Cultural tourism intelligent promotion method and system based on big data
Through the intelligent cultural tourism promotion system based on big data, Apache Flink and BERT models are used to process data, build user portraits and personalized recommendations, solving the problem of poor promotion methods in the existing technology, and achieving accurate and personalized tourism recommendation effects.
Patent Information
- Application Number
- CN202510630578.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2025-08-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing cultural tourism promotion methods are not targeted and difficult to evaluate the effects, making it difficult to adapt to the rapidly changing market environment and consumer behavior.
The intelligent cultural tourism promotion system based on big data is adopted, including heterogeneous data collection layer, data preprocessing module, dynamic database, user side, data analysis module, portrait construction module, dynamic recommendation module, collaborative recommendation engine, dynamic weighting module, evaluation module and optimization module. Streaming data is processed through Apache Flink, sentiment analysis is used for construction of user portraits, personalized recommendations are combined with collaborative filtering algorithms and weighting algorithms, and coverage is enhanced through pop-up windows and SMS push, and user feedback is collected for optimization.
It has achieved the accuracy and personalization of cultural tourism promotion, improved the accuracy and effectiveness of recommendations, and adapted to the rapidly changing market environment and consumer behavior.
Smart Images
Figure CN120561367A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cultural tourism promotion, and in particular to a method and system for intelligent cultural tourism promotion based on big data. Background Art
[0002] In today's society, the cultural tourism industry is booming, becoming a vital force driving economic growth, preserving cultural heritage, and fostering social exchange. With rising living standards and growing cultural needs, cultural tourism is no longer limited to traditional sightseeing but is evolving into a comprehensive consumer activity that integrates cultural experience, leisure vacations, and intellectual exploration. From ancient historical sites to modern cultural and creative parks, from experiencing folk customs to appreciating art exhibitions, cultural tourism offerings are becoming increasingly diverse and enriching, meeting the personalized needs of diverse tourist groups.
[0003] However, traditional cultural tourism promotion methods are not very targeted and their effectiveness is difficult to evaluate, making it difficult to adapt to the rapidly changing market environment and consumer behavior. Summary of the Invention
[0004] The purpose of the present invention is to provide a method and system for intelligent promotion of cultural tourism based on big data, aiming to solve the technical problems in the existing technology that the cultural tourism promotion methods are not targeted enough and the effects are difficult to evaluate, which makes it difficult to adapt to the rapidly changing market environment and consumer behavior.
[0005] To achieve the above-mentioned purpose, the present invention adopts a cultural tourism intelligent promotion system based on big data, which includes a heterogeneous data collection layer, a data preprocessing module, a dynamic database, a user terminal, a data analysis module, a portrait construction module, a dynamic recommendation module, a collaborative recommendation engine, a dynamic weighting module, an evaluation module and an optimization module. The data preprocessing module is connected to the heterogeneous data collection layer, the dynamic database is connected to the data preprocessing module, the data analysis module is connected to the user terminal, the portrait construction module is connected to the data analysis module, the dynamic recommendation module is connected to the portrait construction module, the collaborative recommendation engine and the dynamic weighting module are both connected to the dynamic recommendation module, the evaluation module is connected to the dynamic recommendation module, the optimization module is both connected to the evaluation module and the dynamic recommendation module, and the dynamic recommendation module is also connected to the dynamic database;
[0006] The heterogeneous data collection layer is used to collect tourism-related data, and uses Apache Flink to implement streaming data processing through the data preprocessing module, and uses the BERT model to perform sentiment analysis on unstructured data. The preprocessed data is stored in the dynamic database;
[0007] The user terminal provides a personalized operation page;
[0008] The data analysis module is used to analyze the user behavior data in the user terminal to obtain user characteristics;
[0009] The portrait construction module constructs a user portrait based on the obtained user features, and the dynamic recommendation module performs real-time promotion based on the dynamic database in combination with the user portrait;
[0010] The collaborative recommendation engine finds other users with similar interests to the target user and recommends their preferred attractions;
[0011] The dynamic weighting module balances the diversity of recommendation results.
