Smart tourism guide data pushing system based on cloud platform
By integrating cloud platform, big data analysis and VR/AR technology into the travel guide system, personalized virtual travel scenarios and augmented reality guide content is solved, and the lack of personalization, interactivity and information updates of traditional guide systems are solved. The problem of this issue has achieved efficient personalized information push and immersive experience, improving the quality of tourism services and tourists' satisfaction.
Patent Information
- Application Number
- CN202411053298.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-11-29
AI Technical Summary
The traditional tourism guide system lacks personalized recommendation functions, lack of interaction, untimely update of information and single guide content, which cannot meet tourists' needs for in-depth experience and interactive exploration. The existing VR/AR technology is in the tourism guide system. The application of the application has the problems of complex technology implementation, high equipment cost, insufficient integrated cloud platform and big data analysis.
A smart travel guide data push system based on the cloud platform, integrates cloud platform and big data analysis technology to collect and analyze tourists' habits, interests and consumption capabilities in real time, and combines VR/AR technology to provide personalized virtual tourism scenarios and enhancements. Realistic guide content, design friendly user interface to support multiple interaction methods, and establish strict data encryption and access control mechanisms.
It realizes personalized and customized tourism information push, improves tourists' immersive experience and interactivity, enhances the attractiveness and educational significance of tourism, optimizes tourism resource allocation and service efficiency, and ensures that the information received by tourists matches the needs. , improves tourist satisfaction.
Smart Images

Figure CN119048291A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart tourism guide technology, and in particular to a cloud platform-based smart tourism guide data push system. Background Art
[0002] With the vigorous development of the tourism industry and the rapid advancement of information technology, smart tourism has become a new development trend. Smart tourism provides tourists with more convenient, rich and personalized tourism services by integrating various information technology means. Among them, virtual reality (VR) and augmented reality (AR) technologies, as emerging information technologies, have been widely used in the tourism industry with their unique immersive experience advantages. These technologies can simulate real scenes and provide highly interactive and interesting guided tours, enabling tourists to have a deeper understanding of the culture, history and customs of the tourist destinations. Cloud platforms, as the core infrastructure of modern information technology, have powerful data processing and storage capabilities, providing solid technical support for smart tourism. At the same time, cloud platforms can also realize the sharing and optimal allocation of tourism resources, improving the operational efficiency and service quality of the tourism industry.
[0003] At present, although the traditional tourist guide system has met the basic needs of tourists to a certain extent, it still has obvious shortcomings in the face of the growing personalized needs. First, the traditional guide system lacks personalized recommendation functions and cannot provide customized travel information based on tourists' interests, preferences and needs. Secondly, the traditional guide system lacks interactivity, and tourists can only passively accept the guide information and cannot actively explore and interact. In addition, the traditional guide system also has problems such as untimely information updates and single guide content, which cannot meet tourists' needs for in-depth experience and interactive exploration.
[0004] In the existing technology, although there have been some attempts to apply VR / AR technology to the practice of tourist guide systems, there are often problems such as complex technical implementation, high equipment cost and inconvenient operation. These disadvantages limit the widespread application of VR / AR technology in tourist guide systems. In addition, the existing technology also has shortcomings in integrating cloud platforms, big data analysis and VR / AR technology, and cannot realize the intelligent push of tourist information and interactive experience. These problems not only affect the tourists' travel experience, but also restrict the intelligent development of the tourism industry. Therefore, the development of a smart tourist guide data push system based on a cloud platform to realize the personalized customization and interactive experience of tourist information has important practical significance and application value. Summary of the Invention
[0005] The purpose of this invention is to make up for the shortcomings of the existing technology and provide a smart tourism guide data push system based on a cloud platform. It can collect and analyze tourists' sightseeing habits, interest preferences and consumption capacity in real time by integrating the cloud platform with big data analysis technology, and then provide tourists with highly personalized tourism information push, and use VR / AR technology to create high-quality virtual tourism scenes and augmented reality guide content to provide tourists with an immersive tourism experience.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a cloud platform-based smart tourism guide data push system, characterized in that the system includes the following components:
[0007] Cloud platform architecture and data processing: Build a cloud-based data processing and distribution center to collect and analyze tourism data. Conduct in-depth data mining to analyze tourists' travel habits, interests, preferences, and spending power, providing accurate data support for personalized push notifications.
