Big data-based text travel industry cognitive analysis system

Abstract

The invention discloses a big data-based text travel industry cognitive analysis system, and relates to the technical field of big data, and the system comprises a data collection module which is used for collecting related data, including scenic spot data, tourist behavior data, social media data and traffic data, of the text travel industry from a multi-source channel; the data preprocessing module is used for cleaning, denoising and formatting the collected data and ensuring the data security through a data encryption technology; the cognitive analysis module is used for performing semantic analysis, sentiment analysis and behavior pattern recognition on the preprocessed data based on a deep learning algorithm and a natural language processing technology to generate a cognitive map of the text travel industry; the intelligent decision-making module is used for predicting tourist demands through a machine learning model according to the cognitive map in combination with historical data and real-time data, optimizing resource configuration and providing personalized recommendation services; and the visual display module is used for displaying an analysis result to a user in a visual manner and supporting multi-dimensional data query and real-time monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of big data, and specifically relates to a cognitive analysis system for the culture and tourism industry based on big data. Background Art

[0002] Based on the popularization of technologies such as the Internet, mobile Internet, and Internet of Things, these technologies have promoted the massive generation and accumulation of data in the culture and tourism industry. With the continuous development of big data technology, people have begun to realize the huge value hidden behind these data. Therefore, a cognitive analysis system for the culture and tourism industry based on big data has emerged as the times require.

[0003] The data sources in the culture and tourism industry are very extensive, including hotel reservation data, flight data, scenic spot data, social media data, etc. These data are often scattered in different platforms and systems; the phenomenon of data islands is serious, and it is difficult to effectively integrate and share data between different platforms, resulting in the comprehensiveness and accuracy of data being affected; due to the diversity of data sources, it is often difficult to ensure the accuracy, integrity, and timeliness of data; there may be errors in the data collection process, the data formats and standards of different platforms are not unified, which may lead to data loss and inconsistency, and the data update frequency sometimes cannot meet the real-time requirements, affecting the timeliness of decision-making. Due to the diversity of data sources, it is often difficult to ensure the accuracy, integrity, and timeliness of data, there may be errors in the data collection process, the data formats and standards of different platforms are not unified, which may lead to data loss and inconsistency, and the data update frequency sometimes cannot meet the real-time requirements, affecting the timeliness of decision-making. Summary of the Invention

[0004] To solve the above technical problems, a cognitive analysis system for the culture and tourism industry based on big data is provided. This technical solution solves the problems of serious data island phenomenon, difficult effective integration and sharing of data between different platforms, resulting in the comprehensiveness and accuracy of data being affected, often difficult to ensure the accuracy, integrity, and timeliness of data due to the diversity of data sources, and sometimes the data update frequency cannot meet the real-time requirements, affecting the timeliness of decision-making.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A cognitive analysis system for the culture and tourism industry based on big data, comprising:

[0007] A data collection module: used to collect culture and tourism industry-related data from multiple sources, including scenic spot data, tourist behavior data, social media data, and traffic data;

[0008] A data preprocessing module: cleaning, denoising, and formatting the collected data, and ensuring data security through data encryption technology;

[0009] Cognitive Analysis Module: Based on deep learning algorithms and natural language processing techniques, perform semantic analysis, sentiment analysis, and behavior pattern recognition on the preprocessed data to generate a cognitive map of the cultural and tourism industry;

[0010] Intelligent Decision-making Module: According to the cognitive map, combine historical data and real-time data, predict tourist needs through a machine learning model, optimize resource allocation, and provide personalized recommendation services;

[0011] Visualization Display Module: Display the analysis results to users in a visual way, supporting multi-dimensional data query and real-time monitoring.

[0012] Preferably, the data acquisition module specifically includes:

[0013] IoT Device Acquisition Unit: Deploy sensors and locator devices inside the scenic area to collect environmental and tourist behavior data in real time;

[0014] Online Platform and API Interface Acquisition Unit: Obtain relevant data by cooperating with online travel platforms, social media platforms, and transportation departments;

[0015] Web Crawler Technology Acquisition Unit: Used to collect tourist comments and sharing content on social media;

[0016] Data Sharing and Exchange Unit: Integrate cultural and tourism-related data across departments and levels through the government affairs data sharing platform.

[0017] Preferably, the data preprocessing module specifically includes:

[0018] Automation Unit: Use the preprocessing module in the machine learning library to achieve data cleaning, standardization, and encoding;

[0019] ETL Unit: Extract, transform, and load data through ETL tools;

[0020] Data Security Unit: Combine blockchain technology and encryption algorithms to encrypt sensitive data to ensure data security and privacy protection.

