Intelligent route distribution system based on vehicle owner behavior prediction

Abstract

The invention discloses an intelligent route distribution system based on vehicle owner behavior prediction, and relates to the technical field of route distribution, and the distribution system comprises a data collection module which is used for obtaining the historical driving data of a vehicle owner; the behavior prediction module is used for analyzing the driving habit of the vehicle owner and predicting the behavior of the vehicle owner; the real-time traffic analysis module is used for acquiring real-time traffic data and analyzing real-time traffic conditions, weather information and road condition changes; the route optimization module is used for calculating an optimal route based on the prediction result and the real-time data and recommending the optimal route; and the user interaction module is used for displaying the recommended route and receiving user feedback and adjustment suggestions. According to the invention, by analyzing the historical driving data and driving habits of the vehicle owner, the system can provide route recommendation conforming to personal preferences, the user experience is improved, real-time traffic data and weather information are integrated, it is ensured that the recommended route adapts to the current traffic condition and road condition change, and a more accurate and efficient driving route can be provided.

Description

Technical Field

[0001] The present invention relates to the technical field of route allocation, and in particular to an intelligent route allocation system based on vehicle owner behavior prediction. Background Art

[0002] Route allocation technology is used to optimize and allocate traffic flow, ensure the effective use of road resources in the traffic network, reduce congestion and improve traffic efficiency. Route allocation technology is mainly used to optimize traffic flow, ensure the effective use of resources in the traffic network, reduce congestion and improve traffic efficiency. Its core goal is to reduce the overall traffic cost, including time cost and economic cost, by reasonably allocating traffic flow. The existing shortest path algorithm generally uses the Dijkstra algorithm to calculate the single-source shortest path, and finds the shortest path from the starting point to the end point by gradually expanding the path. There is also a network optimization algorithm that solves the traffic flow allocation problem and handles the path selection problem by setting the objective function and constraints, especially when discrete decisions are required, such as whether to choose a certain road;

[0003] The existing route allocation optimization algorithm has high computational complexity and low efficiency. It cannot reflect the changes in actual traffic flow, ignores the dynamic characteristics of traffic flow, and cannot be combined with real-time data for calculation updates, resulting in deviations in the calculation results. Summary of the invention

[0004] In order to solve the above technical problems, an intelligent route allocation system based on vehicle owner behavior prediction is provided. This technical solution solves the above problems.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] Intelligent route allocation system based on vehicle owner behavior prediction, the allocation system includes:

[0007] Data collection module: used to obtain the owner's historical driving data based on the API interface of the vehicle GPS device;

[0008] Behavior prediction module: The behavior prediction module is electrically connected to the data acquisition module, and is used to analyze the driving habits of the owner based on the owner's historical driving data and predict the owner's behavior;

[0009] Real-time traffic analysis module: The real-time traffic analysis module is electrically connected to the behavior prediction module and the data acquisition module, and is used to obtain real-time traffic data and analyze real-time traffic conditions, weather information, and road condition changes;

[0010] Route optimization module: The route optimization module is electrically connected to the real-time traffic analysis module, the behavior prediction module and the data acquisition module. The route optimization module is used to calculate the optimal route based on the prediction results and real-time data, and make recommendations;

[0011] User interaction module: The user interaction module is electrically connected to the route optimization module, the real-time traffic analysis module, the behavior prediction module and the data acquisition module. The user interaction module is used to display the recommended route and receive user feedback and adjustment suggestions.

[0012] The data acquisition module specifically includes:

[0013] GPS data interface unit: obtains data from vehicle-mounted GPS devices through API interface;

[0014] Data storage unit: stores the collected GPS data in the database;

[0015] Data preprocessing unit: cleans and preprocesses the raw data, removes outliers, smoothes data, and interpolates and completes them;

[0016] Data conversion unit: convert GPS data through distance calculation;

[0017] The distance calculation formula is:

[0018]

[0019] Where d is the distance between two points, r is the radius of the earth, is the latitude difference between two points, Δ∈ is the longitude difference between two points, is the latitude of the first point, is the latitude of the second point, arcsin is the inverse sine function;

[0020] Data synchronization unit: Use the API interface to synchronize the collected data to the analysis system.

[0021] Preferably, the behavior prediction module specifically includes:

[0022] Feature extraction unit: extracts features from raw data using regularized calculation methods;

[0023] Model building unit: building a car owner behavior prediction model based on the extracted features;

[0024] Model training unit: training based on the owner behavior prediction model;

[0025] Behavior prediction unit: Use the trained model to predict future driving behavior. Based on the output of the model, predict the owner's driving habits and driving routes under specific conditions.