[0008] Personalized data push: Based on tourists' historical behavior data and social network data, we build personalized profiles of tourists and integrate real-time push algorithms to push customized travel information in real time based on factors such as the tourists' current location, tour time, and weather conditions.
[0009] VR / AR content generation and push: Integrating VR / AR modules, leveraging 3D modeling and real-scene scanning technologies, creates high-quality virtual tourism scenes and augmented reality guided tours. Visitors can experience interactive features such as virtual tours, historical re-enactments, and information overlays through mobile devices and designated wearable devices.
[0010] Interactive experience design: Design a user-friendly interface that supports multiple interaction methods such as voice commands and gesture control to ensure that visitors can easily operate VR / AR functions and enhance the user experience;
[0011] Security and privacy protection mechanism: Establish strict data encryption and access control mechanisms to ensure the security of visitors' personal information while complying with relevant privacy protection laws and regulations.
[0012] Furthermore, the cloud platform architecture and data processing collects tourist behavior data, namely, tour routes, duration of stay, attraction traffic information, and weather forecast data, through mobile social media and online booking platforms. The collected data is deeply mined using big data analysis technology. The K-means clustering algorithm is used to classify tourist behavior patterns. K data points are randomly selected as initial cluster centers, and the Euclidean distance is used to calculate the distance between each point in the data set and the K cluster centers, namely: P is the data point, C is the cluster center, n is the number of features, p i and c i are the values of the data point and cluster center on the i-th feature, and assign them to the cluster center closest to it: C is the new cluster center, m is the number of data points in the cluster, and p i is the coordinate of the i-th data point in the cluster. By grouping a large amount of tourist behavior data, including the types of attractions visited, length of stay, and consumption habits, into different clusters, the system can better understand tourists' preferences and behavior patterns, thereby identifying tourist groups with similar travel habits and interest preferences.
[0013] Furthermore, the personalized data push uses K-means to help segment user groups, and further realizes personalized information push on this basis through collaborative filtering. By analyzing the user's past behavior ratings and browsing history, it predicts the project attractions and activities that the user is interested in but has not yet directly interacted with. Through collaborative filtering, the collected user browsing history, purchase history and rating data are used to calculate the similarity between users using the cosine similarity algorithm, that is: u and v are users, I uv is the set of items evaluated by both user u and user v, r ui and r vi These are the ratings of user u and user v on item i. Based on user similarity and historical ratings of similar users, the item with the highest rating is predicted as the recommendation list.
[0014] Furthermore, the specific steps of the personalized data push are:
[0015] (1) Data reception and processing: Receive historical tourist data, visited attractions, length of stay, social media behavior, shared content, and basic demographic information such as age and gender collected by the cloud platform architecture and data processing, and process the received data to ensure data quality;
[0016] (2) User portrait construction: Use machine learning algorithms to group users, identify the characteristics of different types of tourists, and combine users' static attributes and dynamic behaviors to build multi-dimensional personalized user portraits;
[0017] (3) Real-time context analysis: monitoring external environmental factors such as tourists’ geographic location, current time, and weather conditions in real time, and using rule engines and context awareness to evaluate the impact of these factors on tourists’ needs;
[0018] (4) Personalized recommendation algorithm: Collaborative filtering is used to calculate the similarity between users, recommending content that similar users like but not yet exposed to the current user. Combining contextual information and user profiles, the recommendation list is adjusted using weighting factors to generate the final personalized push content.
[0019] (5) Push execution and feedback loop: Push personalized content to tourists through APP, SMS and email, and collect tourists' feedback on recommended content, including click-through rate, stay time, and evaluation, to continuously optimize the recommendation algorithm.