[0021] Preferably, the cognitive analysis module specifically includes:

[0022] Semantic Analysis Unit: Preprocess the text to unify the text format and remove noise; analyze the semantic structure in the sentence, label the roles of the agent and the patient to help understand the key information in the text; analyze the dependency relationship between words in the sentence to parse the structure of the text;

[0023] Sentiment Analysis Unit: Classify the sentiment of the text through predefined rules and sentiment dictionaries; Use support vector machines and Naive Bayes algorithms to train and classify text features; Use convolutional neural networks and recurrent neural networks to automatically extract sentiment features in the text;

[0024] Behavior Pattern Recognition Unit: Identify popular scenic spots and areas with longer stay times by analyzing the movement trajectories of tourists in the scenic area; Analyze the consumption records of tourists to identify consumption preferences and consumption patterns; Predict the behavior trends and demands of tourists by analyzing the behavioral time series data of tourists;

[0025] Cognitive Map Unit: Integrate the analysis results in the form of a knowledge graph, and display the knowledge graph through a visualization tool to help users intuitively understand the structure and relationships of the cultural and tourism industry.

[0026] Preferably, the behavior pattern recognition unit specifically includes:

[0027] For time series prediction, the calculation formula:

[0028] X t = c + φ1X t-1 + φ2X t-2 +…+ φ p X t-p + ∈ t

[0029] In the formula, X t is the behavior data at time point t; c is the constant term; φ1, φ2, …, φ p are model parameters; ∈ t is the error term.

[0030] Preferably, the intelligent decision-making module specifically includes:

[0031] Demand Prediction Unit: Analyze the behavior data, historical records, and real-time feedback of tourists using machine learning algorithms to predict the future demands of tourists; According to the prediction results, adjust the allocation of scenic area resources and service content in real time to meet the needs of tourists; Combine time series data and spatial data to provide accurate prediction results;

[0032] Resource Allocation Optimization Unit: Optimize the allocation of human and material resources in the scenic area by analyzing tourist flow and behavior patterns; Use machine learning models to analyze market demand and tourist behavior to formulate dynamic pricing strategies; Dynamically adjust the tour route based on the real-time location and preferences of tourists to avoid congestion;

[0033] Personalized Service Unit: Build a tourist profile covering interest preferences, consumption habits, and behavior patterns through deep learning and data analysis techniques; Recommend suitable scenic spots, restaurants, shopping locations, and activities based on the tourist profile and real-time data;

[0034] Real-time Decision Support Unit: Real-time monitors the tourist flow, environmental data, and service facility status in the scenic area through Internet of Things devices and sensors; provides real-time data support for scenic area managers to help them make decisions quickly.

[0035] Preferably, the demand forecasting unit specifically includes:

[0036] Demand forecasting model, calculation formula:

[0037]

[0038] In the formula, is the predicted future demand, D t is the tourist behavior data at the current time point t, H t is the historical record data, R t is the real-time feedback data, and f is the machine learning model.

[0039] Preferably, the resource allocation optimization unit specifically includes:

[0040] Resource optimization model:

[0041] Optimize(R)=argm R inτ(R,V)

[0042] In the formula, R is the resource allocation plan, V is the tourist flow and behavior pattern data, and τ is the loss function, which measures the efficiency of resource allocation.

[0043] Preferably, the personalized service unit specifically includes:

[0044] Construction of tourist portraits:

[0045] Profile u =BuildProfile(I u ,C u ,B u )

[0046] In the formula, Profile u is the portrait of user u, I u is the interest preference, C u is the consumption habit, and B u is the behavior pattern.

[0047] Preferably, the visualization display module specifically includes:

[0048] Multi-dimensional Data Display Unit: It supports multiple chart types to meet the data display requirements in different scenarios. Users can flexibly explore and analyze data by dragging fields and filtering conditions, and it supports users to perform multi-dimensional drill-down and roll-up operations on the data to deeply understand the details of the data;

[0049] Real-time Monitoring Unit: It supports real-time data refresh to ensure that users can obtain the latest data changes in a timely manner; By setting thresholds and alarm rules, it monitors data anomalies in real time to help managers respond quickly;

[0050] Data Query and Customization Unit: It supports users to query data according to the dimensions of time, location, and event to quickly locate the required information; Users can generate custom reports according to their needs and support exporting them as pictures and data files; According to the user roles and permission settings, it controls the data access scope to ensure data security.

