Intelligent scenic spot multi-dimensional data monitoring and analyzing method based on improved deep learning
By improving the combination of deep learning algorithms, graph convolutional networks and dynamic Bayesian networks, the problem of multidimensional data acquisition and analysis in traditional scenic spot management is solved, efficient and accurate data monitoring and abnormal identification are achieved, and the efficiency of scenic spot management is improved. Experience with tourists.
Patent Information
- Application Number
- CN202411036842.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-07-31
AI Technical Summary
In traditional scenic spot management, there are problems such as data integration difficulties, low data processing efficiency, low resolution accuracy and insufficient data noise processing capabilities, which cannot meet the needs of smart scenic spots for real-time monitoring and efficient management.
The improved deep learning algorithm is adopted, combined with graph convolutional networks and dynamic Bayesian networks, and the multidimensional data is cleaned, standardized and analyzed, and analytical models are built for scenic spots, monitoring and identifying abnormal situations in real time, and decision-making support is provided.
It improves the accuracy and processing speed of data analysis, enhances the robustness of the model, can timely identify abnormal situations and generate accurate alarms, provides more comprehensive decision-making support, and improves the management efficiency of scenic spots and the experience of tourists.
Smart Images

Figure CN119005506A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart scenic spots, and in particular to a multi-dimensional data monitoring and analysis method for smart scenic spots based on improved deep learning. Background Art
[0002] With the rapid development of tourism, the concept of smart scenic spots has gradually become an important means to improve scenic spot management efficiency and tourist experience. In the process of building smart scenic spots, the collection, integration and analysis of multidimensional data is one of the key technologies. In traditional scenic spot management, the collection of multidimensional data often relies on independent sensor systems. The data formats between these systems are not unified, which makes data integration difficult and cannot reflect the overall situation of the scenic spot in real time and accurately. In addition, the data processing efficiency of traditional data acquisition systems is low and cannot meet the needs of real-time monitoring and analysis.
[0003] In the existing technology, multi-dimensional data collection technology mainly relies on a single or a small number of types of sensors, such as using only tourist flow sensors or environmental monitoring sensors. This method has the following defects: first, a single type of sensor cannot fully reflect the multi-dimensional state of the scenic spot, resulting in one-sided monitoring data; second, the data format and communication protocol of different types of sensors are not unified, which increases the difficulty of data integration; finally, traditional data collection and transmission systems are prone to delays and data loss when facing large-scale data, and cannot meet the high requirements of smart scenic spots for real-time data monitoring.
[0004] In terms of data analysis, although existing deep learning models have performed well in areas such as image recognition and natural language processing, they still have many shortcomings when processing complex and multi-dimensional data. When traditional deep learning models are applied in complex environments such as scenic spots, they often face the following problems: First, the model training speed is slow, especially when the amount of multi-dimensional data is large, the training time increases significantly; second, the analysis accuracy is low, and traditional models are difficult to effectively identify abnormal situations or make accurate predictions, especially in scenic spots with large data noise and complex environments, the model's robustness is poor; third, the model is easily affected by external interference, such as a sudden increase in the number of tourists, weather changes, etc., resulting in unstable analysis results.
[0005] The existing technology also has the problem of insufficient data preprocessing capabilities. The multidimensional data in the scenic area often contains a lot of noise and invalid data. Traditional data cleaning and standardization methods cannot completely remove these invalid information, which affects the accuracy of subsequent data analysis. In addition, the standardized processing of different sensor data is also a major problem. The lack of a unified and effective standardized processing method leads to inconsistencies in data formats and units, further increasing the difficulty of data integration and analysis. Summary of the invention
[0006] One purpose of the present invention is to propose a method for multi-dimensional data monitoring and analysis of smart scenic spots based on improved deep learning. The present invention realizes efficient management and precise monitoring of smart scenic spots, and has significant technical advantages and application value.
[0007] According to an embodiment of the present invention, a method for monitoring and analyzing multi-dimensional data of a smart scenic spot based on improved deep learning comprises the following steps:
[0008] S1. Deploy a variety of IoT sensors in the scenic area to collect real-time information on tourist flow, environmental parameters, and facility usage to build a multidimensional data set;
[0009] S2, cleaning the collected original multidimensional data set to remove noise and invalid data;
[0010] S3. Standardize multidimensional data sets from different sources and unify data formats and units;
[0011] S4. Construct a parsing model for multidimensional data sets based on improved deep learning algorithms;
[0012] S5. Use analytical models to analyze real-time data in the scenic area, identify abnormal situations and issue alarms in a timely manner;
[0013] S6. Predict the trend of tourist flow and environmental changes in the future by analyzing historical data;
[0014] S7, provides real-time monitoring function for various data of scenic spots, and managers can view the operation status of scenic spots in real time through the visual interface;
[0015] S8. When the system detects an abnormal situation, it automatically triggers the alarm mechanism and sends a notification to the relevant management personnel;
[0016] S9. Provide decision support for scenic area managers based on data parsing and analysis results;
[0017] S10. Provide intelligent navigation and real-time information push services based on the analysis of tourists’ behaviors and preferences.