[0020] Furthermore, the personalized data push extracts features of tourist attractions, activities, and discount information, including descriptive text, pictures, and videos, and matches them with content features based on the personalized portrait of tourists, such as age, gender, interests, and preferences. The content-based recommendation algorithm uses the term frequency-inverse document frequency TF-IDF statistical method to determine the feature weight of the content. The algorithm formula is: TF-IDF(t,d)=TF(t,d)×IDF(t), where TF(t,d) is the term frequency of term t in document d, and IDF(t) is the inverse document frequency of term t, that is: Where N is the total number of documents, n t is the number of documents containing the term t. Based on the matching results, a content recommendation list that meets the tourists’ interests is generated.
[0021] Furthermore, the personalized data push uses a logistic regression classification algorithm to predict the categories and interest groups of tourists, that is, tourists are divided into different categories such as history and culture enthusiasts, natural scenery fans, and adventure experiencers. Once the tourists are classified, the system pushes relevant tourism information according to the category. The algorithm is implemented as follows: the probability of an event occurring is estimated by fitting the data to a logistic function, and the feature vector x = (x1, x2, ..., x n ) represents various characteristics of tourists, including age, gender, historical ratings, and weight vector w=(w1,w2,…,w n ) and bias term b, logistic regression formula: Calculate the probability that a tourist belongs to a certain category, y = 1 means the tourist belongs to the category, y = 0 means the tourist does not belong to the category. By learning the optimal values of w and b through training data, new tourists are classified and personalized information is pushed. The user's preference for specific content and services is predicted, and the relevant tourism information for the category is pushed.
[0022] Furthermore, the personalized data push utilizes the classification of new tourists and personalized information push, and is used to predict the tourists' interest in tourism products and activities through regression algorithms, and predict the tourists' next behavior, including: which attractions to choose, which activities to participate in, etc., which tourism products to purchase, and help the system push customized tourism information more accurately based on the prediction results. Through the linear regression technology in the regression algorithm, the relationship between the dependent variable target and the independent variable characteristics is studied, and the tourists' interest in tourism products and activities is used as the dependent variable, and the tourists' characteristics are used as the independent variables. The interest level is predicted through linear regression, that is: is the predicted value of the target variable, y is the target variable, and the training data is used to learn the optimal value of the parameter, predict the interest level of new tourists and push personalized information, predict users' ratings of services and expected length of stay, analyze the relationship between user characteristics and corresponding ratings, and optimize user experience.
[0023] Furthermore, the specific steps of generating and pushing VR / AR content are as follows:
[0024] (1) 3D modeling and scene construction: Use 3D modeling software to create a three-dimensional model of the scenic area. According to the actual scene requirements, add textures, materials, and light and shadow effects to the model to simulate the real environment and build a complete virtual tourism scene, including roads, buildings, and vegetation;
[0025] (2) Real scene scanning and data capture: Use laser radar and camera equipment to scan the scenic area in real time, obtain real-world data, process the scanned data, generate point cloud data and three-dimensional models, and combine 3D modeling technology to integrate the real scene scan data with the virtual scene;
[0026] (3) Content production and enhancement: Add multimedia content such as tour guide voice, text description and animation effects to the virtual scene, and use AR technology to overlay virtual information in the tourists' field of vision, including introductions to scenic spots and historical stories, and design interactive elements, clickable buttons, and interactive exhibits;
[0027] (4) Content optimization and testing: Optimize the generated VR / AR content to ensure smooth operation on different devices and network conditions. Collect feedback and make adjustments through internal testing and user testing.
[0028] (5) Content publishing and pushing: Optimized VR / AR content is published on the cloud server. Based on the location, preferences, and visit time of the tourists, the corresponding VR / AR content is pushed to the tourists’ mobile devices and wearable devices through the cloud platform, providing an immersive VR experience and achieving synchronization of perspective and movement through gyroscope and accelerometer data.
[0029] Furthermore, in the VR / AR content generation and push application, linear interpolation is used to make the movement and rotation of objects smoother. When an object moves from one position to another, the intermediate position is calculated through linear interpolation, and the position of the object is updated at each time step to achieve a smooth transition. When creating VR / AR animations, the intermediate frames between key frames are calculated to define the states of the start and end frames, thereby generating a smooth animation effect. The algorithm formula is as follows: (x1, y1) and (x2, y2) are two known data points, x is the estimated x value of the unknown data point, and y is the value obtained by interpolation. In the texture mapping process, linear interpolation is used to calculate the correspondence between texture coordinates and pixel colors to ensure the correct mapping and smooth transition of the texture on the object surface.