[0051] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0052] The present invention proposes to collect data from multiple channels such as scenic spots, tourist behaviors, social media, and transportation through a data collection module, realizing the integration of multi-dimensional data, providing a richer and more comprehensive analysis basis, and thus more accurately reflecting the actual situation of the cultural and tourism industry; Using deep learning and natural language processing technologies, it performs semantic analysis, sentiment analysis, and behavior pattern recognition on the data, and generates a cognitive map of the cultural and tourism industry. This in-depth analysis can reveal the complex relationships and potential trends hidden in the data; The dynamic optimization ability can adjust the scenic spot operation strategy in real time, improve the resource utilization efficiency, and at the same time provide a more personalized experience for tourists; Through personalized recommendation services and intelligent decision-making support, the present invention can significantly improve the tourist experience satisfaction, and at the same time help scenic spot managers optimize resource allocation and reduce operating costs. Brief Description of the Drawings

[0053] Figure 1 It is an internal framework diagram of a cultural and tourism industry cognitive analysis system based on big data;

[0054] Figure 2 It is an internal framework diagram of the data collection module;

[0055] Figure 3 It is an internal framework diagram of the data preprocessing module;

[0056] Figure 4 It is an internal framework diagram of the cognitive analysis module;

[0057] Figure 5 It is an internal framework diagram of the intelligent decision-making module

[0058] Figure 6 It is an internal framework diagram of the visualization display module. Detailed Implementation Manner

[0059] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and other obvious variations can be conceived by those skilled in the art.

[0060] Referring to Figure 1 as shown, a cultural and tourism industry cognitive analysis system based on big data includes:

[0061] Data acquisition module: used to collect data related to the cultural and tourism industry from multiple sources, including scenic spot data, tourist behavior data, social media data, and traffic data;

[0062] Data preprocessing module: cleans, denoises, and formats the collected data, and ensures data security through data encryption technology;

[0063] Cognitive analysis module: based on deep learning algorithms and natural language processing technologies, performs semantic analysis, sentiment analysis, and behavior pattern recognition on the preprocessed data, and generates a cognitive map of the cultural and tourism industry;

[0064] Intelligent decision-making module: according to the cognitive map, combines historical data and real-time data, predicts tourist needs through a machine learning model, optimizes resource allocation, and provides personalized recommendation services;

[0065] Visualization display module: displays the analysis results to users in a visual way, and supports multi-dimensional data query and real-time monitoring.

[0066] This solution significantly improves the data analysis ability and operation efficiency of the cultural and tourism industry through functions such as multi-source data integration, in-depth cognitive analysis, intelligent decision-making support, data security protection, and multi-dimensional visualization display. This solution has more comprehensive data support, more accurate analysis ability, more dynamic optimization mechanism, and higher data security, and can provide a more efficient and intelligent solution for the cultural and tourism industry, helping the digital transformation and high-quality development of the industry.

[0067] Referring to Figure 2 as shown, the data acquisition module specifically includes:

[0068] Internet of Things device acquisition unit: deploy sensors and locator devices inside the scenic spot to collect environmental and tourist behavior data in real time;

[0069] Online platform and API interface acquisition unit: obtain relevant data by cooperating with online travel platforms, social media platforms, and transportation departments;

[0070] Web crawler technology acquisition unit: used to collect tourist comments and sharing content on social media;

[0071] Data Sharing and Exchange Unit: Integrate cross-departmental and cross-level culture and tourism-related data through the government affairs data sharing platform.

[0072] It should be noted that for hardware deployment: Deploy various sensors and positioning devices inside the scenic area to ensure the stable operation of the devices and real-time data transmission; Install intelligent devices (such as intelligent turnstiles and guide screens) and connect them to the system;

[0073] Interface Docking: Collaborate with online travel platforms, social media platforms, transportation departments, etc. to obtain API interface permissions; Develop or integrate API interface programs to achieve automatic data collection and synchronization;

[0074] Web Crawler Development and Deployment: Develop social media crawler tools to ensure the legality and effectiveness of the crawled data; Regularly run the crawler program to collect the latest tourist reviews and sharing content;

[0075] Government Affairs Data Access: Connect to the government affairs data sharing platform to obtain cross-departmental and cross-level culture and tourism data; Standardize the shared data to ensure its availability;

[0076] Data Storage and Management: Store various collected data in the data center and perform preliminary cleaning and formatting; Establish a data management mechanism to ensure the integrity and security of the data.

