Smart city network flow monitoring method based on decision tree model
Through the smart city network traffic monitoring method based on the decision tree model, the data preprocessing problem is solved, efficient and accurate network traffic monitoring and management are achieved, network security risks are reduced, and city managers are supported in formulating scientific resource allocation and security strategies.
Patent Information
- Application Number
- CN202510532001.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-25
- Publication Date
- 2025-09-12
AI Technical Summary
Traditional smart city network traffic monitoring methods have difficulty in data preprocessing, resulting in inaccurate data analysis, affecting network traffic monitoring and management decisions, failing to meet real-time monitoring needs, and failing to effectively identify abnormal traffic, increasing network security risks.
By collecting, preprocessing and building a decision tree model, including data collection, preprocessing, model training and evaluation, network traffic is monitored in real time, alarm messages are generated, and the model is continuously improved through optimization and feedback mechanisms to ensure that the decision tree can accurately classify normal and abnormal traffic.
It improves the accuracy of data analysis, ensures the accuracy of network traffic monitoring and management decisions, reduces the risk of missed or false alarms, improves the timeliness and security of network response, and supports scientific resource allocation and security protection strategies.
Smart Images
Figure CN120639665A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a smart city network traffic monitoring method based on a decision tree model. Background Art
[0002] Smart city network traffic monitoring based on the decision tree model collects and analyzes network data in real time, and uses decision tree algorithms such as CART, ID3 or C4.5 to extract features from complex traffic data and establish a tree-like classification structure. It can quickly identify normal traffic patterns and potential anomalies, and trigger immediate alerts and automatic response measures through predetermined rules, thereby ensuring network stability and security.
[0003] Traditional smart city network traffic monitoring methods include processing the collected raw data into a standard format for analysis, and detecting abnormal behavior in the traffic by setting thresholds or using statistical methods. The above methods make it difficult to pre-process the data during operation, resulting in inaccurate data analysis, affecting network traffic monitoring and management decisions. Complex raw data increases the computational difficulty of data processing and analysis, prolongs processing time, and cannot meet the needs of real-time monitoring, thereby reducing the timeliness of network response. At the same time, if the data is not cleaned and standardized, the system cannot effectively identify abnormal traffic, resulting in missed reports or false reports, and increasing network security risks. Summary of the Invention
[0004] The purpose of the present invention is to provide a smart city network traffic monitoring method based on a decision tree model, which solves the problem in the background technology that it is difficult to pre-process data, resulting in inaccurate data analysis and affecting network traffic monitoring and management decisions.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0006] A smart city network traffic monitoring method based on a decision tree model includes the following steps:
[0007] S1. Data Collection: Collect network traffic data generated by each node in the smart city, including traffic size, packet type, inflow and outflow time, resource and target IG geology, etc., obtain relevant information such as weather, holidays, public activities, etc., and analyze the factors affecting traffic fluctuations;
[0008] S2. Data preprocessing: Remove duplicate and invalid data, fill missing values, ensure data integrity and accuracy, and extract important features from the raw data based on specific monitoring objectives (such as traffic period, traffic peak, traffic category, etc.)
[0009] S3. Build a decision tree model: Select an appropriate decision tree algorithm (such as CART, ID3, or C4.5) and adjust parameters based on the characteristics of the dataset. Use labeled data (abnormal and normal traffic marked based on past traffic conditions) to train the model and generate a preliminary decision tree.
[0010] S4. Model evaluation: Evaluate model accuracy and generalization ability through cross-validation, adjust parameters to improve model performance, and use metrics such as precision, recall, and F1-score to evaluate model effectiveness to ensure that the decision tree can effectively distinguish normal traffic from abnormal traffic.
[0011] S5. Traffic monitoring and prediction: By building a traffic monitoring system, network traffic data is collected in real time, and the new data is input into the trained decision tree model for classification and judgment, so as to promptly identify and respond to abnormal situations in network traffic and generate corresponding alarm messages; abnormal situations include network attacks, congestion, equipment failure, etc.
[0012] S6. Optimization and feedback: Based on monitoring results and actual feedback, continuously optimize the decision tree model, adjust feature selection and parameter settings, improve detection accuracy and efficiency, and formulate corresponding network traffic management strategies based on monitoring and analysis results to make network resource allocation more reasonable and ensure the efficient operation of smart cities.
