Low-carbon tourism behavior monitoring platform

Abstract

The invention discloses a low-carbon tourism behavior monitoring platform, and the platform comprises a data collection layer which is responsible for collecting behavior data of tourists in a tourism process, and the behavior data come from an Internet of Things sensor and a mobile application; the data processing layer is used for cleaning, integrating and preprocessing the collected data, and integrating the processed data in a unified data warehouse; the data analysis layer is used for constructing a model by using a FoLDTree to identify and analyze a low-carbon tourism behavior mode of a tourist, evaluating the contribution degree of each feature to a low-carbon tourism behavior by using an LDA algorithm, screening out features most influencing the analysis of the low-carbon tourism behavior from the integrated data, and analyzing the screened features through the model constructed by the FoLDTree; the report generation layer is used for generating a low-carbon tourism behavior analysis report based on a result of the data analysis layer and performing visual display; and the user feedback layer collects feedback opinions of tourists and scenic spot managers and is used for optimizing functions and performance of the platform.

Description

Technical Field

[0001] The present invention relates to the technical field of low-carbon monitoring, and in particular to a low-carbon tourism behavior monitoring platform. Background Art

[0002] The design of the low-carbon tourism behavior monitoring platform aims to respond to the urgent needs of global climate change and environmental protection, and to promote the green transformation of the tourism industry through scientific and technological means. The platform provides data support and behavioral guidance for tourists, tourism companies and government departments by real-time monitoring and evaluating low-carbon behaviors in tourism activities, aiming to promote the development of low-carbon tourism, reduce the impact of tourism on the environment, and achieve sustainable development of the tourism industry. The low-carbon tourism behavior monitoring platform plays a significant role in enhancing tourists' environmental awareness, optimizing the allocation of tourism resources, promoting the green transformation of the tourism industry and enhancing the image of tourist destinations.

[0003] Existing low-carbon tourism behavior monitoring platforms often rely on traditional data analysis methods, such as statistical analysis and simple machine learning algorithms. These methods may not be able to accurately capture subtle changes and potential patterns in the data when dealing with complex, multi-dimensional data. Therefore, a low-carbon tourism behavior monitoring platform is proposed. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art that traditional data analysis methods may not be able to accurately capture subtle changes and potential laws in the data when processing complex and multi-dimensional data, and to propose a low-carbon tourism behavior monitoring platform.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A low-carbon tourism behavior monitoring platform, comprising:

[0007] Data collection layer: responsible for collecting tourists' behavioral data during the travel process, including travel methods, accommodation choices, energy consumption, carbon emissions, etc. The behavioral data comes from IoT sensors and mobile applications;

[0008] Data processing layer: cleans, integrates and preprocesses the collected data to ensure the accuracy and consistency of the data. The processed data will be integrated into a unified data warehouse for subsequent analysis;

[0009] Data analysis layer: Use FoLDTree to build a model to identify and analyze tourists' low-carbon tourism behavior patterns, use the LDA algorithm to evaluate the contribution of each feature to low-carbon tourism behavior, select the most influential features for low-carbon tourism behavior analysis from the integrated data, and analyze the selected features through the model built by FoLDTree;

[0010] Report generation layer: Based on the results of the data analysis layer, a low-carbon tourism behavior analysis report is generated and visualized in the form of charts, curves, etc.;

[0011] User feedback layer: collect feedback from tourists and scenic area managers to optimize the functions and performance of the platform.

[0012] The above technical solution further includes:

[0013] Furthermore, the IoT sensors include energy consumption monitoring sensors, carbon emission monitoring sensors and environmental monitoring sensors. The energy consumption monitoring sensors are installed on various facilities in the scenic area, such as lighting systems, air-conditioning systems, amusement facilities, etc., for real-time monitoring of the energy consumption of the facilities. The carbon emission monitoring sensors are deployed at key locations in the scenic area, such as major traffic arteries, large activity areas, etc., for measuring and recording carbon emissions to help assess the environmental impact of the scenic area. The environmental monitoring sensors are used to monitor the environmental quality of the scenic area and provide a scientific basis for low-carbon tourism.

[0014] Furthermore, the mobile application is responsible for collecting tourist behavior records as well as feedback and evaluation.