[0077] Refer to Figure 3 As shown, the data preprocessing module specifically includes:

[0078] Automation Unit: Utilize the preprocessing module in the machine learning library to achieve data cleaning, standardization, and encoding;

[0079] ETL Unit: Extract, transform, and load data through ETL tools;

[0080] Data Security Unit: Combine blockchain technology and encryption algorithms to encrypt sensitive data to ensure data security and privacy protection.

[0081] Refer to Figure 4 As shown, the cognitive analysis module specifically includes:

[0082] Semantic Analysis Unit: Preprocess the text to unify the text format and remove noise; Analyze the semantic structure in the sentence, label the roles of the agent and patient to help understand the key information in the text; Analyze the dependency relationship between words in the sentence to parse the structure of the text;

[0083] Sentiment Analysis Unit: Classify the sentiment of text through predefined rules and sentiment lexicons; use support vector machines and Naive Bayes algorithms to train and classify text features; use convolutional neural networks and recurrent neural networks to automatically extract sentiment features from text;

[0084] Behavior Pattern Recognition Unit: Identify popular scenic spots and areas with longer stay times by analyzing the movement trajectories of tourists in the scenic area; analyze the consumption records of tourists to identify consumption preferences and consumption patterns; predict the behavior trends and demands of tourists by analyzing the behavioral time series data of tourists;

[0085] Cognitive Map Unit: Integrate the analysis results in the form of a knowledge graph and display the knowledge graph through a visualization tool to help users intuitively understand the structure and relationships in the cultural and tourism industry.

[0086] The specific components of the Behavior Pattern Recognition Unit include:

[0087] For time series prediction, the calculation formula:

[0088] X t = c + φ1X t-1 + φ2X t-2 +…+ φ p X t-p + ∈ t

[0089] In the formula, X t is the behavior data at time point t; c is the constant term; φ1, φ2, …, φ p are the model parameters; ∈ t is the error term.

[0090] It should be noted that for rule-based sentiment analysis: Use predefined sentiment lexicons (such as SentiWordNet, sentiment lexicon) to classify the sentiment of text, and calculate the sentiment tendency of the text according to the positive, negative, and neutral words in the sentiment lexicon;

[0091] For machine learning-based sentiment analysis: Extract text features and use algorithms such as support vector machines (SVM) and Naive Bayes to classify the sentiment of text;

[0092] For deep learning-based sentiment analysis: Use convolutional neural networks or recurrent neural networks to automatically extract the sentiment features of text, and use pre-trained language models (such as BERT, GPT) for sentiment classification to improve accuracy and generalization ability.

[0093] Trajectory Analysis: Analyze the movement trajectories of tourists within the scenic area, identify popular attractions and areas with longer stay times, use clustering algorithms (such as K-Means) to cluster the trajectory data, and extract typical behavior patterns;

[0094] Consumer Behavior Analysis: Analyze the consumption records of tourists, identify consumption preferences and patterns, and use association rule mining (such as the Apriori algorithm) to discover the association relationships in consumption behaviors;

[0095] Behavior Trend Prediction: Use time series analysis (such as the ARIMA model) to predict the behavior trends of tourists, and use deep learning models (such as LSTM) to process the behavior time series data to predict future demands.

[0096] Refer to Figure 5 As shown, the intelligent decision-making module specifically includes:

[0097] Demand Prediction Unit: Analyze the behavior data, historical records, and real-time feedback of tourists using machine learning algorithms to predict the future demands of tourists; according to the prediction results, adjust the scenic area resource allocation and service content in real time to meet the needs of tourists; combine time series data and spatial data to provide accurate prediction results;

[0098] Resource Allocation Optimization Unit: Optimize the allocation of human and material resources within the scenic area by analyzing tourist flow and behavior patterns; use machine learning models to analyze market demands and tourist behaviors to formulate dynamic pricing strategies; dynamically adjust the tour routes based on the real-time locations and preferences of tourists to avoid congestion;

[0099] Personalized Service Unit: Build tourist portraits covering interest preferences, consumption habits, and behavior patterns through deep learning and data analysis techniques; recommend suitable attractions, dining places, shopping locations, and activities based on tourist portraits and real-time data;

[0100] Real-time Decision Support Unit: Real-time monitor the tourist flow, environmental data, and service facility status within the scenic area through Internet of Things devices and sensors; provide real-time data support for scenic area managers to help them make quick decisions.