[0026] Model evaluation unit: Calculates the mean square error of the model and evaluates the performance of the model based on the mean square error of the model.

[0027] Preferably, the feature extraction unit specifically includes:

[0028] Among them, the regularization calculation formula is:

[0029]

[0030] In the formula, m is the value of minimizing the objective function, n is the number of samples, and y i is the true target value of the i-th sample, x i is the feature vector of the i-th sample, The transpose of the feature vector of the i-th sample, the parameters of the β model, β j The regression coefficient of the jth feature, γ is the regularization parameter;

[0031] Based on the regularization calculation results, some regression coefficients β are made zero;

[0032] Check the regression coefficient β;

[0033] Features with zero coefficients are automatically selected out, while non-zero features are retained in the model;

[0034] The features corresponding to non-zero coefficients are selected features.

[0035] Preferably, the model building unit specifically includes:

[0036] Based on the selected features, a prediction model of the owner's behavior is established;

[0037] Among them, the formula of the owner behavior prediction model is:

[0038]

[0039] In the formula, is the predicted value, x is the feature vector, x T is the transpose of the eigenvector, β is the regression coefficient vector;

[0040] Based on the model's predicted values, calculate the mean square error;

[0041] The mean square error calculation formula is:

[0042]

[0043] In the formula, y i is the ith actual value, is the i-th predicted value, n is the number of samples, and MSE is the mean square error;

[0044] Transmit the model's prediction results and mean square error.

[0045] The real-time traffic analysis module specifically includes:

[0046] Real-time data collection unit: obtain real-time traffic data, including vehicle location, traffic flow, speed and road conditions, collect weather information, and obtain road condition change data;

[0047] Real-time traffic condition analysis unit: obtain real-time traffic flow, speed and density, identify traffic congestion areas, and analyze traffic patterns in different time periods;

[0048] Weather and Road Condition Impact Analysis Unit: Evaluate the impact of weather conditions on traffic flow, monitor and analyze the impact of changing road conditions on traffic.

[0049] Preferably, the route optimization module specifically includes:

[0050] Data integration unit: collects and integrates real-time traffic data and vehicle owner behavior prediction data, wherein the real-time traffic data includes real-time speed, traffic flow and road conditions of road sections;

[0051] Route optimization model building unit: establishes a route optimization model based on real-time traffic data and driver behavior prediction data, and calculates the comprehensive scores of different routes;

[0052] Model result output unit: Calculate the comprehensive score of each path based on the route optimization model, compare the scores of all candidate paths, and select the path with the highest score as the recommended route.

[0053] Preferably, the route optimization model building module specifically includes:

[0054] Among them, the route optimization model includes:

[0055]

[0056] Where S is the comprehensive score of the path, T is the total time of the road segment, D is the total distance of the road segment, P is the adjustment factor based on the prediction of the driver's behavior, α is the weight coefficient of the total time of the road segment, β is the weight coefficient of the total distance of the road segment, γ is the weight coefficient of the adjustment factor of the driver's behavior prediction, and d i is the length of road segment i, v i is the real-time speed of road segment i.

[0057] Preferably, the user interaction module specifically includes:

[0058] Route display unit: graphically displays the recommended route and uses a map interface to display the route and traffic information;

[0059] Route information unit: provides detailed information of the route, including total distance, estimated time and road conditions;

[0060] User feedback receiving unit: allows users to submit feedback about the route, including satisfaction, congestion encountered, and road conditions;

[0061] Feedback collection unit: records and stores user feedback information;

[0062] Adjustment suggestion unit: adjust the recommendation algorithm based on user feedback and real-time data;

[0063] Re-recommendation unit: recalculates and displays the recommended route based on the adjusted score;

[0064] Data synchronization unit: Synchronizes user feedback with real-time traffic data to ensure the timeliness and accuracy of recommended routes.