[0012] The cultural tourism intelligent promotion system based on big data further includes an anomaly detection module, which is connected to the heterogeneous data collection layer:
[0013] The anomaly detection module identifies false data based on the IsolationForest algorithm.
[0014] The user terminal is embedded with a login module and an authorization module. The login module is used to log in to the user terminal, and the authorization module is used for the user to authorize the system to use user information for promotion.
[0015] The big data-based cultural tourism intelligent promotion system further includes a regular promotion unit, which includes a pop-up window push module and an SMS push module, and both the pop-up window push module and the SMS push module are connected to the dynamic recommendation module;
[0016] The SMS push module is embedded with a rejection feedback module, and the rejection feedback module is used to record that no SMS push will be performed again after the user replies to the response information.
[0017] Among them, the cultural tourism intelligent promotion system based on big data also includes an intelligent recognition module and an interactive linkage module. The intelligent recognition module is connected to the heterogeneous data collection layer, and the interactive linkage module is connected to the intelligent recognition module.
[0018] Among them, the cultural tourism intelligent promotion system based on big data also includes a portrait update optimization module, and the portrait update optimization module is connected to the portrait construction module.
[0019] Among them, the cultural tourism intelligent promotion system based on big data also includes an evaluation data collection module and a service shortcoming identification module. The evaluation data collection module is connected to the evaluation module, and the service shortcoming identification module is connected to the evaluation data collection module.
[0020] The present invention also provides a method for intelligent promotion of cultural tourism based on big data, which is applied to the above-mentioned intelligent promotion system for cultural tourism based on big data.
[0021] The steps include:
[0022] First, the tourism-related data is collected through the heterogeneous data collection layer, and the data is pre-processed by the data pre-processing module and stored in the dynamic database;
[0023] The data analysis module analyzes the user behavior data in the user terminal to obtain user characteristics, and constructs a user portrait through the portrait construction module based on the obtained user characteristics;
[0024] The dynamic recommendation module combines user portraits and performs real-time promotion based on a dynamic database; at the same time, the collaborative recommendation engine finds other users with similar interests to the target user and recommends their preferred attractions; the dynamic weighting module balances the diversity of recommendation results.
[0025] The present invention provides a method and system for intelligent promotion of cultural tourism based on big data. When used in practice, tourism-related data is collected through the heterogeneous data collection layer. The data preprocessing module uses Apache Flink for streaming processing and uses the BERT model to perform sentiment analysis and other operations on unstructured data. The preprocessed data is stored in the dynamic database. The user terminal provides a personalized operation page, and the user's behavioral data on the page is analyzed by the data analysis module to extract user features. The portrait construction module uses a machine learning algorithm (such as a decision tree, etc.) to construct a user portrait containing information such as user preferences. The dynamic recommendation module combines user portraits and uses the collaborative filtering algorithm of the collaborative recommendation engine (such as user-based collaborative filtering or item-based collaborative filtering) to find users with similar interests and recommend their preferred attractions. At the same time, the dynamic weighting module uses a weighting algorithm to comprehensively consider weight factors such as the popularity and distance of the attractions to balance the diversity of the recommendation results. The evaluation module collects user feedback, and the optimization module optimizes the dynamic recommendation module using an optimization algorithm (such as gradient descent, etc.) based on the feedback data to improve the accuracy and effectiveness of the recommendations. The entire system works together efficiently to achieve precise and personalized travel recommendations. In this way, the technical problem that the cultural tourism promotion methods in the existing technology are not very targeted and the effects are difficult to evaluate, resulting in difficulty in adapting to the rapidly changing market environment and consumer behavior, is solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] 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 description of the prior art. 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.
[0027] Figure 1 It is a principle block diagram of the first embodiment of the present invention.
[0028] Figure 2 It is a principle block diagram of the second embodiment of the present invention.
[0029] Figure 3 It is a principle block diagram of the third embodiment of the present invention.
[0030] Figure 4 It is a flow chart of the cultural tourism intelligent promotion method based on big data of the present invention.