[0018] Optionally, S1 includes the following sub-steps:
[0019] S11. Deploy a variety of IoT sensors at key locations within the scenic area, including visitor flow sensors, environmental parameter sensors, and facility usage sensors;
[0020] S12. Real-time collection of tourist flow data D t , Environmental parameter data E t , Facility usage data F t ;
[0021] S13, the tourist flow data D t Including the number of tourists entering the scenic area N in (t) and the number of tourists leaving the scenic area N out (t):
[0022] D t = {N in (t), N out (t)};
[0023] S14, the environmental parameter data E t Including temperature T(t), humidity H(t), air quality index AQI(t):
[0024] E t ={T(t), H(t), AQI(t)};
[0025] S15, the facility usage data F t Including the usage status of the facility S i (t) and the fault record of the facility R i (t):
[0026] F t ={S i (t), R i (t)};
[0027] S16, collect the tourist flow data D through the wireless network or wired network t , Environmental parameter data E t , Facility usage data F t Transmit to a central processing system;
[0028] S17, the central processing system receives and stores the data, and constructs a multidimensional data set MDS:
[0029] MDS={D t , E t , F t}.
[0030] Optionally, S4 includes the following sub-steps:
[0031] S41, collect and preprocess multidimensional data sets MDS, including data cleaning and standardization;
[0032] MDScl ean ={Clean(D t ), Clean(E t ), Clean(F t )};
[0033] MDS std= {Std(D t ), Std(E t ), Std(F t )};
[0034] Among them, Clean(·) represents the cleaning process to remove noise and invalid data, and Std(·) represents the standardization process to unify the data format and unit;
[0035] S42. Design and improve deep learning algorithms, including optimizing neural network structures, loss functions, and training methods;
[0036] S43, inputting the preprocessed multidimensional data set into the improved deep learning model for training, and constructing an analysis model AM for analyzing the multidimensional data set;
[0037] S44. Improve the deep learning model by using a combination of graph convolutional networks and dynamic Bayesian networks to optimize the parsing accuracy and data processing capabilities of the parsing model AM;
[0038] H gcn =GCN(MDS std ; W gcn );
[0039] S45. The graph convolution network captures the spatial and temporal dependencies in the scenic area data, and defines the graph convolution layer parameters as W gcn , the output feature is represented as H gcn :
[0040]
[0041] in, represents the adjacency matrix with self-loops added, yes The degree matrix of is the input feature matrix of the first layer, σ is the activation function; A represents the adjacency matrix, and I represents the identity matrix;
[0042] S46, Dynamic Bayesian Network Modeling Data Time-varying Characteristics and Potential Structure, Define the Bayesian Network Node and Edge Weight Matrices as W node and W edge , the output potential is represented as z:
[0043]
[0044] Among them, z i The ith node representing the latent variable, Pa(z i ) represents node z i The parent node set of
[0045]
[0046] in, Represents the mean and standard deviation of the i-th node;
[0047] S47, the output of the graph convolutional network and the dynamic Bayesian network are fused through the fusion layer to obtain the comprehensive feature representation H fuse :
[0048] H fuse =γH gcn +δz;
[0049] Among them, γ and δ represent fusion weights;
[0050] S48, optimizing the model parameters through the back propagation algorithm and gradient descent to obtain the final analytical model AM;
[0051]
[0052] in, represents the basic loss function, Y represents the actual label, λ represents the regularization parameter, α and β represent the weights of the additional loss terms; Risk(H fuse ,S safety ) represents the evaluation of the safety risk of the scenic spot by the analytical model, Satisfaction (H fuse , S user ) represents the evaluation of tourist satisfaction by the analytical model.
[0053] Optionally, the S48 includes the following sub-steps:
[0054] S481. Define the basic loss function Among them, H fuse is the fusion feature representation, Y is the actual label, and the loss function is used to measure the difference between the predicted value and the actual value:
[0055]
[0056] Where N is the number of samples, and Loss(·) is the loss calculation function;
[0057] S482. Define regularization terms to avoid model overfitting, including weight regularization terms for graph convolutional networks and dynamic Bayesian networks:
[0058] Reg(W gcn , W node )=λ(||W gcn || 2 +||W node || 2 );
[0059] Among them, λ is the regularization parameter, ||W gcn || 2 and ||W node || 2 are the second norms of the weight matrices respectively;
[0060] S483. Define additional loss items to evaluate the security risk and user satisfaction of the analytical model:
[0061]
[0062] Among them, α 1 and β 1 is the weight of the additional loss term, S safety and S user They are the evaluation criteria for security risk and user satisfaction respectively;
[0063] S484. Construct a comprehensive loss function that integrates basic loss, regularization term and additional loss term;
[0064] S485. Calculate the gradient of the loss function to the model parameters through the back propagation algorithm:
[0065]
[0066] S486. Update model parameters using gradient descent optimization algorithm:
[0067]
[0068] Among them, η represents the learning rate, and the parameters of the analytical model AM are optimized through repeated iterations until the loss function converges.
[0069] Optionally, S5 includes the following sub-steps:
[0070] S51, real-time data MDS in the scenic area real Input into the constructed analytical model AM;
[0071] S52, the analytical model AM processes the real-time data and extracts the feature representation H real :
[0072] H real =AM(MDS real );
[0073] S53, the extracted features are represented as H real Compare with the preset threshold or reference value, and define the threshold as T threshold,i and T threshold , j , if H real Any element h in iThe following conditions are met:
[0074] h i >T threshold,i or i <T threshold,j ;
[0075] It is considered an abnormal situation;
[0076] S54, classifying abnormal situations and identifying specific abnormal types, including crowded tourists, facility failures, abnormal environmental parameters, etc.;
[0077] S55. Using the preset alarm mechanism, according to the identified abnormal type, an alarm signal is generated and the relevant management personnel are notified in a timely manner;
[0078] S56. The alarm signal includes the abnormality type, occurrence time, specific location and related data information. The alarm signal is defined as:
[0079] A signal ={Type: T type , Time: T time , Location: L location ,Data:D data};
[0080] S57, sending the alarm signal to the scenic area management system via a wireless network or a wired network, and recording it in a system log;
[0081] S58. According to the alarm signal, the status information in the scenic area management system is updated in real time and displayed on the visual interface, so that the management personnel can check and handle abnormal situations in time.