[0101] The said Demand Prediction Unit specifically includes:

[0102] Demand Prediction Model, calculation formula:

[0103]

[0104] In the formula, is the predicted future demand, D t is the tourist behavior data at the current time point t, H t is the historical record data, R tFor real-time feedback data, f is a machine learning model.

[0105] The resource allocation optimization unit specifically includes:

[0106] Resource optimization model:

[0107]

[0108] In the formula, R is the resource allocation plan, V is the tourist flow and behavior pattern data, and τ is the loss function, which measures the efficiency of resource allocation.

[0109] The personalized service unit specifically includes:

[0110] Tourist profile construction:

[0111] Profile u =BuildProfile(I u ,C u ,B u )

[0112] In the formula, Profile u is the profile of user u, I u is the interest preference, C u is the consumption habit, and B u is the behavior pattern.

[0113] The intelligent decision-making module is widely used in the cultural and tourism industry, which can significantly improve the operation efficiency of scenic spots and the tourist experience. For example: Scenic spot resource management: Optimize the allocation of human and material resources to improve operation efficiency; Personalized service: Provide customized tour routes and recommendation services for tourists; Real-time monitoring and decision-making: Help managers quickly respond to tourist needs and emergencies.

[0114] Referring to Figure 6 as shown, the visualization display module specifically includes:

[0115] Multi-dimensional data display unit: Supports various chart types to meet the data display needs in different scenarios. Users can flexibly explore and analyze data by dragging fields and filtering conditions, and support users to perform multi-dimensional drill-down and roll-up operations on data to deeply understand the details of data;

[0116] Real-time monitoring unit: Supports real-time data refresh to ensure that users can obtain the latest data changes in a timely manner; By setting thresholds and alarm rules, it monitors data anomalies in real time to help managers quickly respond;

[0117] Data Query and Customization Unit: It supports users to query data according to the dimensions of time, location, and event, quickly locate the required information; users can generate custom reports according to their needs and support exporting them as pictures and data files; according to the user roles and permission settings, it controls the data access scope to ensure data security.

[0118] In summary, the advantages of the present invention are as follows: The data acquisition module collects data from multiple channels such as scenic spots, tourist behaviors, social media, and transportation, realizing the integration of multi-dimensional data, providing a richer and more comprehensive analysis basis, and thus more accurately reflecting the actual situation of the cultural and tourism industry; by using deep learning and natural language processing technologies, semantic analysis, sentiment analysis, and behavior pattern recognition are performed on the data, and a cognitive map of the cultural and tourism industry is generated. This in-depth analysis can reveal the complex relationships and potential trends hidden in the data; the dynamic optimization ability can adjust the scenic spot operation strategy in real time, improve the resource utilization efficiency, and at the same time provide a more personalized experience for tourists; through personalized recommendation services and intelligent decision-making support, the present invention can significantly improve the experience satisfaction of tourists, and at the same time help scenic spot managers optimize resource allocation and reduce operating costs.

[0119] The above has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A cognitive analysis system for the cultural and tourism industry based on big data, characterized in that: include: Data collection module: used to collect cultural and tourism industry-related data from multiple sources, including scenic spot data, tourist behavior data, social media data, and traffic data; Data preprocessing module: cleans, removes noise, formats the collected data, and ensures data security through data encryption technology; Cognitive analysis module: Based on deep learning algorithms and natural language processing technology, it performs semantic analysis, sentiment analysis, and behavioral pattern recognition on pre-processed data to generate a cognitive map of the cultural and tourism industry; Intelligent decision-making module: Based on cognitive maps, combined with historical data and real-time data, the machine learning model predicts tourist needs, optimizes resource allocation, and provides personalized recommendation services; Visual display module: displays the analysis results to users in a visual way, supporting multi-dimensional data query and real-time monitoring.

2. According to the big data-based cultural and tourism industry cognitive analysis system of claim 1, it is characterized by: The data acquisition module specifically includes: IoT device collection unit: deploy sensors and locator devices in the scenic area to collect environmental and tourist behavior data in real time; Online platform and API interface collection unit: obtain relevant data by cooperating with online travel platforms, social media platforms, and transportation departments; Crawler technology collection unit: used to collect visitor comments and sharing content on social media; Data sharing and exchange unit: Integrate cross-departmental and cross-level cultural and tourism related data through the government data sharing platform.

3. A cultural and tourism industry cognitive analysis system based on big data according to claim 2, characterized in that: The data preprocessing module specifically includes: Automation unit: Use the preprocessing module in the machine learning library to clean, standardize and encode data; ETL unit: extract, transform and load data through ETL tools; Data security unit: Combine blockchain technology and encryption algorithms to encrypt sensitive data to ensure data security and privacy protection.