[0030] Furthermore, the VR / AR content generation and push uses the Phong lighting model to calculate the light intensity on the surface of the object, thereby generating a rendering effect with a sense of reality and three-dimensionality. The ambient lighting part of the Phong lighting model simulates the effect of non-directional light from the surrounding environment on the object, that is, the ambient lighting I a =k a ·L a The diffuse reflection illumination part is used to simulate the effect of directional light from the light source on the surface of the object. By calculating the angle between the light source direction and the normal of the object surface, and combining the diffuse reflection coefficient and the light source color, the diffuse reflection illumination intensity of the object surface is calculated, that is, the diffuse reflection illumination I d =k d ·L d ·max(0,N·L), the specular illumination part is used to simulate the highlight effect on the surface of the object. By calculating the angle between the light reflection direction vector and the sight direction vector, and combining the specular reflection coefficient and the light source color, the specular illumination intensity of the object surface is calculated, that is, the specular illumination part I s =k s ·L s max(0,R·V) n , k a 、k d 、k s They are the ambient reflection coefficient, diffuse reflection coefficient and specular reflection coefficient, L a , L d , L s They are ambient light color, light source color and specular light source color, N is the surface normal vector of the object, L is the light source direction vector, R is the reflection direction unit vector, V is the observation direction unit vector, and n is the reflection index of specular lighting.
[0031] Compared with the existing technology, this cloud platform-based smart tourism guide data push system has the following beneficial effects:
[0032] 1. This invention integrates cloud platforms, big data analysis, and VR / AR technology. Based on multi-dimensional data such as tourists' real-time location, personal interests, and historical behavior, the system intelligently recommends customized information, namely attractions, activities, and discounts. VR / AR technology is also used to create an immersive tour experience, allowing tourists to enjoy interactive fun while deepening their understanding and appreciation of the culture of the tourist destination. This personalized immersive experience transcends the limitations of traditional guided tours and greatly enhances the appeal and educational significance of tourism.
[0033] 2. The cloud platform data processing center constructed by the present invention can efficiently collect and analyze massive tourism data, and use advanced big data analysis technology to conduct in-depth learning of tourist behavior patterns, thereby achieving more accurate personalized information push. This mechanism not only improves the relevance of information and the timing of push, but also optimizes the allocation of tourism resources, reduces the troubles caused to tourists by information overload, ensures that each tourist can receive tourism information that best matches their needs, and improves service efficiency and tourist satisfaction.
[0034] Other advantages, objects and features of the present invention will be described 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 learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] 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 description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.
[0036] Figure 1 This is a process operation diagram of a smart tourism guide data push system based on a cloud platform.
[0037] Figure 2 This is a flow chart of a smart tourism guide data push system based on a cloud platform. DETAILED DESCRIPTION
[0038] The following is a clear and complete description of the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0039] Example 1
[0040] This embodiment introduces in detail the specific application of a cloud-based smart tourism guide data push system. By combining the cloud platform's powerful data processing capabilities and big data analysis technology with VR / AR technology, it provides an unprecedented personalized tourism experience. It not only intelligently pushes relevant information based on tourists' real-time location, time, weather, and personal interests and preferences, but also uses VR / AR technology to create immersive virtual tours and augmented reality guide content, allowing tourists to deeply interact and immerse themselves in the rich history, culture, and natural landscapes. This personalized immersive experience greatly enhances the appeal and educational significance of tourism, surpassing the limitations of traditional guided tours.