[0015] Furthermore, the data processing layer includes a data cleaning module, a data integration module and a data warehouse management module. The data cleaning module is responsible for cleaning the original data received from the data acquisition layer, the data integration module is responsible for integrating the cleaned data to form a unified data set, and the data warehouse management module is responsible for designing and managing the data warehouse and performing data storage and retrieval, including data warehouse structure design (such as defining tables, indexes, views, etc.), data storage strategies (such as partitioning, compression, backup, etc.), and data access control (such as permission management, data encryption, etc.).

[0016] Furthermore, the processing data is analyzed by using the FoLDTree algorithm, comprising the following steps:

[0017] Data preparation: Collect processed data, including information on tourists’ travel modes, accommodation choices, energy consumption, carbon emissions, and other dimensions, and use FoLDTree’s missing value processing mechanism to process the processed data;

[0018] Feature selection: LDA is used to evaluate the contribution of each feature to low-carbon tourism behavior, and the most influential features for low-carbon tourism behavior analysis are selected from the integrated data;

[0019] Assuming there are 10 features (such as travel mode, accommodation type, tour time, energy consumption, etc.), the FoLDTree algorithm first selects travel mode and accommodation type as the two most important features because they have the greatest impact on low-carbon tourism behavior;

[0020] Oblique segmentation analysis: Use FoLDTree’s efficient oblique segmentation capability to perform segmentation in feature space and capture complex decision boundaries in the data;

[0021] In the feature space, FoLDTree divides the data into multiple subsets according to travel modes and accommodation types, each of which represents a different low-carbon tourism behavior pattern;

[0022] Model training and validation: Use FoLDTree to build a model and validate it with validation set data. Through training, the FoLDTree model identifies and analyzes tourists' low-carbon travel behavior patterns. For example, tourists who choose public transportation are more likely to exhibit low-carbon behavior.

[0023] Result analysis and report generation: Based on the analysis results of the FoLDTree model, key features are extracted and an analysis report is generated.

[0024] Furthermore, the specific steps of the feature selection are:

[0025] Determination of initial feature set: Determine an initial feature set based on the needs of low-carbon tourism behavior analysis;

[0026] Application of LDA algorithm: In feature selection, the LDA algorithm is used to evaluate the contribution of each feature to low-carbon tourism behavior. The LDA algorithm evaluates the classification ability of the feature by calculating the inter-class scatter matrix and the intra-class scatter matrix of each feature. The larger the ratio of the inter-class scatter matrix to the intra-class scatter matrix, the higher the contribution of the feature to the classification. The calculation formula of the inter-class scatter matrix is:

[0027] Among them, S B is the inter-class scatter matrix, c is the number of classes, N i is the number of samples in the i-th class, μ i is the mean vector of the i-th class, μ is the mean vector of all samples; the intra-class scatter matrix calculation formula is Among them, S W is the intra-class scatter matrix, C i is the sample set of the i-th category, x is the sample vector; the contribution calculation formula is Among them, w is the weight vector of the feature;

[0028] Feature selection: Based on the output results of the LDA algorithm, each feature is sorted according to its contribution, and the top-ranked features are selected as input for building the model.

[0029] Furthermore, the specific steps of the oblique segmentation analysis are:

[0030] Feature space: including travel mode, accommodation type, tour time and energy consumption;

[0031] Oblique segmentation strategy: a nonlinear boundary was selected to divide the data, aiming to distinguish tourists with different low-carbon tourism behavior patterns;

[0032] Boundary determination: The optimal boundary is determined by calculating the information gain of each oblique cutting boundary. The information gain calculation formula is:

[0033] Where D is the data set, A is the feature, Values(A) is all possible values ​​of feature A, and D v is the sample subset in the data set whose feature A takes value v, Entropy(D) is the entropy of the data set D; the entropy calculation formula is Where c is the number of categories, p i is the probability of the i-th category in the dataset D;

[0034] Data segmentation: According to the optimal boundary, the data in the feature space is segmented into multiple subsets. For example, one subset may represent tourists who choose public transportation and green accommodation, and they show higher low-carbon tourism behavior;

[0035] Recursive analysis: For each subset, recursive analysis is continued to identify more refined low-carbon tourism behavior patterns.

[0036] Furthermore, the report generation layer includes a data analysis result receiving module, a report content generation module, a visualization design module, a report customization module and a report output and distribution module. The data analysis result receiving module is responsible for receiving the results from the data analysis layer, the report content generation module generates the content of the report based on the received data analysis results, the visualization design module is responsible for visually displaying the key data and information in the report content in the form of charts, curves, etc., the report customization module provides report customization function, and the report output and distribution module is responsible for outputting the generated report in an appropriate format (such as PDF, Word, Excel, etc.) and distributing it to relevant tourists and scenic area managers.