[0013] Preferably, the city nodes in the data collection of step S1 include traffic monitoring, public facilities, and user terminals. The traffic monitoring improves traffic efficiency and safety through real-time data collection and intelligent analysis; the public facilities integrate sensors, communications, data centers, etc. to ensure comprehensive data and efficient processing; the user terminals enhance citizen participation and experience through convenient data acquisition and interaction. The three together build an efficient, secure, and interactive smart city network traffic monitoring system.
[0014] Preferably, the traffic monitoring includes road monitoring cameras, traffic lights and an intelligent transportation system. The road monitoring cameras are used to monitor road conditions for traffic flow, and the traffic lights are devices used to control traffic flow and can collect data on traffic flow and congestion. The intelligent transportation system includes data collection for vehicle identification and traffic management systems, and uses data training and optimization of decision tree models to achieve traffic flow prediction, anomaly detection and intelligent adjustment of traffic lights, thereby improving traffic efficiency and safety and reducing congestion and accident risks.
[0015] Preferably, the public facilities include smart street lights, environmental sensors and public WI-FI hotspots. The smart street lights can collect environmental data and perform energy-saving processing. The environmental sensors are used to monitor environmental parameters such as air quality and noise levels. The public WI-FI hotspots are used to collect user network usage data. By jointly collecting, processing and analyzing data from all corners of the city, support is provided for the decision tree model, realizing intelligent monitoring and management of network traffic, and improving the efficiency and security of urban governance.
[0016] Preferably, the S2 data preprocessing includes the following steps:
[0017] a. Collect raw traffic data from various network devices (such as routers, switches, firewalls, etc.) and system logs to ensure the diversity and breadth of data sources;
[0018] b. Check and delete redundant records to ensure the uniqueness of each data point. Use strategies such as interpolation, mean filling, and deletion of records with missing values to solve the problem of missing values in the data set.
[0019] c. Convert data from different sources into a consistent format for subsequent processing, and standardize or normalize numerical features to eliminate the impact of different dimensions and scales on model training and analysis, ensuring data comparability;
[0020] d. Based on business needs and data analysis objectives, select the features that have the greatest impact on traffic analysis, remove redundant or irrelevant features, and improve data representation by calculating traffic statistics (such as mean, variance, maximum, minimum, etc.) or extracting temporal features using time series analysis methods.
[0021] e. Integrate data from different sources to form a unified dataset to ensure data consistency and integrity. Divide the dataset into training and test sets as needed. It can also be divided into different time windows based on time series to facilitate subsequent model training and experiments.
[0022] Preferably, the user terminal includes a smart phone, a wearable device and a home smart device.
[0023] Preferably, the smartphone includes a user device for collecting location, usage habits and network request data, the wearable device includes a smart watch for collecting health and activity data, and the home smart device includes a smart home identification for collecting home network usage data.
[0024] Preferably, the step S3 of constructing a decision tree model further comprises the following steps:
[0025] a. Select an appropriate decision tree algorithm as the basis and preprocess the collected training data, including cleaning the data, handling missing values, and standardizing features;
[0026] b. Select the optimal features through a recursive partitioning function to establish a tree structure. Use criteria such as information gain, information gain ratio, or Gini index to evaluate the splitting effect of the features. During the training process, evaluate the accuracy of the model through cross-validation, and apply pruning techniques to reduce the complexity of the model to prevent overfitting.
[0027] c. Generate an interpretable decision tree and perform model validation to ensure that it maintains good predictive performance on new data.
[0028] Preferably, the S5 flow monitoring and prediction further includes the following steps:
[0029] a. Continuously collect network traffic data, including bandwidth usage, packet size, transmission frequency, etc., through sensors or monitoring tools to achieve real-time data collection;
[0030] b. Input the collected data into a trained decision tree model and use the model's classification and prediction capabilities to quickly identify normal patterns and abnormal behaviors in traffic;
[0031] c. In the anomaly detection phase, the system automatically flags potential anomalies through preset thresholds or pattern matching methods. At the same time, the system generates alerts and takes appropriate response measures;
[0032] d. Combine historical data with current trends to predict traffic flow, and use models to infer future traffic changes to help optimize network resource allocation and prevent potential problems;
[0033] e. Generate reports regularly to analyze and summarize traffic conditions to ensure efficient, secure, and stable operation of the smart city network.