[0082] Optionally, the S52 includes the following sub-steps:
[0083] S521, real-time data MDS real Standardization is done to make it meet the input requirements of the analytical model AM. The standardized data is represented as MDS real_std ;
[0084] S522, standardize the real-time data MDS real_std Input to the input layer of the analytical model AM, and define the input layer weight as W in and the bias is b in , the output of the input layer is calculated as:
[0085]
[0086] Among them, σ represents the nonlinear activation function, and n is the number of nodes in the input layer;
[0087] S523, input layer output Hin Feature extraction is performed through multiple hidden layers, and the weight and bias of each hidden layer are W l and b l , the output of the lth layer is represented as H l :
[0088]
[0089] Among them, φ represents the nonlinear activation function, m l-1 is the number of nodes in the l-1th layer;
[0090] S524, the output H of the last hidden layer l Input to the output layer, define the output layer weight as W out and the bias is b out , calculate the feature representation H of the output layer real :
[0091]
[0092] S525. In each layer of calculation, apply the optimized back propagation algorithm to calculate the loss function according to the actual label Y And adjust the weights and biases according to the gradient descent algorithm:
[0093]
[0094] S526, through multiple iterations of training and optimization, the output feature representation H of the analytical model AM is finally obtained real , used for subsequent abnormal situation identification and alarm.
[0095] Optionally, the S53 includes the following sub-steps:
[0096] S531, the extracted features are represented as H real With the pre-set threshold vector T threshold Compare item by item and define each feature representation h i and threshold T threshold,i ;
[0097] S532, if the feature represents h i Exceeds the preset upper threshold or below the lower threshold It is considered an abnormal situation if:
[0098] or
[0099] S533, for each feature h i Classify the abnormal situations, identify the specific abnormal types, and define the abnormal type set as Etype , including the following categories:
[0100] E type ={tourist crowding, facility failure, abnormal environmental parameters};
[0101] S534, set the corresponding alarm level A for each abnormal type level , divided into multiple levels according to the severity and impact range of the abnormality, and the alarm level set is defined as A level , including the following levels:
[0102] A level ={Level 1 alarm, Level 2 alarm, Level 3 alarm};
[0103] S535. Generate an alarm signal according to the identified abnormal type and alarm level. The alarm signal is defined as: A signal ={Type: E type , Level: A level , Time: T time , Location: L location ,Data:D data};
[0104] S536: When generating an alarm signal, record the specific time when the abnormality occurs T time Specific location L location And related data information D data .
[0105] The beneficial effects of the present invention are:
[0106] (1) The present invention adopts an improved deep learning algorithm, combined with a graph convolutional network and a dynamic Bayesian network, to improve the training speed and analysis accuracy of the analytical model. The combination of the two significantly enhances the robustness of the analytical model in complex environments. By analyzing the real-time data in the scenic area through the constructed analytical model, abnormal situations can be identified in a timely manner and an alarm signal can be generated. The alarm signal includes the abnormality type, occurrence time, specific location and related data information to ensure the accuracy and timeliness of the alarm.
[0107] (2) During the model training process, the present invention constructs a comprehensive loss function, including basic loss, regularization term and additional loss term. The basic loss function is used to measure the difference between the predicted value and the actual value, the regularization term avoids overfitting of the model, and the additional loss term evaluates the safety risk and user satisfaction of the parsing model. Through the optimized back propagation algorithm and gradient descent algorithm, the loss function is calculated according to the actual label, and the weights and biases are adjusted to ensure that the model is continuously optimized in multiple iterative training. The application of this comprehensive loss function enables the model to not only accurately parse data, but also effectively evaluate the safety risks and user satisfaction of the scenic spot, providing more comprehensive decision support. BRIEF DESCRIPTION OF THE DRAWINGS
[0108] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0109] Figure 1 A flowchart of a method for monitoring and analyzing multi-dimensional data of a smart scenic spot based on improved deep learning proposed by the present invention;
[0110] Figure 2 This is a structural schematic diagram of an improved deep learning model for a smart scenic spot multi-dimensional data monitoring and analysis method based on improved deep learning proposed in the present invention. DETAILED DESCRIPTION
[0111] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.