[0037] The present invention has the following beneficial effects:

[0038] In the present invention, the LDA algorithm is used to evaluate the contribution of each feature to low-carbon tourism behavior, and the features that are most relevant to low-carbon tourism behavior and unrelated to each other can be identified. Based on these features, FoLDTree can build a more accurate decision tree model for identifying and analyzing tourists' low-carbon behavior. This not only improves the accuracy of data analysis, but also enables scenic spots to obtain valuable insights more quickly, such as which travel modes and accommodation options contribute the most to low-carbon tourism. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a system block diagram of a low-carbon tourism behavior monitoring platform proposed by the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1 As shown, the present invention is a low-carbon tourism behavior monitoring platform, comprising:

[0042] Data collection layer: responsible for collecting tourists' behavioral data during the travel process, including travel methods, accommodation choices, energy consumption, carbon emissions, etc. The behavioral data comes from IoT sensors and mobile applications;

[0043] Data processing layer: cleans, integrates and preprocesses the collected data to ensure the accuracy and consistency of the data. The processed data will be integrated into a unified data warehouse for subsequent analysis;

[0044] Data analysis layer: Use FoLDTree to build a model to identify and analyze tourists' low-carbon tourism behavior patterns, use the LDA algorithm to evaluate the contribution of each feature to low-carbon tourism behavior, select the most influential features for low-carbon tourism behavior analysis from the integrated data, and analyze the selected features through the model built by FoLDTree;

[0045] Report generation layer: Based on the results of the data analysis layer, a low-carbon tourism behavior analysis report is generated and visualized in the form of charts, curves, etc.;

[0046] User feedback layer: collect feedback from tourists and scenic area managers to optimize the functions and performance of the platform.

[0047] In one embodiment, for the above-mentioned Internet of Things sensors, the Internet of Things sensors include energy consumption monitoring sensors, carbon emission monitoring sensors and environmental monitoring sensors. The energy consumption monitoring sensors are installed on various facilities in the scenic area, such as lighting systems, air-conditioning systems, amusement facilities, etc., for real-time monitoring of the energy consumption of the facilities. The carbon emission monitoring sensors are deployed at key locations in the scenic area, such as major traffic arteries, large activity areas, etc., for measuring and recording carbon emissions to help assess the environmental impact of the scenic area. The environmental monitoring sensors are used to monitor the environmental quality of the scenic area and provide a scientific basis for low-carbon tourism.

[0048] In one embodiment, for the above mobile application, the mobile application is responsible for collecting visitor behavior records, feedback and evaluation.

[0049] In one embodiment, for the above-mentioned data processing layer, the data processing layer includes a data cleaning module, a data integration module and a data warehouse management module. The data cleaning module is responsible for cleaning the original data received from the data acquisition layer, and the data integration module is responsible for integrating the cleaned data to form a unified data set. The data warehouse management module is responsible for designing and managing the data warehouse and performing data storage and retrieval, including data warehouse structure design (such as defining tables, indexes, views, etc.), data storage strategies (such as partitioning, compression, backup, etc.), and data access control (such as permission management, data encryption, etc.).

[0050] In one embodiment, for the above-mentioned use of the FoLDTree algorithm to analyze the processed data, the use of the FoLDTree algorithm to analyze the processed data includes the following steps:

[0051] Data preparation: Collect processed data, including information on tourists’ travel modes, accommodation choices, energy consumption, carbon emissions, and other dimensions, and use FoLDTree’s missing value processing mechanism to process the processed data;

[0052] Feature selection: LDA is used to evaluate the contribution of each feature to low-carbon tourism behavior, and the most influential features for low-carbon tourism behavior analysis are selected from the integrated data;

[0053] Assuming there are 10 features (such as travel mode, accommodation type, tour time, energy consumption, etc.), the FoLDTree algorithm first selects travel mode and accommodation type as the two most important features because they have the greatest impact on low-carbon tourism behavior;

[0054] Oblique segmentation analysis: Use FoLDTree’s efficient oblique segmentation capability to perform segmentation in feature space and capture complex decision boundaries in the data;

[0055] In the feature space, FoLDTree divides the data into multiple subsets according to travel modes and accommodation types, each of which represents a different low-carbon tourism behavior pattern;

[0056] Model training and validation: Use FoLDTree to build a model and validate it with validation set data. Through training, the FoLDTree model identifies and analyzes tourists' low-carbon travel behavior patterns. For example, tourists who choose public transportation are more likely to exhibit low-carbon behavior.

