Tourism advertisement marketing system based on big data

Abstract

The invention discloses a tourism advertisement marketing system based on big data, and relates to the field of advertisement putting, and the system comprises the following components: an intelligent putting and social promotion module which accurately puts an advertisement to a target audience according to an analysis result of a user relation network, and simultaneously puts the advertisement to the target audience through sharing, forwarding and interaction functions of a social media platform; according to the system, a user can be guided to participate in propagation and promotion of advertisements, the system can also adjust a putting strategy in real time according to feedback and interaction data of the user, the propagation effect and conversion rate of the advertisements are improved, and through a reinforcement learning algorithm adopted by the intelligent putting and social promotion module, the characteristics of social media are fully utilized; through sharing, forwarding and interaction functions, the advertisement can be quickly spread in the user relation network, so that the spreading range of the advertisement can be expanded, the number of potential customers can be increased, the credibility and persuasion of the advertisement can be improved, and the advertisement can be more easily trusted and recognized by other users.

Description

Technical Field

[0001] The present invention relates to the field of advertising, and in particular to a tourism advertising marketing system based on big data. Background Art

[0002] With the rapid development of Internet technology and the widespread popularity of social media, social media platforms have become an important channel for people to obtain information, communicate and interact. In the tourism industry, social media has become an important platform for promoting tourism products and attracting potential tourists. By deeply mining and analyzing user behavior data on social media platforms, we can reveal the connections and interaction patterns between users and discover potential target audiences and interest groups.

[0003] However, the existing tourism advertising and marketing system mainly relies on traditional advertising channels, such as search engines, television, and newspapers, and lacks in-depth analysis and utilization of social media user relationship networks. Due to the large number of users on social media platforms and the complex user relationships, it is difficult to achieve accurate advertising reach and effective dissemination by relying solely on simple delivery strategies. In addition, the existing advertising promotion system often lacks interaction and feedback mechanisms with users, and is unable to timely understand users' attitudes and reactions to advertising, making it impossible to accurately evaluate and optimize advertising effects.

[0004] Therefore, how to develop an intelligent social promotion system for tourism advertising based on big data and social media user relationship networks has become an important direction for the development of current advertising marketing. However, existing advertising promotion systems often lack interaction and feedback mechanisms with users, and are unable to timely understand users' attitudes and reactions to advertisements, and thus are unable to accurately evaluate and optimize advertising effects. Therefore, the development of an intelligent social promotion system for tourism advertising based on big data and social media user relationship networks has important practical significance and application value. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a tourism advertising and marketing system based on big data. It can make full use of the user relationship network of the social media platform to achieve accurate advertising delivery and social promotion, improve advertising exposure and conversion rate, increase the number of potential customers, and enhance the marketing effect and user experience of the tourism industry.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a tourism advertising and marketing system, characterized in that the system includes the following components:

[0007] User relationship network construction module: Through access to the API interface or authorization method of the social media platform, obtain the user's basic information, follow list, fan list and interaction information between users, use this data to build a user relationship network, analyze the association and interaction behavior between users, and provide accurate target audiences for subsequent advertising promotion;

[0008] Advertising content planning and generation module: Based on the characteristics of tourism products and the needs of target audiences, combined with big data processing technology, analyze users' interests, preferences and consumption behaviors, formulate personalized advertising content, and generate various forms of advertising materials according to different advertising purposes and delivery channels;

[0009] Intelligent delivery and social promotion module: Based on the analysis results of the user relationship network, the advertisements are accurately delivered to the target audience. At the same time, through the sharing, forwarding and interactive functions of the social media platform, users are guided to participate in the dissemination and promotion of advertisements. The system can also adjust the delivery strategy in real time according to user feedback and interactive data to improve the dissemination effect and conversion rate of advertisements.

[0010] Effect evaluation and optimization module: By collecting and analyzing data after advertising, including click-through rate, conversion rate, and user feedback, the advertising effect is quantitatively evaluated. At the same time, based on the evaluation results, the advertising content and delivery strategy are optimized and adjusted to improve the credibility and persuasiveness of the advertisement.

[0011] Furthermore, the specific steps of the user relationship network construction module are:

[0012] (1) Data acquisition: obtaining users’ basic information, follow lists, fan lists, and interactive information between users through the API interface or authorization method of the social media platform;

[0013] (2) Data preprocessing and network construction: cleaning and organizing the acquired data, removing duplicate, invalid or sensitive information, and constructing a user relationship network diagram based on the interactive behavior between users.

