An Internet advertising marketing method and system based on artificial intelligence

Abstract

The present invention discloses an artificial intelligence-based internet advertising marketing method and system, which relates to the field of internet advertising technology. The method comprises the following steps: collecting user behavior data in real time via the internet and preprocessing it, extracting user behavior features, and fusing them into a comprehensive feature vector; constructing a dynamic prediction model for purchase intention, and predicting the user's purchase probability of a product based on the comprehensive feature vector; generating a product recommendation list based on the user's purchase probability of the product; generating personalized advertising content based on the product recommendation list, and pushing the personalized advertising content to the user based on the user's network usage scenario; and continuously collecting interaction data between the user and the personalized advertising content during the advertising push process to optimize the dynamic prediction model for purchase intention. By constructing a dynamic prediction model for purchase intention, the present invention accurately predicts the user's purchase probability, thereby improving the click-through rate and conversion rate of advertisements.

Description

Technical Field

[0001] The present invention relates to the field of Internet advertising technology, and in particular to an Internet advertising marketing method and system based on artificial intelligence. Background Art

[0002] With the rapid development of internet technology, advertising and marketing are gradually shifting from traditional offline models to online ones. In particular, personalized advertising based on user needs has become a key tool in digital marketing. Currently, intelligent advertising technologies rely primarily on big data analytics and artificial intelligence algorithms. These algorithms predict users' potential needs based on historical behavioral data, such as browsing history, purchase behavior, and search keywords, and deliver targeted advertising. This behaviorally informed advertising approach not only improves advertising accuracy but also enhances the user experience by reducing the distraction of irrelevant information. However, with the increasing complexity and diversity of user behavior data, the key research direction in advertising and marketing technology is how to more efficiently and accurately identify users' true needs and create more personalized advertising content.

[0003] Existing intelligent advertising push technology still has certain limitations in the processing of user behavior data and the personalized generation of advertising content. First, existing methods for analyzing user behavior data are mostly based on static models and lack the ability to dynamically respond to users' real-time behavior. As a result, the pushed advertising content may not match the user's immediate needs, affecting the click-through rate and conversion rate of the advertisement. Secondly, existing advertising push systems usually use a single recommendation algorithm, which fails to fully integrate the short-term and long-term behavioral characteristics of users, making it difficult to accurately predict the user's purchase probability, thereby affecting the personalized recommendation effect of advertisements. Therefore, how to dynamically update user behavior characteristics in real time during the advertising push process and conduct a comprehensive analysis based on the user's short-term and long-term behavior has become a key technical challenge to improve the accuracy of advertising push. Summary of the Invention

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

[0005] Therefore, the present invention provides an artificial intelligence-based Internet advertising marketing method and system to solve the problems in the prior art of lack of dynamic response to user behavior data and inability to combine short-term and long-term behavior characteristics for accurate advertising push.

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

[0007] In a first aspect, the present invention provides an artificial intelligence-based Internet advertising marketing method, which includes collecting user behavior data in real time through the Internet and preprocessing it, extracting user behavior features, and fusing them into a comprehensive feature vector; constructing a dynamic prediction model for purchase intention, and predicting the user's purchase probability of a product based on the comprehensive feature vector; generating a product recommendation list based on the user's purchase probability of the product; generating personalized advertising content based on the product recommendation list, and pushing personalized advertising content to users based on the user's network usage scenario; during the advertising push process, continuously collecting interaction data between users and personalized advertising content, and optimizing the dynamic prediction model for purchase intention.

[0008] As a preferred solution of the artificial intelligence-based Internet advertising and marketing method of the present invention, wherein: the user's behavioral data includes the user's browsing history, search keywords, purchase history, click behavior and social media interaction;

[0009] The preprocessing of user behavior data is as follows:

[0010] Clean user behavior data by removing invalid data, correcting erroneous data, and filling missing values;

[0011] Use hashing algorithms to identify duplicate user behavior records and delete multiple occurrences of the same data to avoid data redundancy.

[0012] Filter outliers and noise data through denoising;

[0013] Through standardization, the timestamps in different user behavior data are converted into a unified format.

[0014] As a preferred solution of the artificial intelligence-based Internet advertising and marketing method of the present invention, the following specific steps are used to extract user behavior characteristics:

[0015] Group user behavior data by time and divide it into different categories according to behavior type;

[0016] For each type of behavioral data, extract the user's behavior frequency within a specific time range;

[0017] By tracking page events, we can extract the duration and interaction depth of each user behavior;

[0018] Extract behavioral sequence features by analyzing the order in which users' behaviors occur;

[0019] Based on nonlinear transformation and feature product, various user behavior features are processed through different linear transformations, and a comprehensive feature vector is generated through the product interaction between features. The expression is:

[0020]

[0021] Among them, F is the comprehensive feature vector, f i represents the behavior characteristics of the i-th category, W i represents the weight matrix for linear transformation of the i-th type behavior feature vector, n represents the total number of user behavior features, σ is the nonlinear activation function, b i It is the bias term when performing linear transformation on the behavioral characteristics of the i-th category.