[0041] In its implementation, the system collects real-time tourist behavior data through mobile social media and online booking platforms, including tour routes, duration of stay, traffic information at scenic spots, and weather forecast data. It then uses big data analysis technology to deeply mine this data and employs the K-means clustering algorithm to classify tourist behavior patterns. The system randomly selects K data points as initial cluster centers and calculates the distance between each tourist data point and the cluster center using the Euclidean distance, i.e.: P is the data point, C is the cluster center, n is the number of features, p i and c i are the values of the data point and cluster center on the i-th feature, and assign them to the cluster center closest to it: C is the new cluster center, m is the number of data points in the cluster, and p i is the coordinate of the i-th data point in the cluster, and assigns it to the nearest cluster. By grouping a large amount of data, the system can more accurately identify groups of tourists with similar travel habits and interest preferences, laying the foundation for subsequent personalized push.
[0042] Based on the K-means clustering results, the system uses collaborative filtering algorithms to further refine user groups. By analyzing users' historical behavior scores and browsing history, the system predicts unknown projects, attractions, or activities that users may be interested in. The collaborative filtering algorithm compares the similarities between users (using the cosine similarity algorithm), namely: u and v are users, I uv is the set of items evaluated by both user u and user v, r ui and r viThe system uses the ratings of user u and user v for item i to predict the user's possible preferences. Then, combined with real-time situational analysis (taking into account the tourist's current location, time, and weather), it uses weighting factors to adjust the recommendation list and generate personalized push content that matches the tourist's profile. For example, if a tourist shows a strong interest in history and culture, the system will push information about historical stories or cultural activities of the attraction when he approaches the relevant attraction.
[0043] The system integrates VR / AR modules and uses 3D modeling and real-scene scanning technology to create high-quality virtual tourism scenes and augmented reality guided content. Visitors can experience interactive functions such as virtual tours, historical re-enactments, and information overlays through mobile devices and designated wearable devices. The system pushes relevant VR / AR content based on the visitor's personalized portrait and current location, enhancing the visitor's immersive experience.
[0044] The system is designed with a user-friendly interface that supports multiple interaction methods such as voice commands and gesture control. Visitors can easily operate VR / AR devices and enjoy personalized tourist guide services. At the same time, the system also provides online customer service functions to answer questions encountered by tourists during the tour and provide real-time help and support.
[0045] The system design includes strict data encryption and access control mechanisms to ensure the security of tourists' personal information during transmission and storage. The system complies with relevant privacy protection laws and regulations, anonymizes tourists' personal data and minimizes collection principles to ensure that tourists' privacy is not violated.
[0046] Example 2
[0047] In this embodiment, a cloud-based smart tourism guide data push system is particularly emphasized. The system uses 3D modeling software and real-scene scanning technology to build a realistic virtual tourism scene and push VR guide content of the ruins, allowing tourists to "walk into" the historical scene through mobile devices and experience an interactive journey through time and space.
[0048] First, we selected well-known scenic spots as examples, and constructed detailed three-dimensional models based on the actual layout and characteristics of the scenic spots, including historical sites, natural scenery and characteristic buildings. We added realistic textures and materials to the models, such as bluestone roads, forests with towering ancient trees, and the brick and tile texture of ancient buildings. We also used light and shadow effects to simulate natural lighting in different time periods, such as the soft morning sunlight and the warm afterglow at dusk, to enhance the sense of immersion. We deployed lidar and high-resolution cameras to conduct panoramic scanning in the scenic area, capturing detailed geographic spatial data. Through point cloud data processing and three-dimensional reconstruction technology, we converted the real-world landscape into a digital model, and combined these real data with the previously constructed 3D model to ensure that the virtual scene is highly consistent with the actual environment. For example, we accurately located the position of each tree and each stone in the virtual environment, embedded the tour guide's voice explanation, interactive information boards and dynamic reproduction animations of historical events in the virtual scene, and used AR technology. When tourists use mobile phones or smart glasses to browse the scenic area, they can browse the scenic area through the virtual scene. When viewing real-world landscapes, relevant information is automatically superimposed in the view, such as arrows pointing to ancient monuments, introductions to cultural relics that appear before your eyes, and historical story animations that can be played by touch. Interactive elements are designed, such as explanatory audio that can be heard by clicking on the screen, and the experience of virtually touching the surface texture of ancient buildings. The generated VR / AR content is performance-optimized to ensure smooth operation on different types of mobile devices and network environments, avoiding freezes or delays. Feedback is collected through internal team and small-scale tourist tests, and detailed adjustments are made to loading speed, screen smoothness, and interactive experience. Using the real-time location information of tourists, combined with their interests, preferences, and tour time, the cloud platform intelligently identifies the best VR / AR content and pushes it in real time through the tourists' travel apps or wearable devices. When tourists arrive near a historical site, the system will push the VR guide content of the site, allowing tourists to "walk into" the historical scene through their mobile devices and experience an interactive journey through time and space.