[0014] Furthermore, the advertising content planning and generation module includes the following specific steps:

[0015] (1) User portrait construction: Build user portraits based on basic user information and interaction data, including interests and consumption habits;

[0016] (2) Advertising content planning and material generation: Based on the characteristics of tourism products and user portraits, plan advertising copy, pictures or videos, and use graphics processing and natural language generation technology to generate advertising materials.

[0017] Furthermore, the smart delivery and social promotion module has the following specific steps:

[0018] (1) Target audience screening: Based on the user relationship network and target user profile, screen out the target audience that is most likely to be interested;

[0019] (2) Advertising and social promotion: Based on the screening results, advertisements are placed on the target audience’s social media platforms to encourage users to share and forward the advertisements, thereby expanding the advertising influence through social interaction.

[0020] Furthermore, the data analysis module specifically comprises the following steps:

[0021] (1) Data collection and evaluation: Collect click, conversion, and sharing data after advertising is placed, and evaluate the effectiveness of advertising based on the collected data;

[0022] (2) Optimization and adjustment: Adjust the advertising delivery strategy and generated content based on the evaluation results.

[0023] Furthermore, the user relationship network construction module constructs a user relationship network diagram by using the adjacency matrix method. Assuming there are N users, an N×N adjacency matrix A is constructed, where A[i][j] represents the relationship strength between user i and user j. Specifically, for any two users i and j, if they have interactive behaviors within a certain period of time, the value of A[i][j] is the number of their interactions; conversely, if they have no interactive behaviors, the value of A[i][j] is 0. In this way, the adjacency matrix A fully represents the association relationship between users, and the formula is: Through the adjacency matrix A, the system can quantify the strength of association between users and provide data support for subsequent precise advertising delivery. Then, the system calculates the influence of users in the network based on the PageRank algorithm. The specific formula is: Among them, PR(A) represents the PageRank value of user A, d is the damping factor, which is usually 0.85, Ti is the page pointing to user A (that is, the users who follow user A), and C(Ti) is the total number of outbound links of page Ti (that is, the total number of users followed by user Ti). By calculating the PageRank value of each user, the system can screen out target audiences with high influence for advertising delivery. At the same time, by continuously optimizing the delivery strategy and content matching algorithm, the system can further improve the pertinence and effectiveness of advertising to meet the personalized needs of users.

[0024] Furthermore, the advertising content planning and generation module uses a deep learning model to generate image advertising materials. The system constructs a data set and annotates corresponding advertising labels based on the characteristics of tourism products and user portraits, and uses a deep learning model for training. During the training process, a gradient descent optimization algorithm is used to update the model weights. The specific formula is as follows: Among them, w represents the model weight, α is the learning rate, It is the gradient of the loss function J(w) with respect to w. Through multiple iterative training, the model can learn the mapping relationship from user portrait to advertising content. Finally, the system can input specific user portrait information and generate advertising content that meets the preferences of the target user group through the model.

[0025] Furthermore, the intelligent delivery and social promotion module adopts a reinforcement learning algorithm to optimize the advertising delivery strategy. The state space, action space and reward function are defined by the system. The state space includes user characteristics and advertising characteristics, the action space includes different advertising delivery strategies, and the reward function is defined according to the advertising effect. The reward function formula is defined as: R(s,a)=CTR(s,a) * CPC(s,a), where R(s,a) represents the expected revenue of the advertising content (s) on the target user group, (CTR(s,a)) represents the click-through rate of the advertising content (s) on the target user group, and (CPC(s,a)) represents the cost per click of the advertising content (s). Then the system initializes the state value function V(s) and starts the iterative optimization process. In each iteration, the system selects and executes actions based on the current state, observes the rewards obtained and the next state, and updates the state value function. The specific formula is: V(s) = V(s) + α × [R(s,a) + γ × V(s′) - V(s)], where V(s) represents the value of state s, α is the learning rate, R(s,a) represents the reward obtained by taking action a in state s, γ is the discount factor, and V(s′) represents the value of the next state s'. By continuously iterating and updating the state value function, the system can find the optimal advertising delivery strategy and maximize the advertising effect.

[0026] Furthermore, the system also includes an advertising delivery optimization module for automatically adjusting the advertising delivery strategy, including delivery time, delivery channel, and delivery frequency, according to the advertising effect prediction results and real-time feedback data, so as to improve the advertising dissemination effect and conversion rate.