[0022] As a preferred solution of the artificial intelligence-based Internet advertising and marketing method of the present invention, the steps of constructing a dynamic prediction model of purchase intention and predicting the user's purchase probability of a product based on a comprehensive feature vector are as follows:

[0023] Through hierarchical behavior modeling, the purchase intention dynamic prediction model is divided into short-term behavior evaluation layer and long-term behavior evaluation layer;

[0024] The short-term behavior evaluation layer adopts a similarity weighting mechanism based on the Gaussian kernel. By comparing the difference between the current feature and the neighborhood feature, the weight is calculated and the neighborhood features are weighted and summed through the ReLU activation function to extract the characteristics of the short-term behavior. The expression is:

[0025]

[0026] Among them, Z s represents the short-term behavior characteristics of the user, F is the comprehensive feature vector, and F x represents the xth neighborhood feature in the comprehensive feature vector F, μ is the standard deviation of the Gaussian kernel, b is the bias term, k is the total number of short-term behavior feature vectors, and x is the index of the neighborhood feature;

[0027] The long-term behavior evaluation layer uses the Memory Network to embed users' long-term behaviors into memory units. Through the query mechanism, it selectively extracts and aggregates long-term behavior features related to users' purchase intentions. The expression is:

[0028]

[0029] Among them, Z l represents the long-term behavioral characteristics of users, k j represents the jth key vector, M j represents the j-th key vector h j The corresponding memory unit, W q Represents the weight matrix used by the user to map the comprehensive feature vector F to the query vector;

[0030] Using the gating mechanism, we dynamically adjust the purchase intention prediction model's focus on short-term and long-term behaviors. When users show impulse buying, the gating mechanism automatically increases its focus on short-term behaviors. When user behavior is stable, the gating mechanism pays more attention to the impact of long-term behaviors. The expression is:

[0031]

[0032] Where g represents the gating signal, σ is the nonlinear activation function, and ∈ represents the numerical offset;

[0033] The short-term behavior evaluation layer, the long-term behavior evaluation layer, and the gating mechanism are integrated through the gating mechanism and nonlinear fusion to form a dynamic prediction model for purchase intention.

[0034] The comprehensive feature vector is input into the purchase intention dynamic prediction model to predict the user's purchase probability of the product. The expression is:

[0035] y k =Sigmoid(W o ·(g·tanh(Z s,k )+(1-g)·tanh(Z l,k ))+b o );

[0036] Among them, y k represents the probability of the user purchasing the kth item, W o The weight matrix used to linearly transform the gated feature combination, Z s,k Represents the short-term behavior characteristics associated with the kth commodity, Z l,k Represents the long-term behavioral characteristics of the k-th commodity.

[0037] As a preferred solution of the artificial intelligence-based Internet advertising and marketing method of the present invention, wherein: generating a product recommendation list based on the user's purchase probability of the product, the specific steps are as follows:

[0038] According to the user's purchase probability y for each product k , sort all products in descending order, select the top N products after sorting, and generate a preliminary product recommendation list R;

[0039] Based on the user's historical behavior data, calculate the behavioral similarity between the current user and other users;

[0040] Based on the similarity between the current user and other users, select the M users with the highest similarity to the current user as the similar user set U;

[0041] Based on the similar user set U, calculate the collaborative filtering score of similar users for product k;

[0042] The probability y of the user purchasing the kth item k and collaborative filtering score r CF,k Combined, a new sorting index is generated, the expression is:

[0043] S k =λ·y k +(1-λ)·r CF,k ;

[0044] Among them, r CF,k represents the collaborative filtering score of similar users for product k, and λ is the purchase probability y of the balanced user for the kth product k and collaborative filtering score r CF,k The weight coefficient, S k It is a new ranking index, CF stands for collaborative filtering;

[0045] According to the new ranking index S k The preliminary product recommendation list R is optimized to generate the final product recommendation list R′.

[0046] As a preferred solution of the artificial intelligence-based Internet advertising and marketing method of the present invention, wherein: based on the product recommendation list, personalized advertising content is generated, and personalized advertising content is pushed to users according to the user's network usage scenario. The specific steps are as follows:

[0047] Based on the user's current network usage and scenario, the ad display format is selected based on the device type, access time period, and visited website type, and personalized ad content is generated for each product based on the recommended product list;

[0048] Based on the user's historical interests and behavior data, analyze the product categories that the user is most interested in, and give priority to pushing advertisements related to the user's historical interests and behavior data to improve the click-through rate and conversion rate of advertisements.

[0049] As a preferred solution of the artificial intelligence-based Internet advertising marketing method of the present invention, in which: during the advertising push process, the interaction data between users and personalized advertising content is continuously collected to optimize the purchase intention dynamic prediction model. The specific steps are as follows:

[0050] During the ad push process, all interaction data between users and ads is monitored and collected in real time;

[0051] Use the collected user interaction data to update the user's behavior characteristics in real time, integrate the updated behavior characteristics with the historical behavior characteristics, and optimize the comprehensive feature vector F;

[0052] Based on the optimized comprehensive feature vector F′, the purchase intention dynamic prediction model is optimized.