[0112] refer to Figure 1 , a smart scenic spot multi-dimensional data monitoring and analysis method based on improved deep learning, comprising the following steps:
[0113] S1. Deploy a variety of IoT sensors in the scenic area to collect real-time information on tourist flow, environmental parameters, and facility usage to build a multidimensional data set;
[0114] S2, cleaning the collected original multidimensional data set to remove noise and invalid data;
[0115] S3. Standardize multidimensional data sets from different sources and unify data formats and units;
[0116] S4. Construct a parsing model for multidimensional data sets based on improved deep learning algorithms;
[0117] S5. Use analytical models to analyze real-time data in the scenic area, identify abnormal situations and issue alarms in a timely manner;
[0118] S6. Predict the trend of tourist flow and environmental changes in the future by analyzing historical data;
[0119] S7, provides real-time monitoring function for various data of scenic spots, and managers can view the operation status of scenic spots in real time through the visual interface;
[0120] S8. When the system detects an abnormal situation, it automatically triggers the alarm mechanism and sends a notification to the relevant management personnel;
[0121] S9. Provide decision support for scenic area managers based on data parsing and analysis results;
[0122] S10. Provide intelligent navigation and real-time information push services based on the analysis of tourists’ behaviors and preferences.
[0123] In this implementation, S1 includes the following sub-steps:
[0124] S11. Deploy a variety of IoT sensors at key locations within the scenic area, including visitor flow sensors, environmental parameter sensors, and facility usage sensors;
[0125] S12. Real-time collection of tourist flow data D t , Environmental parameter data E t , Facility usage data F t ;
[0126] S13. Tourist flow data D t Including the number of tourists entering the scenic area N in (t) and the number of tourists leaving the scenic area N out (t):
[0127] D t = {N in (t), N out (t)};
[0128] S14, Environmental parameter data E t Including temperature T(t), humidity H(t), air quality index AQI(t):
[0129] E t ={T(t), H(t), AQI(t)};
[0130] S15. Facility usage data F t Including the usage status of the facility S i (t) and the fault record of the facility R i (t):
[0131] F t ={S i (t), Ri (t)};
[0132] S16, collect the tourist flow data D through the wireless network or wired network t , Environmental parameter data E t , Facility usage data F t Transmit to a central processing system;
[0133] S17. The central processing system receives and stores data and constructs a multidimensional data set MDS:
[0134] MDS={D t , E t , F t}.
[0135] In this implementation, S4 includes the following sub-steps:
[0136] S41, collect and preprocess multidimensional data sets MDS, including data cleaning and standardization;
[0137] MDS clean ={Clean(D t ), Clean(E t ), Clean(F t )};
[0138] MDS std = {Std(D t ), Std(E t ), Std(F t )};
[0139] Among them, Clean(·) represents the cleaning process to remove noise and invalid data, and Std(·) represents the standardization process to unify the data format and unit;
[0140] S42. Design and improve deep learning algorithms, including optimizing neural network structures, loss functions, and training methods;
[0141] S43, inputting the preprocessed multidimensional data set into the improved deep learning model for training, and constructing an analysis model AM for analyzing the multidimensional data set;
[0142] S44. Improve the deep learning model by using a combination of graph convolutional networks and dynamic Bayesian networks to optimize the parsing accuracy and data processing capabilities of the parsing model AM;
[0143] H gcn =GCN(MDS std ; W gcn );
[0144] S45. The graph convolution network captures the spatial and temporal dependencies in the scenic area data, and defines the graph convolution layer parameters as W gcn , the output feature is represented as H gcn :
[0145]
[0146] in, represents the adjacency matrix with self-loops added, yes The degree matrix of is the input feature matrix of the lth layer, σ is the activation function; A represents the adjacency matrix, and I represents the identity matrix;
[0147] S46, Dynamic Bayesian Network Modeling Data Time-varying Characteristics and Potential Structure, Define the Bayesian Network Node and Edge Weight Matrices as W node and W edge , the output potential is represented as z:
[0148]
[0149] Among them, z i The ith node representing the latent variable, Pa(z i ) represents node z i The parent node set of
[0150]
[0151] in, Represents the mean and standard deviation of the i-th node;
[0152] S47, the output of the graph convolutional network and the dynamic Bayesian network are fused through the fusion layer to obtain the comprehensive feature representation H fuse :
[0153] H fuse =γH gcn +δz;
[0154] Among them, γ and δ represent fusion weights;
[0155] S48, optimizing the model parameters through the back propagation algorithm and gradient descent to obtain the final analytical model AM;
[0156]
[0157] in, represents the basic loss function, Y represents the actual label, λ represents the regularization parameter, α and β represent the weights of the additional loss terms; Risk(H fuse ,S safety) represents the evaluation of the safety risk of the scenic spot by the analytical model, Satisfaction (H fuse , S user ) represents the evaluation of tourist satisfaction by the analytical model.
[0158] In this implementation, S48 includes the following sub-steps:
[0159] S481. Define the basic loss function Among them, H fuse is the fusion feature representation, Y is the actual label, and the loss function is used to measure the difference between the predicted value and the actual value:
[0160]
[0161] Where N is the number of samples, and Loss(·) is the loss calculation function;
[0162] S482. Define regularization terms to avoid model overfitting, including weight regularization terms for graph convolutional networks and dynamic Bayesian networks:
[0163] Reg(W gcn , W node )=λ(||W gcn || 2 +||W node || 2 );
[0164] Among them, λ is the regularization parameter, ||W gcn || 2 and ||v node || 2 are the second norms of the weight matrices respectively;
[0165] S483. Define additional loss items to evaluate the security risk and user satisfaction of the analytical model:
[0166]
[0167] Among them, α 1 and β 1 is the weight of the additional loss term, S safety and S user They are the evaluation criteria for security risk and user satisfaction respectively;
[0168] S484. Construct a comprehensive loss function that integrates basic loss, regularization term and additional loss term;
[0169] S485. Calculate the gradient of the loss function to the model parameters through the back propagation algorithm:
[0170]
[0171] S486. Update model parameters using gradient descent optimization algorithm:
[0172]
[0173] Among them, η represents the learning rate, and the parameters of the analytical model AM are optimized through repeated iterations until the loss function converges.