[0031] 101-Heterogeneous data collection layer, 102-Data preprocessing module, 103-Dynamic database, 104-User end, 105-Data analysis module, 106-Portrait construction module, 107-Dynamic recommendation module, 108-Collaborative recommendation engine, 109-Dynamic weighting module, 110-Evaluation module, 111-Optimization module, 112-Anomaly detection module, 113-Regular promotion unit, 114-Login module, 115-Authorization module, 116-Pop-up push module, 117-SMS push module, 118-Rejection feedback module, 201-Intelligent identification module, 202-Interactive linkage module, 203-Portrait update optimization module, 204-Evaluation data collection module, 205-Service shortcoming identification module, 301-Authentication module, 302-Permission management module, 303-Storage module. DETAILED DESCRIPTION
[0032] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be understood as limiting the present invention.
[0033] The first embodiment of this application is:
[0034] See also Figure 1 , Figure 1 It is a principle block diagram of the first embodiment of the present invention.
[0035] The present invention provides a cultural tourism intelligent promotion system based on big data, including a heterogeneous data collection layer 101, a data preprocessing module 102, a dynamic database 103, a user terminal 104, a data analysis module 105, a portrait construction module 106, a dynamic recommendation module 107, a collaborative recommendation engine 108, a dynamic weighting module 109, an evaluation module 110, an optimization module 111, an anomaly detection module 112 and a regular promotion unit 113. The user terminal 104 is implanted with a login module 114 and an authorization module 115. The regular promotion unit 113 includes a pop-up push module 116 and an SMS push module 117. The SMS push module 117 is implanted with a rejection feedback module 118. The above solution solves the technical problems in the existing technology that the cultural tourism promotion methods are not highly targeted and the effects are difficult to evaluate, resulting in difficulty in adapting to the rapidly changing market environment and consumer behavior.
[0036] In this specific embodiment, the heterogeneous data collection layer 101 is used to collect tourism-related data, and uses Apache Flink to implement streaming data processing through the data preprocessing module 102, and uses the BERT model to perform sentiment analysis on unstructured data. The preprocessed data is stored in the dynamic database 103;
[0037] The user terminal 104 provides a personalized operation page;
[0038] The data analysis module 105 is used to analyze the user behavior data in the user terminal 104 to obtain user characteristics;
[0039] The portrait construction module 106 constructs a user portrait based on the obtained user features, and the dynamic recommendation module 107 performs real-time promotion based on the dynamic database 103 in combination with the user portrait;
[0040] The collaborative recommendation engine 108 finds other users with similar interests to the target user and recommends their preferred attractions;
[0041] The dynamic weighting module 109 balances the diversity of recommendation results.
[0042] Among them, the data preprocessing module 102 is connected to the heterogeneous data collection layer 101, the dynamic database 103 is connected to the data preprocessing module 102, the data analysis module 105 is connected to the user terminal 104, the portrait construction module 106 is connected to the data analysis module 105, the dynamic recommendation module 107 is connected to the portrait construction module 106, the collaborative recommendation engine 108 and the dynamic weighting module 109 are both connected to the dynamic recommendation module 107, the evaluation module 110 is connected to the dynamic recommendation module 107, the optimization module 111 is connected to the evaluation module 110 and the dynamic recommendation module 107, and the dynamic recommendation module 107 is also connected to the dynamic database 103. During specific use, tourism-related data is collected through the heterogeneous data collection layer 101, the data preprocessing module 102 uses Apache Flink for stream processing, and uses the BERT model to perform sentiment analysis and other operations on unstructured data. The preprocessed data is stored in the dynamic database 103. The user terminal 104 provides a personalized operation page. The user's behavioral data on the page is analyzed by the data analysis module 105 to extract user characteristics. The profile construction module 106 uses machine learning algorithms (such as decision trees) to construct a user profile containing information such as user preferences. The dynamic recommendation module 107 combines the user profile and uses the collaborative filtering algorithm of the collaborative recommendation engine 108 (such as user-based collaborative filtering or item-based collaborative filtering) to find users with similar interests and recommend their preferred attractions. At the same time, the dynamic weighting module 109 uses a weighting algorithm to comprehensively consider weight factors such as the popularity and distance of the attractions to balance the diversity of the recommendation results. The evaluation module 110 collects user feedback, and the optimization module 111 optimizes the dynamic recommendation module 107 based on the feedback data using an optimization algorithm (such as gradient descent) to improve the accuracy and effectiveness of the recommendations. The entire system works efficiently and collaboratively to achieve precise and personalized travel recommendations. This solves the technical problems of existing cultural tourism promotion methods that are not targeted, difficult to evaluate, and difficult to adapt to the rapidly changing market environment and consumer behavior.