[0053] In the second aspect, the present invention provides an Internet advertising marketing system based on artificial intelligence, including a comprehensive feature vector generation module, a purchase probability prediction module, a recommendation list generation module, an advertisement push module and a model optimization module; the comprehensive feature vector generation module is used to collect user behavior data in real time through the Internet and preprocess it, and extract user behavior characteristics and fuse them into a comprehensive feature vector; the purchase probability prediction module is used to construct a purchase intention dynamic prediction model, and predict the user's purchase probability of the product based on the comprehensive feature vector; the recommendation list generation module is used to generate a product recommendation list based on the user's purchase probability of the product; the advertisement push module is used to generate personalized advertising content based on the product recommendation list, and push personalized advertising content to the user according to the user's network usage scenario; the model optimization module is used to continuously collect interaction data between the user and personalized advertising content during the advertisement push process, and optimize the purchase intention dynamic prediction model.

[0054] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the artificial intelligence-based Internet advertising marketing method as described in the first aspect of the present invention is implemented.

[0055] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the artificial intelligence-based Internet advertising marketing method as described in the first aspect of the present invention.

[0056] The present invention has the following beneficial effects: by collecting and preprocessing user behavioral data in real time, extracting comprehensive feature vectors, and combining short-term and long-term user behavior, a dynamic purchase intention prediction model is constructed to accurately predict the user's purchase probability and generate a personalized product recommendation list. Furthermore, during the ad push process, user interaction data is continuously collected and the model is dynamically optimized, achieving precise ad push and improving both click-through and conversion rates. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 This is a flow chart of the artificial intelligence-based Internet advertising and marketing method in Example 1.

[0059] Figure 2This is a flow chart of the artificial intelligence-based Internet advertising and marketing system in Example 1. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0061] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0062] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0063] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an Internet advertising marketing method based on artificial intelligence, comprising the following steps:

[0064] S1: Collect user behavior data in real time through the Internet and preprocess it, extract user behavior features, and fuse them into a comprehensive feature vector.

[0065] The above information is obtained with the user's consent and is used for legal purposes.

[0066] S1.1: User behavior data includes browsing history, search keywords, purchase history, click behavior, and social media interactions;

[0067] It should be noted that browsing history refers to the page information visited by users on websites or applications, including records of browsed products, articles or other content.

[0068] Search keywords: These are the query terms users enter into search engines, websites, or apps. They reflect users' proactive needs and immediate interests.

[0069] Purchase records: refers to the purchase behavior completed by users on e-commerce platforms or other trading platforms.

[0070] Click behavior: refers to the specific content that users click on on a web page or advertisement, including ad links, product details pages, etc.

[0071] Social media interaction: refers to user activities on social platforms, including likes, comments, shares, and follows.

[0072] S1.2: Preprocess user behavior data as follows:

[0073] S1.2.1: Clean user behavior data by removing invalid data, correcting erroneous data, and filling missing values;

[0074] Furthermore, ensure that user behavior data is complete and accurate, such as deleting records that are missing key fields or have incorrect formats;

[0075] S1.2.2: Use a hashing algorithm to identify duplicate user behavior records and delete multiple occurrences of the same data to avoid data redundancy that could affect subsequent analysis.

[0076] S1.2.3: Filter outliers and noisy data through denoising; for example, exclude users who stay for unusually long periods of time;

[0077] The specific process is as follows: First, each user behavior record (such as browsing history, click behavior, etc.) is converted into a unique hash value, ensuring that the same behavior record generates the same hash value. Next, the system compares all generated hash values ​​to identify duplicate behavior records. For the same record that appears multiple times, only the first occurrence is retained, and subsequent duplicate data is deleted. This effectively avoids data redundancy, ensuring that each valid data item appears only once, thereby improving data accuracy and preventing duplicate data from negatively impacting subsequent behavior analysis and model training.

[0078] S1.2.4: Convert timestamps in different user behavior data into a unified format through standardization.

[0079] Furthermore, normalization was performed to ensure that all behavioral data could be correctly aligned and analyzed in chronological order.

[0080] S1.3: Group user behavior data by time and divide it into different categories according to behavior type;

[0081] For example, the user's behavior data in the past 7 days can be divided into categories such as browsing behavior (such as browsing a product page 5 times), search behavior (such as searching for "smartphone" 2 times), and click behavior (such as clicking on an ad 3 times) for analysis.

[0082] S1.4: For each type of behavior data, extract the user's behavior frequency within a specific time range;

[0083] For example, if a user browses a certain product category page 25 times in a week, the frequency characteristic of this behavior is recorded as 25 times;

[0084] S1.5: Through page event tracking, extract the duration and interaction depth of each user behavior;

[0085] For example, the average duration of a user's browsing time and the duration of video ad viewing can be used as behavioral deep features. These features can reflect the user's attention to a product and be converted into feature vectors.

[0086] S1.6: Extract behavior sequence features by analyzing the order in which users' behaviors occur;

[0087] For example, a user's behavior sequence of searching for a product and adding it to the shopping cart within a short period of time may indicate that the user has a high purchase intention;

[0088] S1.7: Based on nonlinear transformation and feature multiplication, various user behavior features are processed through different linear transformations, and a comprehensive feature vector is generated through the product interaction between features. The expression is:

[0089]

[0090] Among them, F is the comprehensive feature vector, f i represents the behavior characteristics of the i-th category, W i represents the weight matrix for linear transformation of the i-th type behavior feature vector, n represents the total number of user behavior features, σ is the nonlinear activation function, b i It is the bias term when performing linear transformation on the behavioral characteristics of the i-th category.