[0049] Then, an intuitive and easy-to-use UI interface is designed to support voice commands and gesture control to ensure that tourists can operate easily even when wearing VR devices. Tourists can switch to the next virtual attraction with a simple voice command "next attraction" or by waving their hands upwards. The system uses integrated GPS and environmental sensors to identify the activity status of tourists, such as walking and standing still, and adjust the rhythm and content of information push accordingly. When it detects that a tourist has stopped in front of a certain attraction, a detailed explanation of the attraction will be automatically played.
[0050] Finally, all collected visitor data is encrypted, whether it is personal basic information or travel behavior data, to ensure the security of data during transmission and storage. A detailed privacy policy is formulated and made public to clearly inform tourists which data will be collected, how it will be used and the storage period, to ensure tourists' right to know, and provide channels for data deletion requests to protect tourists' privacy rights.
[0051] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.
Claims
1. A push system for smart tourism guide data based on cloud platform, It is characterized in that The system consists of the following components: Cloud platform architecture and data processing: Build a data processing and distribution center based on cloud servers to collect and analyze tourism data, conduct in-depth mining of the collected data, analyze tourists' travel habits, interest preferences, and consumption capacity, and provide accurate data support for personalized push notifications; Personalized data push: Based on tourists’ historical behavior data and social network data, we build personalized portraits of tourists, integrate real-time push algorithms, and push customized travel information in real time based on tourists’ current location, tour time, and weather conditions, combined with tourist portraits; VR / AR content generation and push: Integrate VR / AR modules, use 3D modeling and real-scene scanning technology to create high-quality virtual tourism scenes and augmented reality guided content. Visitors can experience interactive functions such as virtual tours, historical re-enactments, and information overlays through mobile devices and designated wearable devices; Interactive experience design: Design a user-friendly interface that supports multiple interactive methods such as voice commands and gesture control to ensure that visitors can easily operate VR / AR functions and improve user experience; Security and privacy protection mechanism: Establish strict data encryption and access control mechanisms to ensure the security of tourists’ personal information while complying with relevant privacy protection laws and regulations.
2. According to claim 1, a push system for smart tourism guide data based on a cloud platform, It is characterized in that The cloud platform architecture and data processing collects tourist behavior data, namely, tour routes, stay time, scenic spot traffic information, and weather forecast data, through mobile social media and online booking platform channels, and uses big data analysis technology to conduct in-depth mining of the collected data. The tourist behavior patterns are classified through cluster analysis K-means algorithm, and K data points are randomly selected as initial cluster centers. The Euclidean distance is used to calculate the distance between each point in the data set and the K cluster centers, that is: P is the data point, C is the cluster center, n is the number of features, p i and c i are the values of the data point and cluster center on the i-th feature, and assign them to the nearest cluster center: C is the new cluster center, m is the number of data points in the cluster, and p i is the coordinate of the i-th data point in the cluster. By grouping a large amount of tourist behavior data, including the types of attractions visited, length of stay, and consumption habits, into different clusters, the system can better understand tourists' preferences and behavior patterns, thereby identifying groups of tourists with similar travel habits and interest preferences.
3. According to claim 1, a push system for smart tourism guide data based on a cloud platform, It is characterized in that The personalized data push uses K-means to help segment user groups, and further implements personalized information push on this basis through collaborative filtering. It also predicts the attractions and activities that users are interested in but have not yet interacted with directly by analyzing the user's past behavior ratings and browsing history. The similarity between users is calculated using the cosine similarity algorithm for the collected user browsing records, purchase records and rating data through collaborative filtering, that is: u and v are users, I uv is the set of items rated by both user u and user v, r ui and r vi are the ratings of user u and user v for item i, respectively. Based on user similarity and historical ratings of similar users, the item with the highest rating is predicted as the recommendation list.