[0034] Preferably, the S6 optimization and feedback specifically includes: based on traffic monitoring and prediction, analyzing the accuracy of monitoring results and model predictions, identifying deficiencies or potential problems in the system, and through systematic evaluation of various indicators, timely adjusting the parameters and feature selection of the decision tree model to improve its predictive ability and stability, continuously iteratively updating the model based on newly collected real-time data, adopting incremental learning methods in machine learning to adapt to changes in traffic patterns, regularly collecting feedback from users or operators, understanding their needs and suggestions in actual applications, further optimizing the system's availability and response flexibility, and ensuring that the monitoring system maintains efficient operation in a dynamically changing network environment.
[0035] Compared with the prior art, the present invention has the following beneficial effects:
[0036] 1. The present invention can pre-process data through the setting of data pre-processing operations, improve the accuracy of data analysis, ensure the accuracy of network traffic monitoring and management decisions, avoid the situation where complex raw data increases the difficulty of data processing and analysis calculations and prolongs the processing time, and can meet the needs of real-time monitoring, thereby increasing the timeliness of network response. At the same time, it solves the problem of traditional methods where data is not cleaned and standardized, the system cannot effectively identify abnormal traffic, resulting in missed reports or false reports, and reduces network security risks.
[0037] 2. The present invention can facilitate network administrators and decision makers to quickly identify key factors affecting traffic changes by constructing a decision tree model operation setting. The decision tree model is easy to understand and explain. The visual tree structure makes the decision process transparent and can adapt to complex traffic data, thereby accurately classifying normal and abnormal traffic and improving security monitoring capabilities. The decision tree can also support the processing of missing values and nonlinear relationships, and can achieve real-time or near real-time monitoring and alarming, ensuring timely response to network time. It can not only optimize network performance, but also provide data support for decision-making, effectively helping city managers to formulate scientific resource allocation and security protection strategies.
[0038] 3. Through the setting of traffic monitoring and prediction operations, the present invention can perform real-time traffic monitoring to help timely discover network anomalies and potential security threats, effectively ensure network security and stable operation, and can estimate future traffic demand based on historical data and current trends, help optimize network resource allocation, avoid network congestion, and improve user experience. At the same time, the prediction model can also provide a scientific basis for network planning, support long-term network expansion and upgrade decisions, and ensure that the network infrastructure can adapt to the needs of urban development. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 is a flow chart of the method of the present invention;
[0040] Figure 2 This is a flow chart of data preprocessing of the present invention;
[0041] Figure 3 A flow chart for constructing a decision tree model for the present invention;
[0042] Figure 4 This is a flow chart of flow monitoring and prediction of the present invention. DETAILED DESCRIPTION
[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.