[0091] It should be noted that based on the nonlinear transformation and feature interaction of multiple types of user behavior features, different types of user behaviors (such as browsing, clicking, searching, etc.) are integrated in the form of feature product. Each type of behavior feature f i By linearly transforming the weight matrix W i and the bias term b i After processing, the results of various features interact through multiplication to capture the complex relationships between behaviors. Finally, the feature interaction results are further processed through a nonlinear activation function σ to generate a comprehensive feature vector F, thereby improving the accuracy of modeling user behavior and capturing potential nonlinear associations.

[0092] S2: Build a dynamic prediction model for purchase intention and predict the user's purchase probability of the product based on the comprehensive feature vector.

[0093] S2.1: Through hierarchical behavior modeling, the purchase intention dynamic prediction model is divided into a short-term behavior evaluation layer and a long-term behavior evaluation layer;

[0094] It should be noted that the benefit of dividing the purchase intention dynamic prediction model into short-term and long-term behavior evaluation layers is that this hierarchical modeling can capture users' immediate needs and long-term preferences separately. The short-term behavior evaluation layer focuses on users' recent dynamic behavior, reflecting their current interests and purchase intentions, while the long-term behavior evaluation layer analyzes users' historical behavior to reveal their stable preferences and consumption habits. By combining these two layers, the system can more comprehensively and accurately predict users' purchase intentions, thereby enabling personalized advertising and recommendations.

[0095] S2.1.1: The short-term behavior evaluation layer uses a similarity weighting mechanism based on a Gaussian kernel. By comparing the difference between the current feature and the neighboring features, the weight is calculated and the weighted sum of the neighboring features is applied through the ReLU activation function to extract the characteristics of short-term behavior. The expression is:

[0096]

[0097] Among them, Z s represents the short-term behavior characteristics of the user, F is the comprehensive feature vector, and F x represents the xth neighborhood feature in the comprehensive feature vector F, μ is the standard deviation of the Gaussian kernel, b is the bias term, k is the total number of short-term behavior feature vectors, and x is the index of the neighborhood feature;

[0098] It should be noted that the benefit of extracting short-term features based on the Gaussian kernel is that it can effectively smooth noise and capture local patterns in short-term behavior by weighting the similarity between the current feature and neighboring features, giving higher weights to more similar features. Furthermore, the smoothness of the Gaussian kernel ensures gradual processing between features, helping to retain key information when extracting short-term behavior features, reducing the risk of overfitting, and ultimately extracting more representative short-term features through the ReLU activation function.

[0099] S2.1.2: The long-term behavior evaluation layer uses a memory network to embed users’ long-term behaviors into memory units. Through a query mechanism, it selectively extracts and aggregates long-term behavior features related to users’ purchase intentions. The expression is:

[0100]

[0101] Among them, Z l Represents the long-term behavioral characteristics of users, h j represents the jth key vector, M j represents the j-th key vector h j The corresponding memory unit is the user’s j-th long-term behavior embedding, W q Represents the weight matrix used by the user to map the comprehensive feature vector F to the query vector;

[0102] It should be noted that the reason why the long-term behavior evaluation layer adopts Memory Network is that it can effectively store and manage the user's long-term behavior data through the memory mechanism, and selectively extract the long-term behavior features that are most relevant to the current purchase intention through the query mechanism. Specifically, W in the expression q Map the user's comprehensive feature vector F to the query vector by comparing it with the key vector h j , and selectively aggregate the stored long-term behavior embedding M j This mechanism ensures that the model can flexibly extract the most relevant information from a large amount of long-term behavior, thereby improving its ability to capture users' long-term preferences and behavior patterns, and combining short-term behavior to make more accurate purchase intention predictions.

[0103] S2.1.3: Use a gating mechanism to dynamically adjust the purchase intention prediction model's focus on short-term and long-term behaviors. When users show impulse buying, the gating mechanism automatically increases its focus on short-term behaviors. When user behavior is stable, the gating mechanism pays more attention to the impact of long-term behaviors. The expression is:

[0104]

[0105] Where g represents the gating signal, σ is the nonlinear activation function, and ∈ represents the numerical offset, which is used to prevent instability caused by zero or very small values ​​during the calculation process.

[0106] It should be noted that the benefit of utilizing a gating mechanism is that the system can dynamically adjust the emphasis on short-term and long-term behaviors based on the user's current behavior. When a user exhibits impulsive buying behavior, the gating mechanism automatically increases the emphasis on short-term behavior through expression g. When user behavior stabilizes, the gating mechanism prioritizes the impact of long-term behavior. This dynamic adjustment allows the model to more flexibly balance the weights of short-term and long-term behaviors, thereby improving the accuracy of purchase intention predictions and preventing computational instability in extreme cases (prevented by ∈).

[0107] It should also be noted that the specific method for determining impulsive buying is to monitor a user's short-term behavioral data (such as browsing, clicking, and searching over the past week). If the frequency of a certain type of behavior increases significantly within a short period of time, the user can be determined to be in an "impulsive buying" state. For example, a user may view the detail pages of the same or related products multiple times within a week, or may click on them repeatedly within a short period of time.

[0108] The specific method for determining whether user behavior is stable is to examine the user's long-term behavior data (such as purchase records and search history over the past month). If the user's behavior frequency is low in the short term and there is no obvious high-frequency click or search behavior, it can be determined that "behavior is stable." For example, a user may not frequently browse or click on products over a period of time, relying mainly on historical purchase records and long-term interests.