[0174] In this implementation, S5 includes the following sub-steps:
[0175] S51, real-time data MDS in the scenic area real Input into the constructed analytical model AM;
[0176] S52, the analytical model AM processes the real-time data and extracts the feature representation H real :
[0177] H real =AM(MDS real );
[0178] S53, the extracted features are represented as H real Compare with the preset threshold or reference value, and define the threshold as T threshold,i and T threshold ,j, if H real Any element h in i The following conditions are met:
[0179] h i >T threshold,i or i <T threshold,j ;
[0180] It is considered an abnormal situation;
[0181] S54, classifying abnormal situations and identifying specific abnormal types, including crowded tourists, facility failures, abnormal environmental parameters, etc.;
[0182] S55. Using the preset alarm mechanism, according to the identified abnormal type, an alarm signal is generated and the relevant management personnel are notified in a timely manner;
[0183] S56. The alarm signal includes the abnormality type, occurrence time, specific location and related data information. The alarm signal is defined as:
[0184] A signal ={Type: T type , Time: T time , Location: L location ,Data:D data};
[0185] S57, sending the alarm signal to the scenic area management system via a wireless network or a wired network, and recording it in a system log;
[0186] S58. According to the alarm signal, the status information in the scenic area management system is updated in real time and displayed on the visual interface, so that the management personnel can check and handle abnormal situations in time.
[0187] In this implementation, S52 includes the following sub-steps:
[0188] S521, real-time data MDS real Standardization is done to make it meet the input requirements of the analytical model AM. The standardized data is represented as MDS real_std ;
[0189] S522, standardize the real-time data MDS real_std Input to the input layer of the analytical model AM, and define the input layer weight as W in and the bias is b in , the output of the input layer is calculated as:
[0190]
[0191] Among them, σ represents the nonlinear activation function, and n is the number of nodes in the input layer;
[0192] S523, input layer output H in Feature extraction is performed through multiple hidden layers, and the weight and bias of each hidden layer are W l and b l , the output of the first layer is represented as H l :
[0193]
[0194] Among them, φ represents the nonlinear activation function, m l-1 is the number of nodes in the l-1th layer;
[0195] S524, the output H of the last hidden layer l Input to the output layer, define the output layer weight as W out and the bias is b out , calculate the feature representation H of the output layer real :
[0196]
[0197] S525. In each layer of calculation, apply the optimized back propagation algorithm to calculate the loss function according to the actual label Y And adjust the weights and biases according to the gradient descent algorithm:
[0198]
[0199]
[0200] S526, through multiple iterations of training and optimization, the output feature representation H of the analytical model AM is finally obtained real , used for subsequent abnormal situation identification and alarm.
[0201] In this implementation, S53 includes the following sub-steps:
[0202] S531, the extracted features are represented as H real With the pre-set threshold vector T threshold Compare item by item and define each feature representation h i and threshold T threshold,i ;
[0203] S532, if the feature represents h i Exceeds the preset upper threshold or below the lower threshold It is considered an abnormal situation if:
[0204] or
[0205] S533, for each feature h i Classify the abnormal situations, identify the specific abnormal types, and define the abnormal type set as E type , including the following categories:
[0206] E type ={tourist crowding, facility failure, abnormal environmental parameters};
[0207] S534, set the corresponding alarm level A for each abnormal type level , divided into multiple levels according to the severity and impact range of the abnormality, and the alarm level set is defined as A level , including the following levels:
[0208] A level ={Level 1 alarm, Level 2 alarm, Level 3 alarm};
[0209] S535. Generate an alarm signal according to the identified abnormality type and alarm level, and define the alarm signal as:
[0210] A signal ={Type: E type , Level: A level , Time: T time , Location: Llocation ,Data:D data};
[0211] S536: When generating an alarm signal, record the specific time when the abnormality occurs T time Specific location L location And related data information D data .
[0212] Embodiment 1:
[0213] In order to verify the effectiveness of the multi-dimensional data monitoring and analysis method of the smart scenic spot based on improved deep learning, a large tourist scenic spot in XX city was selected as the experimental scene. The scenic spot covers a large area and receives millions of tourists every year. There are many important attractions, service facilities and rest areas in the scenic spot. Due to the large number of tourists and their wide distribution, the management and monitoring of the scenic spot is difficult, so an efficient and accurate monitoring and analysis method is needed.
[0214] In the scenic area, a variety of IoT sensors are deployed, including tourist flow sensors, environmental parameter sensors and facility usage sensors. These sensors are installed near the main entrance, important scenic spots, rest areas and service facilities of the scenic area to ensure that data such as tourist flow, temperature, humidity, air quality index and facility usage status can be collected in real time and comprehensively.
[0215] During a weekend, the number of tourists in the scenic area increased significantly. Traditional monitoring methods mainly rely on manual inspections and data from a single sensor, which cannot reflect the overall situation of the scenic area in real time and accurately. Especially during the peak tourist season, the data processing efficiency is low and abnormal situations cannot be discovered and handled in time. The method of the present invention can efficiently integrate multiple sensor data, monitor multi-dimensional data in the scenic area in real time, and accurately analyze it through an improved deep learning algorithm.