[0043] Secondly, the anomaly detection module 112 is connected to the heterogeneous data collection layer 101:
[0044] The anomaly detection module 112 uses the Isolation Forest algorithm to identify false data, which can control the data quality in the data collection stage, promptly discover anomalies that may occur during the data collection process, and prevent abnormal data from entering the subsequent processing flow, thereby ensuring the accuracy and reliability of subsequent cultural tourism promotion analysis, recommendation and other operations based on these data, and improving the data quality and promotion effect of the entire system.
[0045] Meanwhile, the login module 114 is used to log in to the user terminal 104, and the authorization module 115 is used by the user to authorize the system to use the user's information for promotional purposes. The login module 114 provides a convenient and secure login method for users, facilitating access to the system and enhancing the user experience. The provision of the authorization module 115 protects user privacy and the legality of data use. The system can only obtain relevant data if the user explicitly authorizes the system to use their information for promotional purposes.
[0046] In addition, the pop-up window push module 116 and the SMS push module 117 are both connected to the dynamic recommendation module 107;
[0047] The rejection feedback module 118 is used to record the end of SMS push notifications after the user replies to the response message. Through the pop-up push module 116 and the SMS push module 117, cultural tourism-related information can be proactively pushed to the user, increasing the promotional coverage and exposure. By implementing the rejection feedback module 118, the user's feelings and needs are fully taken into account. When the user replies to the response message to indicate that he or she no longer wants to receive SMS push notifications, the system can record this information and stop SMS push notifications to the user, avoiding unnecessary interruptions to the user and improving the user's trust and favorability in the system.
[0048] In the specific use of the cultural tourism intelligent promotion system based on big data of this embodiment, tourism-related data is collected through the heterogeneous data collection layer 101. The data preprocessing module 102 uses Apache Flink for stream processing and uses the BERT model to perform sentiment analysis and other operations on unstructured data. The preprocessed data is stored in the dynamic database 103. The user terminal 104 provides a personalized operation page. The user's behavioral data on the page is analyzed by the data analysis module 105 to extract user characteristics. The profile construction module 106 uses machine learning algorithms (such as decision trees) to construct a user profile containing information such as user preferences. The dynamic recommendation module 107 combines the user profile and uses the collaborative filtering algorithm of the collaborative recommendation engine 108 (such as user-based collaborative filtering or item-based collaborative filtering) to find users with similar interests and recommend their preferred attractions. At the same time, the dynamic weighting module 109 uses a weighting algorithm to comprehensively consider weight factors such as the popularity and distance of the attractions to balance the diversity of the recommendation results. The evaluation module 110 collects user feedback, and the optimization module 111 optimizes the dynamic recommendation module 107 based on the feedback data using an optimization algorithm (such as gradient descent, etc.) to improve the accuracy and effectiveness of the recommendation. The entire system works together efficiently to achieve accurate and personalized travel recommendations, thereby solving the technical problems in the existing technology of cultural tourism promotion methods being not highly targeted and difficult to evaluate, resulting in difficulty in adapting to the rapidly changing market environment and consumer behavior.
[0049] The second embodiment of the present application is:
[0050] Based on the first embodiment, please refer to Figure 2 , Figure 2 It is a principle block diagram of the second embodiment of the present invention.
[0051] The present invention provides a cultural tourism intelligent promotion system based on big data, which also includes an intelligent recognition module 201, an interactive linkage module 202, a portrait update optimization module 203, an evaluation data collection module 204 and a service shortcoming identification module 205.