[0044] See also Figure 1 and Figure 2 , a smart city network traffic monitoring method based on a decision tree model, including the following steps: data collection: collecting network traffic data generated by each node in the smart city, including traffic size, data packet type, inflow and outflow time, resources and target IG geology, etc., obtaining relevant information such as weather, holidays, public activities, etc., and analyzing the influencing factors of traffic fluctuations; data preprocessing: removing duplicate and invalid data, filling missing values, ensuring data integrity and accuracy, and extracting important features from the original data according to specific monitoring objectives; (traffic period, traffic peak, traffic category, etc.); building a decision tree model: selecting a suitable decision tree algorithm and adjusting parameters according to the characteristics of the data set (decision tree algorithms such as CART, ID3, C4.5, etc.) Use labeled data (abnormal traffic and normal traffic marked according to past traffic conditions) for model training to generate a preliminary decision tree ; Model evaluation: Evaluate the accuracy and generalization ability of the model through cross-validation, adjust parameters to improve model performance, and use indicators such as precision, recall rate, F1-score to evaluate the model effect to ensure that the decision tree can effectively distinguish normal traffic from abnormal traffic; Traffic monitoring and prediction: By building a traffic monitoring system, collect network traffic data in real time, input new data into the trained decision tree model for classification and judgment, promptly identify and respond to anomalies in network traffic, and generate corresponding alarm messages; anomalies include network attacks, congestion, equipment failure, etc.; Optimization and feedback: Based on the monitoring results and actual feedback, continuously optimize the decision tree model, adjust feature selection and parameter settings, improve detection accuracy and efficiency, and formulate corresponding network traffic management strategies based on the monitoring and analysis results to make network resource allocation more reasonable and ensure the efficient operation of smart cities;
[0045] In step S1, the city nodes in data collection include traffic monitoring, public facilities, and user terminals. The traffic monitoring improves traffic efficiency and safety through real-time data collection and intelligent analysis; the public facilities integrate sensors, communications, data centers, etc. to ensure comprehensive data and efficient processing; the user terminals enhance citizen participation and experience through convenient data acquisition and interaction. The three together build an efficient, safe, and interactive smart city network traffic monitoring system. Traffic monitoring includes road monitoring cameras, traffic lights, and intelligent transportation systems. Road monitoring cameras are used to monitor road conditions for traffic flow, and traffic lights are used to control traffic flow equipment, which can collect information about traffic. Traffic and congestion data, intelligent transportation systems include vehicle identification and traffic management system data collection, public facilities include smart street lights, environmental sensors and public WI-FI hotspots, smart street lights can collect environmental data and perform energy-saving processing, environmental sensors are used to monitor environmental parameters such as air quality and noise levels, public WI-FI hotspots are used to collect user network usage data, by jointly collecting, processing and analyzing data from all corners of the city, providing support for decision tree models, realizing intelligent monitoring and management of network traffic, and improving the efficiency and security of urban governance, user terminals include smartphones, wearable devices and home smart devices, smartphones include user devices, Used to collect location, usage habits and network request data. Wearable devices include smart watches, which are used to collect health and activity data. Home smart devices include smart home devices, which are used to collect home network usage data. Data preprocessing includes the following steps: collecting raw traffic data from various network devices (such as routers, switches, firewalls, etc.) and system logs to ensure the diversity and breadth of data sources; checking and deleting redundant records to ensure the uniqueness of each data, using interpolation, mean filling, deleting records with missing values and other strategies to solve the problem of missing values in the data set; converting data from different sources into a consistent format for subsequent processing, and performing Perform standardization or normalization to eliminate the impact of different dimensions and scales on model training and analysis, and ensure data comparability; select the features that have the greatest impact on traffic analysis based on business needs and data analysis objectives, remove redundant or irrelevant features, and improve data expression capabilities by calculating statistical features of traffic (such as mean, variance, maximum, minimum, etc.) or using time series analysis methods to extract time features; integrate data from different sources to form a unified data set to ensure data consistency and integrity, and divide the data set into training and test sets as needed. It can also be divided into different time windows based on time series to facilitate subsequent model training and experiments.
[0046] By setting up data preprocessing operations, data can be preprocessed to improve the accuracy of data analysis, ensure the accuracy of network traffic monitoring and management decisions, and avoid the situation where complex raw data will increase the difficulty of data processing and analysis calculations and prolong processing time. It can meet the needs of real-time monitoring, thereby increasing the timeliness of network response. At the same time, it solves the problem of traditional methods where data is not cleaned and standardized, the system cannot effectively identify abnormal traffic, resulting in missed reports or false reports, thereby reducing network security risks.
[0047] Please refer to Figure 3 , S3 building a decision tree model also includes the following steps: selecting a suitable decision tree algorithm as the basis, preprocessing the collected training data, including cleaning data, processing missing values and standardizing features; selecting the optimal features through recursive partitioning function to establish a tree structure, using information gain, information gain rate or Gini index and other criteria to evaluate the splitting effect of features; during the training process, evaluating the accuracy of the model through cross-validation, and applying pruning technology to reduce the complexity of the model to prevent overfitting; generating an interpretable decision tree and performing model validation to ensure that it can maintain good predictive performance on new data.