[0216] The improved deep learning algorithm of the present invention includes a combination of graph convolutional networks and dynamic Bayesian networks. The graph convolutional network is used to capture the spatial and temporal dependencies in the data, while the dynamic Bayesian network is used to model the time-varying characteristics and potential structure of the data. This combination enables the parsing model to have higher accuracy and robustness when processing complex, multi-dimensional data.
[0217] During the specific experiment, the method of the present invention successfully identified multiple abnormal situations. For example, in an area with dense tourists, the system detected a sudden increase in tourist flow, exceeding the preset safety threshold. The system immediately generated an alarm signal and notified the scenic area management staff to promptly guide tourists, avoiding possible crowding and trampling incidents. Another example is that near a tourist facility, the environmental sensor detected a sharp increase in the air quality index. The system identified this abnormal situation and quickly notified the relevant departments to investigate and deal with it, ensuring the health and safety of tourists.
[0218] In order to evaluate the effectiveness of the method of the present invention, the application effects of the traditional method and the method of the present invention in the same scenic spot were compared. The following Table 1 is the specific data comparison results:
[0219] Table 1 Comparison data between traditional method and the method of the present invention
[0220] Data Category Traditional methods Method of the present invention Visitor flow monitoring 50% 95% Environmental parameter monitoring 60% 98% Facility usage monitoring 55% 97% Abnormal situation recognition rate 40% 92% Data processing efficiency 70% 98% Safety accident rate 5 up / month 1 from / month
[0221] As can be seen from Table 1, the traditional method has great deficiencies in monitoring tourist flow, environmental parameters and facility usage, and the recognition rate of abnormal situations is also low. In contrast, the method of the present invention shows significant advantages in all aspects, especially in the recognition and processing of abnormal situations, reaching a recognition rate of 92%, greatly reducing the incidence of safety accidents in scenic spots.
[0222] Specifically, in terms of tourist flow monitoring, traditional methods mainly rely on manual statistics and data from a single sensor, with limited monitoring coverage and untimely data updates. The method of the present invention collects data in real time through multiple sensors and uses an improved deep learning model for analysis, which can accurately monitor tourist flow in each period. Experimental data show that after adopting the method of the present invention, the accuracy of tourist flow monitoring has increased from 50% of the traditional method to 95%.
[0223] In terms of environmental parameter monitoring, traditional methods mainly use a small number of environmental sensors for monitoring, and the data collection range is limited, which cannot fully reflect the environmental conditions in the scenic area. After adopting the method of the present invention, by deploying multiple environmental sensors, real-time data such as temperature, humidity and air quality index are collected, and through data preprocessing and deep learning analysis, the accuracy of environmental parameter monitoring is increased from 60% of the traditional method to 98%.
[0224] In terms of facility usage monitoring, traditional methods mainly rely on inspection records of facility managers, and data is not updated in a timely manner, which cannot reflect the usage status and fault conditions of facilities in real time. The method of the present invention collects data in real time through facility usage sensors and uses deep learning models for analysis. The accuracy of facility usage monitoring is increased from 55% of traditional methods to 97%.
[0225] In terms of abnormal situation identification, traditional methods have a low recognition rate of abnormal situations due to their single data source and low processing efficiency, and they often fail to detect and handle abnormal situations in a timely manner. After adopting the method of the present invention, through real-time monitoring of multi-dimensional data and accurate analysis of deep learning models, the recognition rate of abnormal situations has increased from 40% of traditional methods to 92%. For example, in a certain experiment, the system successfully identified multiple abnormal situations such as crowded tourists and abnormal air quality, and generated alarm signals in a timely manner to notify relevant departments for processing, effectively avoiding the occurrence of safety accidents.
[0226] In terms of data processing efficiency, the method of the present invention is significantly superior to the traditional method. Due to the decentralized nature of data collection and processing, the traditional method has low processing efficiency and is prone to delays and data loss. The method of the present invention achieves real-time monitoring and analysis of multidimensional data through efficient data collection and integration, combined with an improved deep learning algorithm, and improves data processing efficiency from 70% of the traditional method to 98%.
[0227] Through the above experiments and data comparisons, it can be seen that the multi-dimensional data monitoring and analysis method for smart scenic spots based on improved deep learning of the present invention has significantly improved the management efficiency of scenic spots and the tourist experience, and solved the problems of inaccurate multi-dimensional data collection and integration and poor application effect of deep learning models in complex environments existing in traditional methods. It has broad application prospects and practical value.
[0228] The present invention adopts an improved deep learning algorithm, combined with graph convolutional networks and dynamic Bayesian networks, to improve the training speed and analysis accuracy of the analytical model. The combination of the two significantly enhances the robustness of the analytical model in complex environments. By analyzing the real-time data in the scenic area through the constructed analytical model, abnormal situations can be identified in time and an alarm signal can be generated. The alarm signal includes the abnormality type, occurrence time, specific location and related data information to ensure the accuracy and timeliness of the alarm.
[0229] During the model training process, the present invention constructs a comprehensive loss function, including basic loss, regularization term and additional loss term. The basic loss function is used to measure the difference between the predicted value and the actual value, the regularization term avoids overfitting of the model, and the additional loss term evaluates the safety risk and user satisfaction of the parsing model. Through the optimized back propagation algorithm and gradient descent algorithm, the loss function is calculated according to the actual label, and the weight and bias are adjusted to ensure that the model is continuously optimized in multiple iterative training. The application of this comprehensive loss function enables the model to not only accurately parse data, but also effectively evaluate the safety risk and user satisfaction of the scenic spot, and provide more comprehensive decision support.