4. According to claim 3, a push system for smart tourism guide data based on a cloud platform, It is characterized in that The specific steps of personalized data push are: (1) Data reception and processing: Receive historical tourist data, visited attractions, length of stay, social media behavior, shared content, and basic demographic age and gender information collected by the cloud platform architecture and data processing, and process the received data to ensure data quality; (2) User portrait construction: Use machine learning algorithms to group users, identify the characteristics of different types of tourists, and combine users' static attributes and dynamic behaviors to build multi-dimensional personalized user portraits; (3) Real-time situational analysis: monitoring external environmental factors such as tourists’ geographic location, current time and weather conditions in real time, and using rule engines and situational awareness to evaluate the impact of these factors on tourists’ needs; (4) Personalized recommendation algorithm: Collaborative filtering is used to calculate the similarity between users, and content that similar users like but that the current user has not yet seen is recommended. The recommendation list is adjusted using weighting factors based on contextual information and user profiles to generate the final personalized push content. (5) Push execution and feedback loop: Push personalized content to tourists through APP, SMS and email, and collect tourists’ feedback on recommended content, including click-through rate, dwell time and evaluation, to continuously optimize the recommendation algorithm.
5. According to claim 1, a push system for smart tourism guide data based on a cloud platform, It is characterized in that The personalized data push extracts features of tourist attractions, activities, and discount information, including descriptive text, pictures, and videos, and matches them with content features based on the personalized portrait age, gender, interests, and preferences of tourists. The content-based recommendation algorithm uses the term frequency-inverse document frequency TF-IDF statistical method to determine the feature weight of the content. The algorithm formula is: TF-IDF(t, d) = TF(t, d) × IDF(t), TF(t, d) is the term frequency of term t in document d, and IDF(t) is the inverse document frequency of term t, that is: Where N is the total number of documents, n t is the number of documents containing term t. Based on the matching results, a content recommendation list that meets the interests of tourists is generated.
6. According to claim 5, a push system for smart tourism guide data based on a cloud platform, It is characterized in that The personalized data push uses a logistic regression classification algorithm to predict the categories and interest groups of tourists, that is, tourists are divided into different categories such as history and culture enthusiasts, natural scenery fans, and adventure experiencers. Once the tourists are classified, the system pushes relevant tourism information according to the category. The algorithm is implemented as follows: the probability of an event occurring is estimated by fitting the data to a logistic function. The feature vector x = (x 1 ,x 2 ,…,x n ) represents various characteristics of tourists, including age, gender, historical ratings, and weight vector w = (w 1 ,w 2 ,…,w n ) and bias term b, logistic regression formula: Calculate the probability that a tourist belongs to a certain category, y=1 means that the tourist belongs to the category, y=0 means that the tourist does not belong to the category. The optimal values of w and b are learned through training data, and new tourists are classified and personalized information is pushed. The user's preference for specific content and services is predicted, and the tourism information related to the category is pushed.
7. According to claim 6, a cloud platform-based smart tourism guide data push system, It is characterized in that The personalized data push utilizes the classification of new tourists and personalized information push, and is used to predict the tourists' interest in tourism products and activities through the regression algorithm, and predict the tourists' next behavior, including: which scenic spot to choose, which activity to participate in, etc., which tourism product to buy, and help the system push customized tourism information more accurately based on the prediction results. Through the linear regression technology in the regression algorithm, the relationship between the dependent variable target and the independent variable characteristics is studied, and the tourists' interest in tourism products and activities is used as the dependent variable, and the tourists' characteristics are used as the independent variable. The interest level is predicted through linear regression, that is: is the predicted value of the target variable, y is the target variable, and the training data is used to learn the optimal value of the parameter, predict the interest level of new tourists and push personalized information, predict the user's rating of the service and the expected length of stay, analyze the relationship between user characteristics and corresponding ratings, and optimize the user experience.