[0048] By constructing a decision tree model operation setting, network administrators and decision makers can quickly identify key factors that affect traffic changes. The decision tree model is easy to understand and explain. The visual tree structure makes the decision-making process transparent and can adapt to complex traffic data, thereby accurately classifying normal and abnormal traffic and improving security monitoring capabilities. The decision tree can also support the processing of missing values and nonlinear relationships, and can achieve real-time or near real-time monitoring and alarms to ensure timely response to network time. It can not only optimize network performance, but also provide data support for decision-making, effectively helping city managers to formulate scientific resource allocation and security protection strategies.
[0049] Please also refer to Figure 4 S5 traffic monitoring and prediction also includes the following steps: continuously collecting network traffic data, including bandwidth usage, packet size, transmission frequency, etc., through sensors or monitoring tools to achieve real-time data collection; inputting the collected data into the trained decision tree model, and using the classification and prediction capabilities of the model to quickly identify normal patterns and abnormal behaviors in the traffic; in the anomaly detection stage, the system automatically marks potential anomalies through preset thresholds or pattern matching methods. At the same time, the system will generate alarms and take corresponding response measures; combining historical data with current trends to predict traffic, using models to infer future traffic changes, helping to optimize network resource allocation and prevent potential problems; by regularly generating reports, analyzing and summarizing traffic conditions, ensuring the efficient, secure and stable operation of the smart city network.
[0050] By setting up traffic monitoring and prediction operations, real-time traffic monitoring can help promptly detect network anomalies and potential security threats, effectively ensuring network security and stable operation. It can also estimate future traffic demand based on historical data and current trends, help optimize network resource allocation, avoid network congestion, and improve user experience. At the same time, the prediction model can also provide a scientific basis for network planning, support long-term network expansion and upgrade decisions, and ensure that the network infrastructure can adapt to the needs of urban development.
[0051] While the 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 alterations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the invention is defined by the appended claims and their equivalents.
Claims
1. A smart city network traffic monitoring method based on a decision tree model, characterized in that: The following steps are involved: S1. Data Collection: Collect network traffic data generated by each node in the smart city, including traffic size, packet type, inflow and outflow time, resource and target IG geology, etc., obtain relevant information such as weather, holidays, public activities, etc., and analyze the factors affecting traffic fluctuations; S2. Data preprocessing: Remove duplicate and invalid data, fill missing values, ensure data integrity and accuracy, and extract important features (flow period, flow peak, flow category, etc.) from the raw data according to specific monitoring objectives; S3. Build a decision tree model: Select an appropriate decision tree algorithm (such as CART, ID3, or C4.5) and adjust parameters based on the characteristics of the dataset. Use labeled data (abnormal and normal traffic marked based on past traffic conditions) to train the model and generate a preliminary decision tree. S4. Model evaluation: Evaluate model accuracy and generalization ability through cross-validation, adjust parameters to improve model performance, and use metrics such as precision, recall, and F1-score to evaluate model effectiveness to ensure that the decision tree can effectively distinguish normal traffic from abnormal traffic. S5. Traffic Monitoring and Forecasting: By building a traffic monitoring system, network traffic data is collected in real time. New data is input into the trained decision tree model for classification and judgment. This allows for timely identification and response to anomalies in network traffic, and generates corresponding alarm messages. Abnormal situations include network attacks, congestion, equipment failure, etc. S6. Optimization and feedback: Based on monitoring results and actual feedback, continuously optimize the decision tree model, adjust feature selection and parameter settings, improve detection accuracy and efficiency, and formulate corresponding network traffic management strategies based on monitoring and analysis results to make network resource allocation more reasonable and ensure the efficient operation of smart cities.
2. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 1, characterized in that: The city nodes in the data collection in step S1 include traffic monitoring, public facilities, and user terminals. The traffic monitoring improves traffic efficiency and safety through real-time data collection and intelligent analysis; the public facilities integrate sensors, communications, data centers, etc. to ensure comprehensive data and efficient processing; the user terminals enhance citizen participation and experience through convenient data acquisition and interaction. The three together build an efficient, secure, and interactive smart city network traffic monitoring system.
3. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 2, characterized in that: The traffic monitoring includes road monitoring cameras, traffic lights and intelligent transportation systems. The road monitoring cameras are used to monitor road conditions for traffic flow, and the traffic lights are equipment for controlling traffic flow and can collect data on traffic flow and congestion. The intelligent transportation system includes vehicle identification and traffic management system data collection, and uses data training and optimization of decision tree models to achieve traffic flow prediction, anomaly detection and intelligent adjustment of traffic lights, thereby improving traffic efficiency and safety and reducing congestion and accident risks.
4. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 2, characterized in that: The public facilities include smart street lights, environmental sensors and public Wi-Fi hotspots. The smart street lights can collect environmental data and perform energy-saving processing. The environmental sensors are used to monitor environmental parameters such as air quality and noise levels. The public Wi-Fi hotspots are used to collect user network usage data. By jointly collecting, processing and analyzing data from all corners of the city, support is provided for the decision tree model, realizing intelligent monitoring and management of network traffic, and improving the efficiency and security of urban governance.
5. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 4, characterized in that: The S2 data preprocessing includes the following steps: a. Collect raw traffic data from various network devices (such as routers, switches, firewalls, etc.) and system logs to ensure the diversity and breadth of data sources; b. Check and delete redundant records to ensure the uniqueness of each data point. Use strategies such as interpolation, mean filling, and deletion of records with missing values to solve the problem of missing values in the data set. c. Convert data from different sources into a consistent format for subsequent processing, and standardize or normalize numerical features to eliminate the impact of different dimensions and scales on model training and analysis, ensuring data comparability; d. Based on business needs and data analysis objectives, select the features that have the greatest impact on traffic analysis, remove redundant or irrelevant features, and improve data representation by calculating traffic statistics (such as mean, variance, maximum, minimum, etc.) or extracting temporal features using time series analysis methods. e. Integrate data from different sources to form a unified dataset to ensure data consistency and integrity. Divide the dataset into training and test sets as needed. It can also be divided into different time windows based on time series to facilitate subsequent model training and verification.
6. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 2, characterized in that: The user terminals include smart phones, wearable devices and home smart devices.
7. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 6, characterized in that: The smartphone includes a user device for collecting location, usage habits and network request data, the wearable device includes a smart watch for collecting health and activity data, and the home smart device includes a smart home device for collecting home network usage data.
8. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 1, characterized in that: The S3 decision tree model construction further includes the following steps: a. Select an appropriate decision tree algorithm as the basis and preprocess the collected training data, including cleaning the data, handling missing values, and standardizing features; b. Select the optimal features through a recursive partitioning function to establish a tree structure. Use criteria such as information gain, information gain ratio, or Gini index to evaluate the splitting effect of the features. During the training process, evaluate the accuracy of the model through cross-validation, and apply pruning techniques to reduce the complexity of the model to prevent overfitting. c. Generate an interpretable decision tree and perform model validation to ensure that it maintains good predictive performance on new data.
9. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 1, characterized in that: The S5 flow monitoring and prediction further includes the following steps: a. Continuously collect network traffic data, including bandwidth usage, packet size, transmission frequency, etc., through sensors or monitoring tools to achieve real-time data collection; b. Input the collected data into a trained decision tree model and use the model's classification and prediction capabilities to quickly identify normal patterns and abnormal behaviors in traffic; c. In the anomaly detection phase, the system automatically flags potential anomalies through preset thresholds or pattern matching methods. At the same time, the system generates alerts and takes appropriate response measures; d. Combine historical data with current trends to predict traffic flow, and use models to infer future traffic changes to help optimize network resource allocation and prevent potential problems; e. Generate reports regularly to analyze and summarize traffic conditions to ensure efficient, secure, and stable operation of the smart city network.
10. The method for monitoring network traffic in a smart city based on a decision tree model according to claim 1, characterized in that: The S6 optimization and feedback specifically include: based on traffic monitoring and prediction, analyzing the accuracy of monitoring results and model predictions, identifying deficiencies or potential problems in the system, and through systematic evaluation of various indicators, timely adjusting the parameters and feature selection of the decision tree model to improve its predictive ability and stability, continuously iteratively updating the model based on newly collected real-time data, adopting incremental learning methods in machine learning to adapt to changes in traffic patterns, regularly collecting feedback from users or operators to understand their needs and suggestions in actual applications, further optimizing the system's availability and response flexibility, and ensuring that the monitoring system maintains efficient operation in a dynamically changing network environment.