[0109] S2.2: The short-term behavior evaluation layer, the long-term behavior evaluation layer, and the gating mechanism are integrated through a gating mechanism and nonlinear fusion to form a dynamic prediction model for purchase intention.

[0110] S2.3: Input the comprehensive feature vector into the purchase intention dynamic prediction model to predict the user's purchase probability of the product. The expression is:

[0111] y k =Sigmoid(W o ·(g·tanh(Z s,k )+(1-g)·tanh(Z l,k ))+b);

[0112] Among them, y k represents the probability of the user purchasing the kth item, W o The weight matrix used to linearly transform the gated feature combination, Z s,k Represents the short-term behavior characteristics associated with the kth commodity, Z l,k Represents the long-term behavioral characteristics of the k-th commodity.

[0113] It should be noted that this expression dynamically adjusts the degree of attention to short-term and long-term behaviors by inputting the comprehensive feature vector into the purchase intention dynamic prediction model to predict the user's purchase probability y for the kth item. k Specifically, the gating signal g controls the model’s response to the short-term feature Z s,k and long-term characteristics Z l,k The weighted combination of , respectively, uses the tanh activation function to process short-term and long-term behavior features. Subsequently, the gated feature combination is linearly transformed (by the weight matrix W o and bias term b), and outputs the final purchase probability y through the Sigmoid function k This mechanism can dynamically adjust the weights of short-term and long-term features based on the user’s current behavior, thereby more accurately predicting the user’s purchase intention.

[0114] S3: Generate a product recommendation list based on the user's purchase probability of the product.

[0115] S3.1: Based on the user's purchase probability y for each product k, sort all products in descending order, select the top N products after sorting, and generate a preliminary product recommendation list R;

[0116] S3.2: Based on the user's historical behavior data, calculate the behavior similarity between the current user and other users. The expression is:

[0117]

[0118] Among them, u represents the behavior vector of the current user, v represents the behavior vector of other users, and u k represents the number of times the current user has acted on product k, v K represents the number of actions taken by other users on product i, and S(u,v) represents the similarity between the current user and other users;

[0119] S3.3: Based on the similarity between the current user and other users, select the M users with the highest similarity to the current user as the similar user set U;

[0120] S3.4: Based on the similar user set U, calculate the collaborative filtering score of similar users for product k, expressed as:

[0121]

[0122] Among them, r CF,k represents the collaborative filtering score of similar users for product k, b u,k is the behavior value of user u towards product k;

[0123] Furthermore, the collaborative filtering score represents the collective purchase probability of other users;

[0124] S3.5: The user's purchase probability y for the kth item k and collaborative filtering score r CF,k Combined, a new sorting index is generated, the expression is:

[0125] S k =λ·y k +(1-λ)·r CF,k ;

[0126] Among them, r CF,k represents the collaborative filtering score of similar users for product k, and λ is the purchase probability y of the balanced user for the kth product k and collaborative filtering score r CF,k The weight coefficient, S k It is a new ranking index, CF stands for collaborative filtering;

[0127] It should be noted that this expression combines the user's purchase probability y k and collaborative filtering score rCF,k Generate a new ranking index S k , where λ controls the balance between the two. This not only reflects the user's personalized purchase intention, but also leverages collaborative filtering feedback from similar users to improve the accuracy and personalization of recommendations.

[0128] It should also be noted that λ is set based on the relative importance of personalized recommendation and collaborative filtering. For example, if the user's historical behavior data is relatively rich and the personalized demand is strong, λ can be set to a larger value (such as 0.8) to focus more on the user's purchase probability y of the product. k If the user's behavior data is less or unclear, λ can be set to a smaller value (such as 0.3), and more reliance is placed on the collaborative filtering score r of similar users. CF,k to generate a list of recommendations.

[0129] S3.6: According to the new ranking index S k The preliminary product recommendation list R is optimized to generate the final product recommendation list R′.

[0130] S4: Generate personalized advertising content based on the product recommendation list and push personalized advertising content to users based on their network usage scenarios.

[0131] For example, suppose the preliminary product recommendation list R contains products A, B, and C, and their purchase probabilities y are calculated respectively. k and collaborative filtering score r CF,k , and use λ to balance the influence of the two. After calculation, the comprehensive score of product A is 0.66, product B is 0.56, and product C is 0.74. According to these new ranking indicators S k , the system re-sorts the products from high to low according to the scores and generates the final product recommendation list R′, namely: product C, product A, product B.

[0132] S4.1: Based on the user's current network usage and scenario, the ad display format is selected based on the device type, access time period, and visited website type, and personalized ad content is generated for each product based on the recommended product list;

[0133] For example, if a user browses a social media platform using a mobile device at night, the system will select an appropriate native advertising format based on the device type, and based on the access time period and the characteristics of the social platform, generate personalized advertising content for the user from the recommended product list, such as pushing smart home products suitable for evening use, to ensure the relevance and display effect of the advertisement.

[0134] Ad display formats include banner ads, pop-up ads, video ads, native ads, and recommendation bar ads, etc., to provide the best display effect based on the user's browsing scenarios and preferences.