[0027] Furthermore, the system also includes a user feedback collection module for collecting user feedback data on advertisements, including user evaluations, comments, and suggestions, so as to understand user satisfaction with advertisements and improvement needs, and provide feedback basis for the optimization of advertisement content and delivery strategies.

[0028] Compared with the existing technology, the tourism advertising and marketing system based on big data has the following beneficial effects:

[0029] 1. The present invention uses a reinforcement learning algorithm adopted by the intelligent delivery and social promotion module to fully utilize the characteristics of social media. Through sharing, forwarding and interactive functions, advertisements can be quickly spread in user relationship networks, which can not only expand the dissemination range of advertisements and increase the number of potential customers, but also improve the credibility and persuasiveness of advertisements, making it easier to gain the trust and recognition of other users.

[0030] 2. The present invention can collect and analyze user feedback and interaction data in real time through the intelligent delivery and social promotion module, adjust the delivery strategy based on these data, optimize the advertising content, make advertising promotion more flexible and efficient, and better adapt to market changes and changes in user needs. At the same time, it combines with the social media user relationship network for in-depth analysis, and can more accurately identify the target audience, thereby achieving precise advertising delivery.

[0031] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 This is a process operation diagram of the tourism advertising and marketing system based on big data. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Example 1: Intelligent delivery of tourism advertisements based on user relationship networks

[0036] In this embodiment, the system first collects user interaction behavior data from social media platforms through a user relationship network construction module. These data include attention, forwarding, and comments between users, as well as travel-related content posted by users. The collected raw data needs to be cleaned and sorted to remove duplicate, invalid, or noisy data to ensure the accuracy and reliability of the data. The user relationship network diagram is constructed using the adjacency matrix method. The elements A[i][j] of the adjacency matrix A are calculated according to the following mathematical formula:

[0037]

[0038] Through the adjacency matrix A, the system can quantify the strength of association between users and provide data support for subsequent precise advertising delivery. Then, the system calculates the influence of users in the network based on the PageRank algorithm. The specific formula is as follows:

[0039]

[0040] Among them, PR(A) represents the PageRank value of user A, d is the damping factor, which is usually 0.85, Ti is the page pointing to user A (that is, the users who follow user A), and C(Ti) is the total number of outbound links of page Ti (that is, the total number of users followed by user Ti). By calculating the PageRank value of each user, the system can screen out target audiences with higher influence for advertising.

[0041] This embodiment achieves accurate delivery of tourism advertisements by constructing a user relationship network and using a network analysis algorithm to screen out the target audience. This not only improves the efficiency and effectiveness of advertising delivery, but also reduces advertising costs, bringing greater commercial value to tourism companies. At the same time, by continuously optimizing delivery strategies and content matching algorithms, the system can further improve the pertinence and effectiveness of advertisements and meet the personalized needs of users.

[0042] Example 2

[0043] In this embodiment, the main focus is on the functional improvement of the advertising content planning and generation module, especially the use of deep learning technology to generate image advertising materials. The system collects relevant information from historical data and real-time data, including descriptions, pictures, prices of tourism products, and basic information, interest preferences, and consumption records of users. Based on this information, the system constructs a data set containing rich features and annotates each data sample with corresponding advertising labels, such as style, emotional tendency, and target user group. The system uses a deep learning model for training and uses a convolutional neural network (CNN) as the main model structure. During the training process, a gradient descent optimization algorithm is used to update the weight of the model. The specific mathematical formula is:

[0044]

[0045] Among them, w represents the model weight, α is the learning rate, It is the gradient of the loss function J(w) with respect to w. In each iteration, the system first calculates the loss function value of the model on the training data under the current weight, and then calculates the gradient of the loss function with respect to the weight, and finally updates the weight according to the learning rate and gradient. Through multiple iterations, the model gradually learns the mapping relationship from user portrait to advertising content. When the model training is completed, the system can receive new user portrait information as input, and generate advertising content that meets the preferences of the target user group through the model. Specifically, the system first extracts key features such as age, gender, and interest preferences based on user portrait information, and then inputs these features into the trained deep learning model. The model generates corresponding advertising content, such as pictures and text descriptions, based on the learned mapping relationship. In this way, the system can generate personalized advertising content based on different user portraits, thereby improving the pertinence and attractiveness of advertising. At the same time, due to the strong learning and generalization capabilities of deep learning models, the system can also continuously update the model based on real-time data to adapt to changing market demands and user preferences.

[0046] In summary, this embodiment achieves personalized and intelligent generation of advertising content by using deep learning technology to generate advertising content, and provides new ideas and methods for advertising promotion in the tourism industry.