8. According to claim 7, a cloud platform-based smart tourism guide data push system, It is characterized in that The specific steps of VR / AR content generation and push are as follows: (1) 3D modeling and scene construction: Use 3D modeling software to create a three-dimensional model of the scenic spot. According to the actual scene requirements, add textures, materials, and light and shadow effects to the model to simulate the real environment and build a complete virtual tourism scene, including roads, buildings, and vegetation; (2) Real scene scanning and data capture: Use laser radar and camera equipment to scan the scenic area in real time, obtain real-world data, process the scanned data, generate point cloud data and three-dimensional models, and combine 3D modeling technology to integrate the real scene scan data with the virtual scene; (3) Content production and enhancement: Add multimedia content such as tour guide voice, text description and animation effects to the virtual scene, and use AR technology to overlay virtual information in the tourists' field of vision, including introductions to scenic spots and historical stories, and design interactive elements, clickable buttons and interactive exhibits; (4) Content optimization and testing: Optimize the generated VR / AR content to ensure smooth operation on different devices and network conditions. Collect feedback and make adjustments through internal testing and user testing. (5) Content publishing and push: The optimized VR / AR content is published on the cloud server. According to the location, preferences and visit time of the tourists, the corresponding VR / AR content is pushed to the tourists’ mobile devices and wearable devices through the cloud platform, providing an immersive VR experience and achieving synchronization of perspective and movement through gyroscope and accelerometer data.
9. According to claim 1, a push system for smart tourism guide data based on a cloud platform, It is characterized in that In the VR / AR content generation and push application, linear interpolation is used to make the movement smoother for object movement and rotation. When an object moves from one position to another, the intermediate position is calculated by linear interpolation, and the position of the object is updated at each time step to achieve a smooth transition. When creating VR / AR animations, the intermediate frames between key frames are calculated to define the states of the start frame and the end frame to generate a smooth animation effect. The algorithm formula is as follows: (x1, y1) and (x2, y2) are two known data points, x is the estimated x value of the unknown data point, and y is the value obtained by interpolation. In the texture mapping process, linear interpolation is used to calculate the correspondence between texture coordinates and pixel colors to ensure the correct mapping and smooth transition of the texture on the surface of the object.
10. A push system for smart tourism guide data based on a cloud platform according to claim 9, It is characterized in that The VR / AR content generation and push uses the Phong illumination model to calculate the illumination intensity on the surface of an object, thereby generating a rendering effect with a sense of reality and three-dimensionality. The ambient illumination part of the Phong illumination model is used to simulate the effect of non-directional light from the surrounding environment on the object, i.e., ambient illumination I a =k a ·L a The diffuse reflection illumination part is used to simulate the effect of directional light from the light source on the surface of the object. By calculating the angle between the light source direction and the normal of the object surface, and combining the diffuse reflection coefficient and the light source color, the diffuse reflection illumination intensity of the object surface is calculated, that is, the diffuse reflection illumination I d =k d ·L d max(0,N·L), the specular illumination part is used to simulate the highlight effect on the surface of an object. By calculating the angle between the light reflection direction vector and the sight direction vector, and combining the specular reflection coefficient and the light source color, the specular illumination intensity of the object surface is calculated, that is, the specular illumination part I s =k s ·L s max(0,R·V) n , k a , k d , k s They are the ambient reflection coefficient, diffuse reflection coefficient and specular reflection coefficient, L a , L d , L s They are the ambient light color, light source color and specular light source color, N is the surface normal vector of the object, L is the light source direction vector, R is the reflection direction unit vector, V is the observation direction unit vector, and n is the reflection index of specular lighting.
Citation Information
Cited By
Tourism content recommendation system for analyzing favorites of tourism scenic spots
CN119474552A
User behavior big data analysis method and system applied to cloud office resource pushing
CN119537702A
AI-based cultural tourism content personalized recommendation system
CN119646311A
Cultural and artistic space browsing interaction method, device and equipment
CN119759206A
Learning resource recommendation method and device based on machine learning, terminal and medium
CN119917746A