[0135] S4.2: Based on the user's historical interests and behavior data, analyze the product categories that the user is most interested in, and prioritize pushing advertisements related to the user's historical interests and behavior data to improve the click-through rate and conversion rate of advertisements.

[0136] For example, suppose a user's historical interests and behavior data show that they frequently browse and purchase electronics, particularly smartphones and headphones. By analyzing this data, the system prioritizes electronic product-related ads, such as promotions for the latest smartphones or wireless headphones, thereby increasing ad click-through rates and conversion rates, as these products are highly relevant to the user's interests.

[0137] Behavioral data includes browsing history, purchase history, and click behavior.

[0138] S5: During the ad push process, continuously collect data on user interaction with personalized ad content to optimize the purchase intention dynamic prediction model.

[0139] S5.1: During the ad push process, all user interaction data with the ad is monitored and collected in real time;

[0140] It should be noted that interaction data includes the number of times users click on ads, frequency of ad exposure, duration of stay, scrolling behavior, whether they make a purchase, whether they close or skip ads, and whether they share or comment on the ad content. By collecting this interaction data, the system can evaluate ad effectiveness in real time and dynamically adjust push strategies.

[0141] S5.2: Use the collected user interaction data to update the user's behavior characteristics in real time, integrate the updated behavior characteristics with the historical behavior characteristics, and optimize the comprehensive feature vector F;

[0142] It should be noted that during the ad push process, the system uses collected user interaction data (such as number of clicks, duration of stay, purchase behavior, etc.) to update the user's behavioral characteristics in real time. First, the system integrates this new data with the user's current behavioral characteristics and dynamically adjusts short-term behavioral characteristics. Subsequently, the system combines the updated behavioral characteristics with the user's historical behavioral characteristics to ensure that they reflect the user's immediate interests while retaining their long-term preferences. Through this integration, the comprehensive feature vector is optimized, making subsequent ad push more accurate and personalized, thereby improving the effectiveness of advertising.

[0143] It should also be noted that the updated behavioral features are integrated with historical behavioral features. Specifically, the gating mechanism assigns higher weights to recent behavioral features. When a user expresses an impulse to buy, the weight of short-term behavioral features increases, while the weight of long-term behavioral features decreases accordingly. The system then fuses the short-term and long-term behavioral features through a weighted summation to generate a new behavioral feature vector. Finally, the integrated features are nonlinearly transformed using a nonlinear activation function (such as ReLU or Sigmoid) to generate an optimized comprehensive feature vector F, which is used for further purchase probability prediction and personalized advertising push.

[0144] S5.3: Optimize the purchase intention dynamic prediction model based on the optimized comprehensive feature vector F′.

[0145] It should be noted that the system inputs the optimized comprehensive feature vector F′ into the purchase intention dynamic prediction model to further improve prediction accuracy. By combining real-time user interaction data and historical behavioral characteristics, the optimized F′ more comprehensively reflects the user's current interests and long-term preferences. The model uses this optimized feature vector to dynamically weight short-term and long-term behaviors, readjusting the impact of each behavior on purchase intention. This allows for more accurate predictions of the user's purchase probability for different products, ultimately enabling personalized and efficient advertising strategies.

[0146] This embodiment also provides an artificial intelligence-based Internet advertising and marketing system, comprising: a comprehensive feature vector generation module, a purchase probability prediction module, a recommendation list generation module, an advertisement push module, and a model optimization module;

[0147] The comprehensive feature vector generation module is used to collect user behavior data in real time through the Internet, pre-process it, extract user behavior features, and fuse them into a comprehensive feature vector;

[0148] The purchase probability prediction module is used to build a dynamic prediction model for purchase intention and predict the user's purchase probability of the product based on the comprehensive feature vector;

[0149] The recommendation list generation module is used to generate a product recommendation list based on the user's purchase probability of the product;

[0150] Advertisement push module, used to generate personalized advertising content based on the product recommendation list and push personalized advertising content to users according to their network usage scenarios;

[0151] The model optimization module is used to continuously collect data on users' interactions with personalized advertising content during the advertising push process, and optimize the dynamic prediction model for purchase intention.

[0152] This embodiment also provides a computer device suitable for the case of an artificial intelligence-based Internet advertising and marketing method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the artificial intelligence-based Internet advertising and marketing method proposed in the above embodiment.

[0153] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0154] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the artificial intelligence-based Internet advertising and marketing method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0155] In summary, this invention builds a dynamic purchase intention prediction model by collecting and preprocessing user behavioral data in real time, extracting comprehensive feature vectors, and combining short-term and long-term user behavior. This model accurately predicts a user's purchase probability and generates a personalized product recommendation list. Furthermore, during the ad push process, user interaction data is continuously collected and the model is dynamically optimized, achieving precise ad push and improving both click-through and conversion rates.

[0156] Example 2, referring to Table 1, is the second embodiment of the present invention. In order to further verify the technical solution of the present invention, experimental simulation data of an Internet advertising marketing method based on artificial intelligence is provided.

[0157] In order to verify the effectiveness of the Internet advertising marketing method based on artificial intelligence, this embodiment selected 100 users and divided them into two groups: the first group used the traditional static advertising push method (traditional push group), and the second group used the intelligent advertising marketing method of the present invention (intelligent push group). The experiment lasted for two weeks and mainly examined key indicators such as ad click-through rate, ad conversion rate, user stay time, purchase success rate, and ad relevance score. The behavioral data of all users were collected in real time through the Internet and preprocessed to ensure the accuracy and completeness of the data.