[0047] Example 3

[0048] In this embodiment, the focus is mainly on the intelligent delivery and social promotion modules. By introducing the reinforcement learning algorithm, the dynamic optimization of the advertising delivery strategy is realized to improve the advertising effect and user experience. By constructing a reinforcement learning framework suitable for the advertising delivery strategy, the framework includes the definition of state space, action space and reward function. The state space is used to describe various situations that may be encountered during the advertising delivery process, including user characteristics, advertising characteristics and historical delivery data. The action space defines the delivery strategies that the system can take under a given state, such as delivery time, delivery frequency, and delivery channel. Different delivery strategies will have different effects on the advertising effect. Therefore, the design of the action space needs to fully consider various possible situations. The reward function is used to evaluate the quality of the advertising delivery strategy. It is defined according to the advertising effect. The formula is defined as:

[0049] R(s,a)=CTR(s,a) * CPC(s,a)

[0050] , where R(s,a) represents the expected revenue of the advertising content (s) on the target user group, (CTR(s,a)) represents the click-through rate of the advertising content (s) on the target user group, and (CPC(s,a)) represents the cost per click of the advertising content (s). After that, the system initializes the state value function V(s) and starts the iterative optimization process. In each iteration, the system selects and executes actions based on the current state, observes the rewards obtained and the next state, and updates the state value function. The specific formula is:

[0051] V(s)=V(s)+α×[R(s,a)+γ×V(s′)-V(s)]

[0052] , where V(s) represents the value of state s, α is the learning rate, R(s,a) represents the reward for taking action a in state s, γ is the discount factor, and V(s′) represents the value of the next state s′. By continuously iteratively updating the state value function, the system can find the optimal advertising delivery strategy and maximize the advertising effect.

[0053] This embodiment implements personalized advertising delivery strategies for different users and different advertising features by adopting an intelligent advertising delivery strategy optimization method based on reinforcement learning. By continuously iterating and optimizing the state value function, the system can find the optimal advertising delivery strategy, improve advertising effects and reduce delivery costs.

[0054] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A tourism advertising and marketing system based on big data, characterized by: The system consists of the following components: User relationship network construction module: Through access to the API interface or authorization method of the social media platform, obtain the user's basic information, follow list, fan list and interaction information between users, use this data to build a user relationship network, analyze the association and interaction behavior between users, and provide accurate target audiences for subsequent advertising promotion; Advertising content planning and generation module: Based on the characteristics of tourism products and the needs of target audiences, combined with big data processing technology, analyze users' interests, preferences and consumption behaviors, formulate personalized advertising content, and generate various forms of advertising materials according to different advertising purposes and delivery channels; Intelligent delivery and social promotion module: Based on the analysis results of the user relationship network, the advertisements are accurately delivered to the target audience. At the same time, through the sharing, forwarding and interactive functions of the social media platform, users are guided to participate in the dissemination and promotion of advertisements. The system can also adjust the delivery strategy in real time according to user feedback and interactive data to improve the dissemination effect and conversion rate of advertisements. Effect evaluation and optimization module: By collecting and analyzing data after advertising, including click-through rate, conversion rate, and user feedback, the advertising effect is quantitatively evaluated. At the same time, based on the evaluation results, the advertising content and delivery strategy are optimized and adjusted to improve the credibility and persuasiveness of the advertisement.

2. The tourism advertising and marketing system based on big data according to claim 1 is characterized in that: The specific steps of the user relationship network construction module are as follows: (1) Data acquisition: obtaining users’ basic information, follow lists, fan lists, and interactive information between users through the API interface or authorization method of the social media platform; (2) Data preprocessing and network construction: cleaning and organizing the acquired data, removing duplicate, invalid or sensitive information, and constructing a user relationship network diagram based on the interactive behavior between users.

3. The tourism advertising and marketing system based on big data according to claim 1 is characterized in that: The specific steps of the advertising content planning and generation module are as follows: (1) User portrait construction: Build user portraits based on basic user information and interaction data, including interests and consumption habits; (2) Advertising content planning and material generation: Based on the characteristics of tourism products and user portraits, plan advertising copy, pictures or videos, and use graphics processing and natural language generation technology to generate advertising materials.

4. The tourism advertising and marketing system based on big data according to claim 1 is characterized in that: The specific steps of the intelligent delivery and social promotion module are as follows: (1) Target audience screening: Based on the user relationship network and target user profile, screen out the target audience that is most likely to be interested; (2) Advertising and social promotion: Based on the screening results, advertisements are placed on the target audience’s social media platforms to encourage users to share and forward the advertisements, thereby expanding the advertising influence through social interaction.