[0052] For this specific implementation, the intelligent identification module 201 is connected to the heterogeneous data collection layer 101, and the interactive linkage module 202 is connected to the intelligent identification module 201. The intelligent identification module 201 is used to intelligently identify the data collected by the heterogeneous data collection layer 101, and when it is determined that there is public opinion, it is pushed to the management personnel through the interactive linkage module 202.
[0053] The profile update and optimization module 203 is connected to the profile construction module 106. Since user behavior and preferences are dynamic, the profile update and optimization module 203 can update and optimize the user profile in real time or periodically after being connected to the profile construction module 106. By continuously tracking new user behavior and feedback, the user profile can be adjusted and improved in a timely manner, ensuring that the system is always promoting based on the latest and most accurate user information.
[0054] Secondly, the evaluation data collection module 204 is connected to the evaluation module 110, and the service shortcoming identification module 205 is connected to the evaluation data collection module 204. The evaluation data collection module 204 is connected to the evaluation module 110, and can efficiently and comprehensively collect these evaluation data, providing a rich data source for subsequent analysis and processing. The service shortcoming identification module 205 uses data analysis technology to accurately identify the shortcomings and deficiencies in cultural tourism services based on the large amount of evaluation data obtained by the evaluation data collection module 204.
[0055] Using a cultural tourism intelligent promotion system based on big data of this embodiment, after the portrait update optimization module 203 is connected to the portrait construction module 106, the user portrait can be updated and optimized in real time or regularly. By continuously tracking the user's new behavior and new feedback, the user portrait is adjusted and improved in a timely manner to ensure that the system is always promoted based on the latest and most accurate user information. The evaluation data collection module 204 is connected to the evaluation module 110, and can efficiently and comprehensively collect these evaluation data, providing a rich data source for subsequent analysis and processing. The service shortcoming identification module 205 uses data analysis technology to accurately identify the shortcomings and deficiencies in cultural tourism services based on the large amount of evaluation data obtained by the evaluation data collection module 204.
[0056] The third embodiment of the present application is:
[0057] Based on the second embodiment, please refer to Figure 3 , Figure 3 It is a principle block diagram of the third embodiment of the present invention.
[0058] The present invention provides a cultural tourism intelligent promotion system based on big data, which also includes an identity authentication module 301, a rights management module 302 and a storage module 303.
[0059] For this specific implementation, the identity authentication module 301 is connected to the login module 114, and the permission management module 302 is connected to the identity authentication module 301. The identity authentication module 301 is used to authenticate the user who logs in to the user terminal 104 using the login module 114, and the permission management module 302 manages the operation permissions based on the identity of the logged-in user.
[0060] The storage module 303 is connected to the dynamic recommendation module 107 , and is used to log the dynamic recommendation module 107 , so as to facilitate subsequent review and update based on the log.
[0061] A cultural tourism intelligent promotion system based on big data is used in this embodiment. The identity authentication module 301 is used to authenticate the user who logs in to the user terminal 104 using the login module 114. The permission management module 302 manages the operation permission based on the logged-in user identity. The storage module 303 is used to log the dynamic recommendation module 107 for subsequent review and update based on the log.
[0062] See also Figure 4 , Figure 4 It is a flow chart of the cultural tourism intelligent promotion method based on big data of the present invention.
[0063] The present invention also provides a method for intelligent promotion of cultural tourism based on big data, which is applied to the above-mentioned intelligent promotion system for cultural tourism based on big data.
[0064] The steps include:
[0065] S1. First, the tourism-related data is collected through the heterogeneous data collection layer 101, and the data is pre-processed by the data pre-processing module 102 and stored in the dynamic database 103;
[0066] S2. The data analysis module 105 analyzes the user behavior data in the user terminal 104 to obtain user characteristics, and constructs a user profile through the portrait construction module 106 based on the obtained user characteristics;
[0067] S3, the dynamic recommendation module 107 combines the user portrait and performs real-time promotion based on the dynamic database 103;
[0068] S4. At the same time, when the user does not actively search, cultural tourism related information is actively pushed to the user through the pop-up push module 116 and the SMS push module 117 to increase the coverage and exposure of the promotion.
[0069] The above disclosure is only a preferred embodiment of the present invention, and certainly cannot be used to limit the scope of the rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiment and equivalent changes made in accordance with the claims of the present invention are still within the scope of the invention.