[0158] During data preprocessing, we first cleanse user browsing behavior, search keywords, purchase history, clickthrough rate, and social media interactions to remove invalid and duplicate data. We use hashing algorithms to identify duplicate behaviors, remove redundant data, and standardize timestamps and other formats to ensure that all behavioral data is correctly aligned in chronological order for subsequent analysis.

[0159] Next, user behavior data is categorized into short-term and long-term behavior. Short-term behavior includes browsing and clicking activity within the past week, while long-term behavior includes purchase and search history within the past month. By performing nonlinear transformations on behavioral data from different time periods, a comprehensive feature vector for each user is generated. For the smart push notification group, a dynamic purchase intention prediction model is constructed based on these comprehensive feature vectors. Through a weighted analysis of short-term and long-term behavior, the model predicts the probability of a user purchasing different products.

[0160] Ad content is generated based on a list of recommended products, taking into account the user's device type, access time, and website type to ensure personalized ad content. During ad push, we continuously collect data on user interaction with ads and dynamically optimize our purchase intent prediction model to ensure the relevance and real-time nature of push content.

[0161] The details are shown in Table 1 below:

[0162] Table 1 Comparison of advertising push effects

[0163]

[0164]

[0165] Analyzing the data in the table above clearly demonstrates that intelligent ad push significantly outperforms traditional push methods in terms of click-through rate, conversion rate, user dwell time, and purchase success rate. For example, the average click-through rate for the intelligent push group reached 9.77%, significantly higher than the 2.87% for the traditional push group. The purchase success rate also increased from the traditional 1.13% to 4.87%. These data demonstrate that intelligent push significantly improves ad effectiveness and user engagement by accurately predicting user purchase intent and delivering personalized ads.

[0166] The AI-based internet advertising and marketing method of the present invention not only effectively improves the click-through rate and conversion rate of advertisements, but also significantly increases the length of time users spend on ad pages and the success rate of purchases, thereby achieving more accurate ad push and higher user engagement. Moreover, by dynamically predicting user purchase intentions and continuously optimizing models, advertising content can be more personalized and meet user needs in real time and efficiently. This demonstrates the innovative and practical value of the present invention in improving advertising accuracy and user experience.

[0167] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An artificial intelligence-based Internet advertising and marketing method, characterized by: include, Collect user behavior data in real time through the Internet, pre-process it, extract user behavior features, and fuse them into a comprehensive feature vector; Build a dynamic prediction model for purchase intention, and predict the user's purchase probability of the product based on the comprehensive feature vector; Generate a product recommendation list based on the user's purchase probability of the product; Generate personalized advertising content based on the product recommendation list and push personalized advertising content to users based on their network usage scenarios; During the ad push process, we continuously collect data on user interaction with personalized ad content to optimize the purchase intention dynamic prediction model. The construction of the purchase intention dynamic prediction model predicts the user's purchase probability of the product based on the comprehensive feature vector. The specific steps are as follows: Through hierarchical behavior modeling, the purchase intention dynamic prediction model is divided into short-term behavior evaluation layer and long-term behavior evaluation layer; The short-term behavior evaluation layer uses a similarity weighting mechanism based on a Gaussian kernel. By comparing the difference between the current feature and the neighboring features, it calculates the weight and performs a weighted summation of the neighboring features. After the ReLU activation function is applied, the short-term behavior features are extracted. The long-term behavior evaluation layer uses MemoryNetwork to embed users' long-term behaviors into memory units. Through a query mechanism, it selectively extracts and aggregates long-term behavior features related to users' purchase intentions. Using a gating mechanism, the purchase intention prediction model dynamically adjusts the emphasis on short-term and long-term behaviors. When users show impulse buying, the gating mechanism automatically increases the focus on short-term behaviors. When user behavior is stable, the gating mechanism pays more attention to the impact of long-term behaviors. The short-term behavior evaluation layer, the long-term behavior evaluation layer, and the gating mechanism are integrated through the gating mechanism and nonlinear fusion to form a dynamic prediction model for purchase intention. The comprehensive feature vector is input into the purchase intention dynamic prediction model to predict the user's purchase probability of the product.

2. The artificial intelligence-based Internet advertising and marketing method according to claim 1, characterized in that: The user's behavioral data includes the user's browsing history, search keywords, purchase history, click behavior and social media interactions; The pre-processing of user behavior data is specifically as follows: Clean user behavior data by removing invalid data, correcting erroneous data, and filling missing values; Use hashing algorithms to identify duplicate user behavior records and delete multiple occurrences of the same data to avoid data redundancy. Filter outliers and noise data through denoising; Through standardization, the timestamps in different user behavior data are converted into a unified format.