[0057] Result analysis and report generation: Based on the analysis results of the FoLDTree model, key features are extracted and an analysis report is generated.

[0058] In one embodiment, for the above feature selection, the specific steps of the feature selection are:

[0059] Determination of initial feature set: Determine an initial feature set based on the needs of low-carbon tourism behavior analysis;

[0060] Application of LDA algorithm: In feature selection, the LDA algorithm is used to evaluate the contribution of each feature to low-carbon tourism behavior. The LDA algorithm evaluates the classification ability of the feature by calculating the inter-class scatter matrix and the intra-class scatter matrix of each feature. The larger the ratio of the inter-class scatter matrix to the intra-class scatter matrix, the higher the contribution of the feature to the classification. The calculation formula of the inter-class scatter matrix is:

[0061] Among them, S B is the inter-class scatter matrix, c is the number of classes, N i is the number of samples in the i-th class, μ i is the mean vector of the i-th class, μ is the mean vector of all samples; the intra-class scatter matrix calculation formula is Among them, S W is the intra-class scatter matrix, C i is the sample set of the i-th category, x is the sample vector; the contribution calculation formula is Among them, w is the weight vector of the feature;

[0062] Feature selection: Based on the output results of the LDA algorithm, each feature is sorted according to its contribution, and the top-ranked features are selected as input for building the model.

[0063] In one embodiment, for the above-mentioned oblique segmentation analysis, the specific steps of the oblique segmentation analysis are:

[0064] Feature space: including travel mode, accommodation type, tour time and energy consumption;

[0065] Oblique segmentation strategy: a nonlinear boundary was selected to divide the data, aiming to distinguish tourists with different low-carbon tourism behavior patterns;

[0066] Boundary determination: The optimal boundary is determined by calculating the information gain of each oblique cutting boundary. The information gain calculation formula is:

[0067] Where D is the data set, A is the feature, Values(A) is all possible values ​​of feature A, and D v is the sample subset in the data set whose feature A takes value v, Entropy(D) is the entropy of the data set D; the entropy calculation formula is Where c is the number of categories, p i is the probability of the i-th category in the dataset D;

[0068] Data segmentation: According to the optimal boundary, the data in the feature space is segmented into multiple subsets. For example, one subset may represent tourists who choose public transportation and green accommodation, and they show higher low-carbon tourism behavior;

[0069] Recursive analysis: For each subset, recursive analysis is continued to identify more refined low-carbon tourism behavior patterns.

[0070] In one embodiment, for the above-mentioned report generation layer, the report generation layer includes a data analysis result receiving module, a report content generation module, a visualization design module, a report customization module and a report output and distribution module. The data analysis result receiving module is responsible for receiving the results from the data analysis layer, the report content generation module generates the content of the report based on the received data analysis results, the visualization design module is responsible for visually displaying the key data and information in the report content in the form of charts, curves, etc., the report customization module provides report customization function, and the report output and distribution module is responsible for outputting the generated report in an appropriate format (such as PDF, Word, Excel, etc.) and distributing it to relevant tourists and scenic spot managers.

[0071] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A low-carbon tourism behavior monitoring platform, characterized in that: include: Data collection layer: responsible for collecting tourists' behavioral data during the travel process, which comes from IoT sensors and mobile applications; Data processing layer: cleans, integrates and preprocesses the collected data. The processed data will be integrated into a unified data warehouse; Data analysis layer: Use FoLDTree to build a model to identify and analyze tourists' low-carbon tourism behavior patterns, use the LDA algorithm to evaluate the contribution of each feature to low-carbon tourism behavior, select the most influential features for low-carbon tourism behavior analysis from the integrated data, and analyze the selected features through the model built by FoLDTree; Report generation layer: Based on the results of the data analysis layer, a low-carbon tourism behavior analysis report is generated and displayed visually; User feedback layer: collect feedback from tourists and scenic area managers to optimize the functions and performance of the platform.