5. The tourism advertising and marketing system based on big data according to claim 1 is characterized in that: The specific steps of the effect evaluation and optimization module are as follows: (1) Data collection and evaluation: Collect click, conversion, and sharing data after advertising is placed, and evaluate the effectiveness of advertising based on the collected data; (2) Optimization and adjustment: Adjust the advertising delivery strategy and generated content based on the evaluation results.

6. The tourism advertising and marketing system based on big data according to claim 3 is characterized in that: The user relationship network construction module constructs a user relationship network diagram by using the adjacency matrix method. Assuming there are N users, an N×N adjacency matrix A is constructed, where A[i][j] represents the relationship strength between user i and user j. Specifically, for any two users i and j, if they have interactive behaviors within a certain period of time, the value of A[i][j] is the number of their interactions; conversely, if they have no interactive behaviors, the value of A[i][j] is 0. In this way, the adjacency matrix A fully represents the association relationship between users. The formula is: Through the adjacency matrix A, the system can quantify the strength of association between users and provide data support for subsequent precise advertising delivery. Then the system calculates the user's influence in the network based on the PageRank algorithm. The specific formula is: PR(A) = (1-d) + d∑ T i∈ Pointing to A's user Among them, PR(A) represents the PageRank value of user A, d is the damping factor, which is usually 0.85, Ti is the page pointing to user A (that is, the users who follow user A), and C(Ti) is the total number of outbound links of page Ti (that is, the total number of users followed by user Ti). By calculating the PageRank value of each user, the system can screen out target audiences with high influence for advertising delivery. At the same time, by continuously optimizing the delivery strategy and content matching algorithm, the system can further improve the pertinence and effectiveness of advertising to meet the personalized needs of users.

7. The tourism advertising and marketing system based on big data according to claim 3 is characterized in that: The advertising content planning and generation module uses a deep learning model to generate image advertising materials. The system constructs a data set and annotates corresponding advertising labels based on the characteristics of tourism products and user portraits, and uses a deep learning model for training. During the training process, a gradient descent optimization algorithm is used to update the model weights. The specific formula is as follows: Among them, w represents the model weight, α is the learning rate, It is the gradient of the loss function J(w) with respect to w. Through multiple iterative training, the model can learn the mapping relationship from user portrait to advertising content. Finally, the system can input specific user portrait information and generate advertising content that meets the preferences of the target user group through the model.

8. The tourism advertising and marketing system based on big data according to claim 5 is characterized in that: The intelligent delivery and social promotion module adopts reinforcement learning algorithm to optimize the advertising delivery strategy. The state space, action space and reward function are defined by the system. The state space includes user characteristics and advertising characteristics, the action space includes different advertising delivery strategies, and the reward function is defined according to the advertising effect. The reward function formula is defined as: R(s,a)=CTR(s,a) * CPC(s,a), where R(s,a) represents the expected revenue of the advertising content (s) on the target user group, (CTR(s,a)) represents the click-through rate of the advertising content (s) on the target user group, and (CPC(s,a)) represents the cost per click of the advertising content (s). Then the system initializes the state value function V(s) and starts the iterative optimization process. In each iteration, the system selects and executes actions based on the current state, observes the rewards obtained and the next state, and updates the state value function. The specific formula is: V(s) = V(s) + α × [R(s,a) + γ × V(s′) - V(s)], where V(s) represents the value of state s, α is the learning rate, R(s,a) represents the reward obtained by taking action a in state s, γ is the discount factor, and V(s′) represents the value of the next state s'. By continuously iterating and updating the state value function, the system can find the optimal advertising delivery strategy and maximize the advertising effect.

9. The tourism advertising and marketing system based on big data according to claim 1 is characterized in that: The system also includes an advertising delivery optimization module, which is used to automatically adjust the advertising delivery strategy, including delivery time, delivery channel, and delivery frequency, according to the advertising effect prediction results and real-time feedback data, so as to improve the advertising dissemination effect and conversion rate.

10. The tourism advertising and marketing system based on big data according to claim 1 is characterized in that: The system also includes a user feedback collection module for collecting user feedback data on advertisements, including user evaluations, comments, and suggestions, so as to understand user satisfaction with advertisements and improvement needs, and provide feedback basis for optimization of advertisement content and delivery strategies.

Images