3. The artificial intelligence-based Internet advertising and marketing method according to claim 2, characterized in that: Extract user behavior features. The specific steps are as follows: Group user behavior data by time and divide it into different categories according to behavior type; For each type of behavioral data, extract the user's behavior frequency within a specific time range; By tracking page events, we can extract the duration and interaction depth of each user behavior; Extract behavioral sequence features by analyzing the order in which users' behaviors occur; Based on nonlinear transformation and feature product, various user behavior features are processed through different linear transformations, and a comprehensive feature vector is generated through the product interaction between features. The expression is: Among them, F is the comprehensive feature vector, f i represents the behavior characteristics of the i-th category, W i represents the weight matrix for linear transformation of the i-th type behavior feature vector, n represents the total number of user behavior features, σ is the nonlinear activation function, b i It is the bias term when performing linear transformation on the behavioral characteristics of the i-th category.

4. The artificial intelligence-based Internet advertising and marketing method according to claim 3, characterized in that: The feature of extracting short-term behavior is expressed as follows: Among them, Z s represents the short-term behavior characteristics of the user, F is the comprehensive feature vector, and F x represents the xth neighborhood feature in the comprehensive feature vector F, μ is the standard deviation of the Gaussian kernel, b is the bias term, k is the total number of short-term behavior feature vectors, and x is the index of the neighborhood feature; The query mechanism selectively extracts and aggregates long-term behavioral features related to user purchase intentions, expressed as: Among them, Z l Represents the long-term behavioral characteristics of users, h j represents the jth key vector, M j represents the j-th key vector h j The corresponding memory unit, W q Represents the weight matrix used by the user to map the comprehensive feature vector F to the query vector; The purchase intention dynamic prediction model pays attention to short-term and long-term behaviors by adjusting the gating signal in the gating mechanism, which is expressed as: Where g represents the gating signal, σ is the nonlinear activation function, and ∈ represents the numerical offset; The predicted probability of a user purchasing a product is expressed as: y k =Sigmoid(W o ·(g·tanh(Z s,k )+(1-g)·tanh(Z l,k ))+b o ); Among them, y k represents the probability of the user purchasing the kth item, W o The weight matrix used to linearly transform the gated feature combination, Z s,k Represents the short-term behavior characteristics associated with the kth commodity, Z l,k Represents the long-term behavioral characteristics of the k-th commodity.

5. The artificial intelligence-based Internet advertising and marketing method according to claim 4, characterized in that: The specific steps of generating a product recommendation list based on the user's purchase probability of the product are as follows: According to the user's purchase probability y for each product k , sort all products in descending order, select the top N products after sorting, and generate a preliminary product recommendation list R; Based on the user's historical behavior data, calculate the behavioral similarity between the current user and other users; Based on the similarity between the current user and other users, select the M users with the highest similarity to the current user as the similar user set U; Based on the similar user set U, calculate the collaborative filtering score of similar users for product k; The probability y of the user purchasing the kth item k and collaborative filtering score r CF,k Combined, a new sorting index is generated, the expression is: S k =λ·y k +(1-λ)·r CF,k ; Among them, r CF,k represents the collaborative filtering score of similar users for product k, and λ is the purchase probability y of the balanced user for the kth product k and collaborative filtering score r CF,k The weight coefficient, S k It is a new ranking index, CF stands for collaborative filtering; According to the new ranking index S k The preliminary product recommendation list R is optimized to generate the final product recommendation list R'.

6. The artificial intelligence-based Internet advertising and marketing method according to claim 5, characterized in that: The personalized advertising content is generated based on the product recommendation list, and the personalized advertising content is pushed to the user according to the user's network usage scenario. The specific steps are as follows: Based on the user's current network usage and scenario, the ad display format is selected based on the device type, access time period, and visited website type, and personalized ad content is generated for each product based on the recommended product list; Based on the user's historical interests and behavior data, analyze the product categories that the user is most interested in, and prioritize pushing advertisements related to the user's historical interests and behavior data.

7. The artificial intelligence-based Internet advertising and marketing method according to claim 6, characterized in that: During the ad push process, the user's interaction data with personalized ad content is continuously collected to optimize the purchase intention dynamic prediction model. The specific steps are as follows: During the ad push process, all interaction data between users and ads is monitored and collected in real time; Use the collected user interaction data to update the user's behavior characteristics in real time, integrate the updated behavior characteristics with the historical behavior characteristics, and optimize the comprehensive feature vector F; Based on the optimized comprehensive feature vector F', the purchase intention dynamic prediction model is optimized.

8. An artificial intelligence-based Internet advertising and marketing system, based on the artificial intelligence-based Internet advertising and marketing method according to any one of claims 1 to 7, characterized in that: Including comprehensive feature vector generation module, purchase probability prediction module, recommendation list generation module, advertising push module and model optimization module; The comprehensive feature vector generation module is used to collect user behavior data in real time through the Internet, pre-process it, extract user behavior features, and fuse them into a comprehensive feature vector; The purchase probability prediction module is used to build a dynamic prediction model for purchase intention and predict the user's purchase probability of the product based on the comprehensive feature vector; The recommendation list generation module is used to generate a product recommendation list based on the user's purchase probability of the product; Advertisement push module, used to generate personalized advertising content based on the product recommendation list and push personalized advertising content to users according to their network usage scenarios; The model optimization module is used to continuously collect data on users' interactions with personalized advertising content during the advertising push process, and optimize the dynamic prediction model for purchase intention.

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 artificial intelligence-based Internet advertising and marketing 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 artificial intelligence-based Internet advertising and marketing method according to any one of claims 1 to 7 are implemented.

Images