical advertising data and historical behavior data of the target user; based on the historical advertising data and historical behavior data of the target user, predicting the current advertising demand data of the target user; based on the advertising demand data, generating an initial advertising design, and receiving feedback data from the user end, and judging whether it meets the needs of the target user based on the feedback data; when the initial advertising design cannot meet the needs of the target user, obtaining the behavior data and scenario data of the target user, and analyzing the demand change parameters of the target user based on the behavior data and scenario data; based on the demand change parameters, determining the targeted demand adjustment label of the target user; adjusting the initial advertising design with the targeted demand adjustment label to obtain an updated advertising design; based on the result of adjusting the initial advertising design, obtaining an updated advertising design.

[0102] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, an advertising design assistance method based on targeted demand is implemented, including the following steps: when it is detected that the user terminal meets the advertising triggering condition, the historical advertising data and historical behavior data of the target user are obtained; based on the historical advertising data and historical behavior data of the target user, the current advertising demand data of the target user is predicted; based on the advertising demand data, an initial advertising design is generated, and feedback data from the user terminal is received, and it is determined whether the demand of the target user is met based on the feedback data; when the initial advertising design cannot meet the demand of the target user, the behavior data and scenario data of the target user are obtained, and the demand change parameters of the target user are analyzed based on the behavior data and scenario data; based on the demand change parameters, a targeted demand adjustment tag of the target user is determined; the initial advertising design is adjusted by the targeted demand adjustment tag to obtain an updated advertising design; based on the result of adjusting the initial advertising design, an updated advertising design is obtained.

[0103] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0104] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0105] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An advertisement design auxiliary method based on directional demand, characterized in that: The method comprises: When it is detected that the user terminal meets the advertising triggering conditions, the historical advertising data and historical behavior data of the target user are obtained; Predicting the current advertising demand data of the target user based on the historical advertising data and historical behavior data of the target user; Generate an initial advertisement design based on the advertisement demand data, receive feedback data from the user end, and determine whether the needs of the target user are met based on the feedback data; When the initial advertisement design cannot meet the needs of the target user, the behavior data and scenario data of the target user are obtained, and the demand change parameters of the target user are analyzed according to the behavior data and scenario data; Determining the directional demand adjustment label of the target user according to the demand change parameter; The initial advertisement design is adjusted by using the directional demand adjustment tag to obtain an updated advertisement design; Based on the result of adjusting the initial advertisement design, an updated advertisement design is obtained.

2. The advertisement design assistance method based on targeted demand according to claim 1, characterized in that: The method of analyzing the target user's demand change parameters according to the behavior data and the scenario data includes: Obtaining historical revenue data of the historical advertising data; Analyze the revenue conversion rate of the advertisement design based on the historical revenue data; Obtain scene data corresponding to historical advertising data; Analyze the coupling relationship between the scene characteristics and the revenue conversion rate based on the revenue conversion rate and the scene data corresponding to the historical advertising data, and determine the influencing characteristics of the revenue conversion rate based on the analysis results; According to the analysis results, build a demand analysis model; Acquire the behavior data and scenario data of the target user in real time, input the behavior data and scenario data into the demand analysis model, output the analysis result through the demand analysis model, and obtain the demand change vector; Based on the demand change vector, a demand change parameter of the target user is determined.

3. The advertisement design assistance method based on targeted demand according to claim 2, characterized in that: Before the step of analyzing the target user's demand change parameters according to the behavior data and the scenario data, the method further includes: identifying the type of scenario data and elements of an initial advertisement design; Based on the recognition result, determining whether the elements of the initial advertisement design conflict with the type of the scene data; When there is a conflict between the elements of the initial advertisement design and the type of the scene data; Identifying the conflict type between the initial advertisement design and the scenario data; An advertisement mode adjustment strategy is generated according to the conflict type.

4. The advertisement design assistance method based on targeted demand according to claim 3 is characterized in that: After the step of identifying the conflict type between the initial advertisement design and the scenario data, the method includes: When the scene data is a driving scene, identifying dynamic elements, interactive elements, and visual complexity in the initial advertisement design; According to the safety requirements of the driving scene, determine whether the dynamic elements, interactive elements and visual complexity pose a potential threat to driving safety; When the dynamic element, interactive element or visual complexity poses a potential threat to driving safety, the conflict type is determined to be a driving safety conflict of a safety conflict.

5. The advertisement design assistance method based on targeted demand according to claim 4, characterized in that: The step of generating an advertisement mode adjustment strategy according to the conflict type comprises: Based on the driving safety conflict, the dynamic elements in the initial advertisement design are adjusted to a static element mode, and the visual complexity is reduced; Adjust the interactive elements in the initial advertisement design to a delayed trigger mode, which is triggered only when the vehicle stops or the driving environment is safe; Adjusting the presentation of the advertisement content according to the real-time data of the driving scene, wherein the presentation includes voice broadcast or simplified visual information; Real-time acquisition of user behavior data in driving scenarios, including driving speed, road conditions, and user attention distribution; Analyze the user's acceptance of the advertising content and attention concentration in the driving scene based on the user behavior data; Based on the analysis results, dynamically adjust the presentation duration, frequency and information density of the advertising content; When an emergency situation is detected in a driving scenario, the presentation of the advertising content is paused, and the user behavior data in the emergency situation is recorded to adjust the emergency scenario adaptability of the advertising design.

6. The advertisement design assistance method based on targeted demand according to claim 1, characterized in that: Before the step of obtaining an updated advertisement design based on the result of adjusting the initial advertisement design, the method includes: obtaining an updated advertisement design, and analyzing the complexity level of the advertisement content according to the advertisement design; Obtaining historical behavior data and corresponding historical scenario data of the target user; Analyzing the average interaction frequency of the target user according to the historical behavior data and the corresponding historical scenario data; Based on the analysis results, a frequency analysis model is constructed to analyze the advertisement design update frequency acceptable to the target user based on the initial advertisement design; Acquire the behavior data and scenario data of the target user in real time, input the advertisement design, behavior data and scenario data into the frequency analysis model, and output the advertisement design update frequency of the target user through the frequency analysis model; The advertisement design is updated based on the advertisement design update frequency.

7. The advertisement design assistance method based on targeted demand according to claim 1, characterized in that: After the step of obtaining the historical advertising data and historical behavior data of the target user, the method further includes: When the historical behavior data cannot predict the target user's demand data, identifying the data type missing from the historical behavior data; According to the missing data type, inferring an alternative data source corresponding to the data type; Based on the inference result, the alternative data source is fused with the historical behavior data; The fused historical behavior data is used to re-predict the demand data of the target user.

8. An advertisement design assistance system based on directional demand, characterized in that: include: The first acquisition module is used to acquire the historical advertising data and historical behavior data of the target user when it is detected that the user terminal meets the advertisement triggering condition; A prediction module, used to predict the current advertising demand data of the target user based on the historical advertising data and historical behavior data of the target user; A judgment module, used to generate an initial advertisement design according to the advertisement demand data, receive feedback data from the user end, and judge whether the demand of the target user is met according to the feedback data; A second acquisition module is used to acquire the behavior data and scenario data of the target user when the initial advertisement design cannot meet the needs of the target user, and analyze the demand change parameters of the target user according to the behavior data and scenario data; A label module, used to determine the directional demand adjustment label of the target user according to the demand change parameter; An adjustment module, configured to adjust the initial advertisement design by using the directional demand adjustment tag to obtain an updated advertisement design; The updating module is used to obtain an updated advertisement design based on the result of adjusting the initial advertisement design.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images