Claims
1. A cultural tourism intelligent promotion system based on big data, characterized by: It includes a heterogeneous data collection layer, a data preprocessing module, a dynamic database, a user terminal, a data analysis module, a portrait construction module, a dynamic recommendation module, a collaborative recommendation engine, a dynamic weighting module, an evaluation module and an optimization module. The data preprocessing module is connected to the heterogeneous data collection layer, the dynamic database is connected to the data preprocessing module, the data analysis module is connected to the user terminal, the portrait construction module is connected to the data analysis module, the dynamic recommendation module is connected to the portrait construction module, the collaborative recommendation engine and the dynamic weighting module are both connected to the dynamic recommendation module, the evaluation module is connected to the dynamic recommendation module, the optimization module is both connected to the evaluation module and the dynamic recommendation module, and the dynamic recommendation module is also connected to the dynamic database; The heterogeneous data collection layer is used to collect tourism-related data, and uses Apache Flink to implement streaming data processing through the data preprocessing module, and uses the BERT model to perform sentiment analysis on unstructured data. The preprocessed data is stored in the dynamic database; The user terminal provides a personalized operation page; The data analysis module is used to analyze the user behavior data in the user terminal to obtain user characteristics; The portrait construction module constructs a user portrait based on the obtained user features, and the dynamic recommendation module performs real-time promotion based on the dynamic database in combination with the user portrait; The collaborative recommendation engine finds other users with similar interests to the target user and recommends their preferred attractions; The dynamic weighting module balances the diversity of recommendation results.
2. The cultural tourism intelligent promotion system based on big data according to claim 1, characterized in that: The cultural tourism intelligent promotion system based on big data also includes an anomaly detection module, which is connected to the heterogeneous data collection layer: The anomaly detection module identifies false data based on the IsolationForest algorithm.
3. The cultural tourism intelligent promotion system based on big data according to claim 2, characterized in that: The user terminal is embedded with a login module and an authorization module. The login module is used to log in to the user terminal, and the authorization module is used for the user to authorize the system to use user information for promotion.
4. The cultural tourism intelligent promotion system based on big data according to claim 3 is characterized in that: The cultural tourism intelligent promotion system based on big data also includes a regular promotion unit, which includes a pop-up push module and an SMS push module, and both the pop-up push module and the SMS push module are connected to the dynamic recommendation module; The SMS push module is embedded with a rejection feedback module, and the rejection feedback module is used to record that no SMS push will be performed again after the user replies to the response information.
5. The cultural tourism intelligent promotion system based on big data according to claim 4 is characterized in that: The cultural tourism intelligent promotion system based on big data also includes an intelligent recognition module and an interactive linkage module. The intelligent recognition module is connected to the heterogeneous data collection layer, and the interactive linkage module is connected to the intelligent recognition module.
6. The cultural tourism intelligent promotion system based on big data according to claim 5 is characterized in that: The cultural tourism intelligent promotion system based on big data also includes a portrait update optimization module, which is connected to the portrait construction module.
7. The method and system for intelligent promotion of cultural tourism based on big data according to claim 6, characterized in that: The cultural tourism intelligent promotion system based on big data also includes an evaluation data collection module and a service shortcoming identification module. The evaluation data collection module is connected to the evaluation module, and the service shortcoming identification module is connected to the evaluation data collection module.
8. A method for intelligent promotion of cultural tourism based on big data, applied to the intelligent promotion system for cultural tourism based on big data as claimed in claim 7, characterized in that: The steps include: First, the tourism-related data is collected through the heterogeneous data collection layer, and the data is pre-processed by the data pre-processing module and stored in the dynamic database; The data analysis module analyzes the user behavior data in the user terminal to obtain user characteristics, and constructs a user portrait through the portrait construction module based on the obtained user characteristics; The dynamic recommendation module combines user portraits and performs real-time promotion based on a dynamic database; at the same time, the collaborative recommendation engine finds other users with similar interests to the target user and recommends their preferred attractions; the dynamic weighting module balances the diversity of recommendation results.