2. A low-carbon tourism behavior monitoring platform according to claim 1, characterized in that: The IoT sensors include energy consumption monitoring sensors, carbon emission monitoring sensors and environmental monitoring sensors. The energy consumption monitoring sensors are installed on various facilities in the scenic area to monitor the energy consumption of the facilities in real time. The carbon emission monitoring sensors are deployed at key locations in the scenic area to measure and record carbon emissions. The environmental monitoring sensors are used to monitor the environmental quality of the scenic area.

3. A low-carbon tourism behavior monitoring platform according to claim 1, characterized in that: The mobile application is responsible for collecting visitor behavior records as well as feedback and evaluations.

4. A low-carbon tourism behavior monitoring platform according to claim 1, characterized in that: The data processing layer includes a data cleaning module, a data integration module and a data warehouse management module. The data cleaning module is responsible for cleaning the original data received from the data acquisition layer. The data integration module is responsible for integrating the cleaned data to form a unified data set. The data warehouse management module is responsible for designing and managing the data warehouse and performing data storage and retrieval, including data warehouse structure design, data storage strategy and data access control.

5. A low-carbon tourism behavior monitoring platform according to claim 1, characterized in that: The FoLDTree algorithm is used to analyze the processed data, comprising the following steps: Data preparation: collect the processed data and use FoLDTree's missing value processing mechanism to process the processed data; Feature selection: LDA is used to evaluate the contribution of each feature to low-carbon tourism behavior, and the most influential features for low-carbon tourism behavior analysis are selected from the integrated data; Oblique segmentation analysis: Use FoLDTree’s efficient oblique segmentation capability to perform segmentation in feature space and capture complex decision boundaries in the data; Model training and validation: Use FoLDTree to build a model and validate it with validation set data. Through training, the FoLDTree model can identify and analyze tourists' low-carbon tourism behavior patterns; Result analysis and report generation: Based on the analysis results of the FoLDTree model, key features are extracted and an analysis report is generated.

6. A low-carbon tourism behavior monitoring platform according to claim 5, characterized in that: The specific steps of feature selection are: Determination of initial feature set: Determine an initial feature set based on the needs of low-carbon tourism behavior analysis; Application of LDA algorithm: In feature selection, the LDA algorithm is used to evaluate the contribution of each feature to low-carbon tourism behavior. The LDA algorithm evaluates the classification ability of the feature by calculating the inter-class scatter matrix and the intra-class scatter matrix of each feature. The larger the ratio of the inter-class scatter matrix to the intra-class scatter matrix, the higher the contribution of the feature to the classification. The calculation formula of the inter-class scatter matrix is: Among them, S B is the inter-class scatter matrix, c is the number of classes, N i is the number of samples in the i-th class, μ i is the mean vector of the i-th class, μ is the mean vector of all samples; the intra-class scatter matrix calculation formula is Among them, S w is the intra-class scatter matrix, C i is the sample set of the i-th category, x is the sample vector; the contribution calculation formula is Among them, w is the weight vector of the feature; Feature selection: Based on the output results of the LDA algorithm, each feature is sorted according to its contribution, and the top-ranked features are selected as input for building the model.

7. A low-carbon tourism behavior monitoring platform according to claim 5, characterized in that: The specific steps of the oblique cutting analysis are: Feature space: including travel mode, accommodation type, tour time and energy consumption; Oblique segmentation strategy: a nonlinear boundary was selected to divide the data, aiming to distinguish tourists with different low-carbon tourism behavior patterns; Boundary determination: The optimal boundary is determined by calculating the information gain of each oblique cutting boundary. The information gain calculation formula is: Where D is the data set, A is the feature, Values(A) is all possible values ​​of feature A, Dv is the sample subset in the data set where feature A takes value v, and Entropy(D) is the entropy of the data set D. The entropy is calculated as Where c is the number of categories, p i is the probability of the i-th category in the dataset D; Data segmentation: Data in the feature space is segmented into multiple subsets based on the optimal boundary; Recursive analysis: For each subset, recursive analysis is continued to identify more refined low-carbon tourism behavior patterns.

8. A low-carbon tourism behavior monitoring platform according to claim 1, characterized in that: The report generation layer includes a data analysis result receiving module, a report content generation module, a visualization design module, a report customization module and a report output and distribution module. The data analysis result receiving module is responsible for receiving the results from the data analysis layer. The report content generation module generates the content of the report based on the received data analysis results. The visualization design module is responsible for visually displaying the key data and information in the report content. The report customization module provides a report customization function. The report output and distribution module is responsible for outputting the generated report and distributing it to relevant tourists and scenic area managers.

Images