4. According to the big data-based cultural and tourism industry cognitive analysis system of claim 3, it is characterized in that: The cognitive analysis module specifically includes: Semantic analysis unit: pre-processes the text to unify the text format and remove noise; analyzes the semantic structure in the sentence, marks the roles of the agent and the patient, and helps understand the key information in the text; analyzes the structure of the text by analyzing the dependency relationship between words in the sentence; Sentiment analysis unit: classify text sentiments through predefined rules and sentiment dictionaries; train and classify text features using support vector machines and naive Bayes algorithms; and automatically extract sentiment features from texts using convolutional neural networks and recurrent neural networks; Behavior pattern recognition unit: Identify popular attractions and areas with longer stays by analyzing tourists’ movement trajectories in the scenic area; analyze tourists’ consumption records to identify consumption preferences and consumption patterns; and predict tourists’ behavior trends and needs by analyzing tourists’ behavior time series data; Cognitive graph unit: Integrate the analysis results in the form of a knowledge graph, display the knowledge graph through visualization tools, and help users intuitively understand the structure and relationships of the cultural and tourism industry.

5. According to the big data-based cultural and tourism industry cognitive analysis system of claim 4, it is characterized in that: The behavior pattern recognition unit specifically includes: Using time series prediction, the calculation formula is: X t =c+φ1X t-1 +φ2X t-2 +…+φ p X t-p +∈ t Where, X t is the behavior data at time point t; c is a constant term; φ1, φ2, …, φ p is the model parameter; ∈ t is the error term.

6. A cultural and tourism industry cognitive analysis system based on big data according to claim 5, characterized in that: The intelligent decision-making module specifically includes: Demand forecasting unit: Use machine learning algorithms to analyze tourists’ behavior data, historical records, and real-time feedback to predict tourists’ future needs; adjust scenic spot resource allocation and service content in real time based on the forecast results to meet tourists’ needs; combine time series data and spatial data to provide accurate forecast results; Resource allocation optimization unit: optimize the allocation of human and material resources within the scenic area by analyzing tourist flow and behavior patterns; use machine learning models to analyze market demand and tourist behavior and formulate dynamic pricing strategies; dynamically adjust tour routes based on tourists' real-time locations and preferences to avoid congestion; Personalized service unit: Through deep learning and data analysis technology, we build tourist profiles covering interest preferences, consumption habits, and behavior patterns; based on tourist profiles and real-time data, we recommend suitable attractions, restaurants, shopping locations, and activities; Real-time decision support unit: monitors tourist flow, environmental data and service facility status in the scenic area in real time through IoT devices and sensors; provides real-time data support to scenic area managers to help them make decisions quickly.

7. The big data-based cultural and tourism industry cognitive analysis system according to claim 6 is characterized in that: The demand forecasting unit specifically includes: Demand forecasting model, calculation formula: In the formula, To predict future demand, D t is the tourist behavior data at the current time point t, H t is the historical data, R t is the real-time feedback data, and f is the machine learning model.

8. The big data-based cultural and tourism industry cognitive analysis system according to claim 6, characterized in that: The resource configuration optimization unit specifically includes: Resource optimization model: Where R is the resource allocation plan, V is the tourist flow and behavior pattern data, and τ is the loss function, which measures the efficiency of resource allocation.

9. The big data-based cultural and tourism industry cognitive analysis system according to claim 6, characterized in that: The personalized service unit specifically includes: Tourist portrait construction: Profile u =BuildProfile(I u ,C u ,B u ) In the formula, Profile u is the portrait of user u, I u is interest preference, C u For consumption habits, B u For behavior patterns.

10. The big data-based cultural and tourism industry cognitive analysis system according to claim 8, characterized in that: The visual display module specifically includes: Multi-dimensional data display unit: supports multiple chart types to meet the data display needs in different scenarios. Users can flexibly explore and analyze data by dragging fields and filtering conditions. It supports multi-dimensional drill-down and roll-up operations on data to gain in-depth understanding of data details. Real-time monitoring unit: supports real-time data refresh to ensure that users can obtain the latest data changes in a timely manner; By setting thresholds and alarm rules, data anomalies can be monitored in real time to help managers respond quickly; Data query and customization unit: supports users to query data based on the dimensions of time, location, and event, and quickly locate the required information; users can generate customized reports based on needs, and support exporting to images and data files; according to user roles and permission settings, control the scope of data access to ensure data security.

Images