[0230] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
Claims
1. A method for monitoring and analyzing multidimensional data of a smart scenic spot based on improved deep learning, characterized in that: The steps include: S1. Deploy a variety of IoT sensors in the scenic area to collect real-time information on tourist flow, environmental parameters, and facility usage to build a multidimensional data set; S2, cleaning the collected original multidimensional data set to remove noise and invalid data; S3. Standardize multidimensional data sets from different sources and unify data formats and units; S4. Construct a parsing model for multidimensional data sets based on improved deep learning algorithms; S5. Use analytical models to analyze real-time data in the scenic area, identify abnormal situations and issue alarms in a timely manner; S6. Predict the trend of tourist flow and environmental changes in the future by analyzing historical data; S7, provides real-time monitoring function for various data of scenic spots, and managers can view the operation status of scenic spots in real time through the visual interface; S8. When the system detects an abnormal situation, it automatically triggers the alarm mechanism and sends a notification to the relevant management personnel; S9. Provide decision support for scenic area managers based on data parsing and analysis results; S10. Provide intelligent navigation and real-time information push services based on the analysis of tourists’ behaviors and preferences.
2. According to claim 1, a method for monitoring and analyzing multidimensional data of a smart scenic spot based on improved deep learning is characterized in that: The S1 comprises the following sub-steps: S11. Deploy a variety of IoT sensors at key locations within the scenic area, including visitor flow sensors, environmental parameter sensors, and facility usage sensors; S12. Real-time collection of tourist flow data D t , Environmental parameter data E t , Facility usage data F t ; S13, the tourist flow data D t Including the number of tourists entering the scenic area N in (t) and the number of tourists leaving the scenic area N out (t): D t ={N in (t),N out (t)}; S14, the environmental parameter data E t Including temperature T(t), humidity H(t), air quality index AQI(t): E t ={T(t),H(t),AQI(t)}; S15, the facility usage data F t Including the usage status of the facility S i (t) and the fault record of the facility R i (t): F t ={S i (t),R i (t)}; S16, collect the tourist flow data D through the wireless network or wired network t , Environmental parameter data E t , Facility usage data F t Transmit to a central processing system; S17, the central processing system receives and stores the data, and constructs a multidimensional data set MDS: MDS={D t ,E t ,F t }.
3. According to claim 2, a method for monitoring and analyzing multi-dimensional data of a smart scenic spot based on improved deep learning is characterized in that: The S4 comprises the following sub-steps: S41, collect and preprocess multidimensional data sets MDS, including data cleaning and standardization; MDS clean ={Clean(D t ),Clean(E t ),Clean(F t )}; MDS std ={Std(D t ),Std(E t ),Std(F t )}; Among them, Clean(·) represents the cleaning process to remove noise and invalid data, and Std(·) represents the standardization process to unify the data format and unit; S42. Design and improve deep learning algorithms, including optimizing neural network structures, loss functions, and training methods; S43, inputting the preprocessed multidimensional data set into the improved deep learning model for training, and constructing an analysis model AM for analyzing the multidimensional data set; S44. Improve the deep learning model by using a combination of graph convolutional networks and dynamic Bayesian networks to optimize the parsing accuracy and data processing capabilities of the parsing model AM; H gcn =GCN(MDS std ;W gcn ); S45. The graph convolution network captures the spatial and temporal dependencies in the scenic area data, and defines the graph convolution layer parameters as W gcn , the output feature is represented as H gcn : in, represents the adjacency matrix with self-loops added, yes The degree matrix of is the input feature matrix of the lth layer, σ is the activation function; A represents the adjacency matrix, and I represents the identity matrix; S46, Dynamic Bayesian Network Modeling Data Time-varying Characteristics and Potential Structure, Define the Bayesian Network Node and Edge Weight Matrices as W node and W edge , the output potential is represented as z: Among them, z i The ith node representing the latent variable, Pa(z i ) represents node z i The parent node set of in, Represents the mean and standard deviation of the i-th node; S47, the output of the graph convolutional network and the dynamic Bayesian network are fused through the fusion layer to obtain the comprehensive feature representation H fuse : H fuse =γH gcn +δz; Among them, γ and δ represent fusion weights; S48, optimizing the model parameters through the back propagation algorithm and gradient descent to obtain the final analytical model AM; in, represents the basic loss function, Y represents the actual label, λ represents the regularization parameter, α and β represent the weights of the additional loss terms; Risk(H fuse ,S safety ) represents the evaluation of the safety risk of the scenic spot by the analytical model, Satisfaction (H fuse ,S user ) represents the evaluation of tourist satisfaction by the analytical model.
4. According to claim 3, a method for monitoring and analyzing multi-dimensional data of a smart scenic spot based on improved deep learning is characterized in that: The S48 comprises the following sub-steps: S481. Define the basic loss function Among them, H fuse is the fusion feature representation, Y is the actual label, and the loss function is used to measure the difference between the predicted value and the actual value: Where N is the number of samples, and Loss(·) is the loss calculation function; S482. Define regularization terms to avoid model overfitting, including weight regularization terms for graph convolutional networks and dynamic Bayesian networks: Reg(In gcn ,IN node )=λ(||W gcn || 2 +||In node || 2 ); Among them, λ is the regularization parameter, ||W gcn || 2 and ||W node || 2 are the second norms of the weight matrix respectively; S483. Define additional loss items to evaluate the security risk and user satisfaction of the analytical model: Among them, α1 and β1 are the weights of the additional loss term, S safety and S user They are the evaluation criteria for security risk and user satisfaction respectively; S484. Construct a comprehensive loss function that integrates basic loss, regularization term and additional loss term; S485. Calculate the gradient of the loss function to the model parameters through the back propagation algorithm: S486. Update model parameters using gradient descent optimization algorithm: Among them, η represents the learning rate, and the parameters of the analytical model AM are optimized through repeated iterations until the loss function converges.
5. According to claim 4, a method for monitoring and analyzing multi-dimensional data of a smart scenic spot based on improved deep learning is characterized in that: The S5 comprises the following sub-steps: S51, real-time data MDS in the scenic area real Input into the constructed analytical model AM; S52, the analytical model AM processes the real-time data and extracts the feature representation H real : H real =AM(MDS real ); S53, the extracted features are represented as H real Compare with the preset threshold or reference value, and define the threshold as T threshold,i and T threshold,j , if H real Any element h in i The following conditions are met: h i >T threshold,i or i <T threshold,j ; It is considered an abnormal situation; S54, classifying abnormal situations and identifying specific abnormal types, including crowded tourists, facility failures, abnormal environmental parameters, etc.; S55. Using the preset alarm mechanism, according to the identified abnormal type, an alarm signal is generated and the relevant management personnel are notified in a timely manner; S56. The alarm signal includes the abnormality type, occurrence time, specific location and related data information. The alarm signal is defined as: A signal ={Type:T type ,Time:T time ,Location:L location ,Data:D data }; S57, sending the alarm signal to the scenic area management system via a wireless network or a wired network, and recording it in a system log; S58. According to the alarm signal, the status information in the scenic area management system is updated in real time and displayed on the visual interface, so that the management personnel can check and handle abnormal situations in time.
6. The method for monitoring and analyzing multi-dimensional data of a smart scenic spot based on improved deep learning according to claim 5 is characterized in that: The S52 comprises the following sub-steps: S521, real-time data MDS real Standardization is done to make it meet the input requirements of the analytical model AM. The standardized data is represented as MDS real_std ; S522, standardize the real-time data MDS real_std Input to the input layer of the analytical model AM, and define the input layer weight as W in and the bias is b in , the output of the input layer is calculated as: Among them, σ represents the nonlinear activation function, and n is the number of nodes in the input layer; S523, input layer output H in Feature extraction is performed through multiple hidden layers, and the weight and bias of each hidden layer are W l and b l , the output of the lth layer is represented as H l : Among them, φ represents the nonlinear activation function, m l-1 is the number of nodes in the l-1th layer; S524, the output H of the last hidden layer l Input to the output layer, define the output layer weight as W out and the bias is b out , calculate the feature representation H of the output layer real : S525. In each layer of calculation, apply the optimized back propagation algorithm to calculate the loss function according to the actual label Y And adjust the weights and biases according to the gradient descent algorithm: S526, through multiple iterations of training and optimization, the output feature representation H of the analytical model AM is finally obtained real , used for subsequent abnormal situation identification and alarm.
7. The method for monitoring and analyzing multi-dimensional data of a smart scenic spot based on improved deep learning according to claim 6 is characterized in that: The S53 comprises the following sub-steps: S531, the extracted features are represented as H real With the pre-set threshold vector T threshold Compare item by item and define each feature representation h i and threshold T threshold,i ; S532, if the feature represents h i Exceeds the preset upper threshold or below the lower threshold It is considered an abnormal situation if: S533, for each feature h i Classify the abnormal situations, identify the specific abnormal types, and define the abnormal type set as F type , including the following categories: E type ={tourist crowding, facility failure, abnormal environmental parameters}; S534, set the corresponding alarm level A for each abnormal type level , divided into multiple levels according to the severity and impact range of the abnormality, and the alarm level set is defined as A level , including the following levels: A level ={Level 1 alarm, Level 2 alarm, Level 3 alarm}; S535. Generate an alarm signal according to the identified abnormality type and alarm level, and define the alarm signal as: A signal ={Type:E type ,Level:A level ,Time:T time ,Location:L location ,Data:D data }; S536: When generating an alarm signal, record the specific time when the abnormality occurs T time Specific location L location And related data information D data .
Citation Information
Patent Citations
A pedestrian re-identification method based on uncertainty optimization
CN109886141A
Scenic area passenger flow real-time prediction method based on tourist time-space behavior pattern mining
CN114519454A
Time series data and knowledge fusion representation method for industrial equipment abnormity monitoring
CN114625883A
Hyperspectral image classification method based on Bayesian layer graph convolutional neural network
CN115393631A
Traffic flow prediction method and system based on Bayesian method and graph convolution
CN115660135A
Cited By
Building environment digital twinning monitoring system
CN119293675A
Airport luggage tracking system and method based on block chain
CN119539667A
Intelligent scenic spot management and control system and method based on Internet of Things and big data analysis
CN119623875A
Scenic Area Intelligent Control System and Method Based on Internet of Things and Big Data Analysis
CN119623875B
Intelligent monitoring and evaluation system and method for karst geological relic protection area
CN120182066A