[0065] Preferably, the adjustment suggestion unit specifically includes:

[0066] The adjustment formula is:

[0067] A 调 =S+τ·F

[0068] In the formula, A 调 is the adjusted comprehensive score of the path, S is the score of the original recommended path, F is the user feedback value, and F is the weight coefficient of the user feedback value.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] The present invention proposes that by analyzing the car owner's historical driving data and driving habits, the system can provide route recommendations that meet personal preferences, improve user experience, and integrate real-time traffic data and weather information to ensure that the recommended routes adapt to current traffic conditions and road conditions. Combined with predicted behavior and real-time data for route optimization, the present invention can provide more accurate and efficient driving routes. By designing a user feedback system, the present invention allows the recommendation algorithm to be adjusted according to actual usage, gradually improving the system's recommendation accuracy and user satisfaction. The system takes into account multiple factors and increases the comprehensiveness and practicality of the recommended routes. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 It is the internal system framework diagram of the present invention;

[0072] Figure 2 It is the internal system framework diagram of the data acquisition module in the present invention;

[0073] Figure 3 It is an internal system framework diagram of the behavior prediction module in the present invention;

[0074] Figure 4 This is an internal system framework diagram of the real-time traffic analysis module in the present invention;

[0075] Figure 5 This is an internal system framework diagram of the route optimization module in the present invention;

[0076] Figure 6 This is an internal system framework diagram of the user interaction module in the present invention. DETAILED DESCRIPTION

[0077] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0078] Reference Figure 1 As shown, the intelligent route allocation system based on the prediction of vehicle owner behavior includes:

[0079] Data collection module: used to obtain the owner's historical driving data based on the API interface of the vehicle GPS device;

[0080] Behavior prediction module: The behavior prediction module is electrically connected to the data acquisition module, and is used to analyze the driving habits of the owner based on the owner's historical driving data and predict the owner's behavior;

[0081] Real-time traffic analysis module: The real-time traffic analysis module is electrically connected to the behavior prediction module and the data acquisition module, and is used to obtain real-time traffic data and analyze real-time traffic conditions, weather information, and road condition changes;

[0082] Route optimization module: The route optimization module is electrically connected to the real-time traffic analysis module, the behavior prediction module and the data acquisition module. The route optimization module is used to calculate the optimal route based on the prediction results and real-time data, and make recommendations;

[0083] User interaction module: The user interaction module is electrically connected to the route optimization module, the real-time traffic analysis module, the behavior prediction module and the data acquisition module. The user interaction module is used to display the recommended route and receive user feedback and adjustment suggestions.

[0084] Reference Figure 2 As shown, the data acquisition module specifically includes:

[0085] GPS data interface unit: obtains data from vehicle-mounted GPS devices through API interface;

[0086] Data storage unit: stores the collected GPS data in the database;

[0087] Data preprocessing unit: cleans and preprocesses the raw data, removes outliers, smoothes data, and interpolates and completes them;

[0088] Data conversion unit: convert GPS data through distance calculation;

[0089] The distance calculation formula is:

[0090] The distance calculation formula is:

[0091]

[0092] Where d is the distance between two points, r is the radius of the earth, is the latitude difference between two points, Δ∈ is the longitude difference between two points, is the latitude of the first point, is the latitude of the second point, arcsin is the inverse sine function;

[0093] Data synchronization unit: Use the API interface to synchronize the collected data to the analysis system.

[0094] Reference Figure 3 As shown, the behavior prediction module specifically includes:

[0095] Feature extraction unit: extracts features from raw data using regularized calculation methods;

[0096] Model building unit: building a car owner behavior prediction model based on the extracted features;

[0097] Model training unit: training based on the owner behavior prediction model;

[0098] Behavior prediction unit: Use the trained model to predict future driving behavior. Based on the output of the model, predict the owner's driving habits and driving routes under specific conditions.

[0099] Model evaluation unit: Calculates the mean square error of the model and evaluates the performance of the model based on the mean square error of the model.

[0100] The feature extraction unit specifically includes:

[0101] Among them, the regularization calculation formula is:

[0102]

[0103] In the formula, m is the value of minimizing the objective function, n is the number of samples, and yi is the true target value of the i-th sample, x i is the feature vector of the i-th sample, The transpose of the feature vector of the i-th sample, the parameters of the β model, β j The regression coefficient of the jth feature, γ is the regularization parameter;

[0104] Based on the regularization calculation results, some regression coefficients β are made zero;

[0105] Check the regression coefficient β;

[0106] Features with zero coefficients are automatically selected out, while non-zero features are retained in the model;

[0107] The features corresponding to non-zero coefficients are selected features.

[0108] The model building unit specifically includes:

[0109] Based on the selected features, a prediction model of the owner's behavior is established;

[0110] Among them, the formula of the owner behavior prediction model is:

[0111]

[0112] In the formula, is the predicted value, x is the feature vector, x T is the transpose of the eigenvector, β is the regression coefficient vector;

[0113] Based on the model's predicted values, calculate the mean square error;

[0114] The mean square error calculation formula is:

[0115]

[0116] In the formula, y i is the ith actual value, is the i-th predicted value, n is the number of samples, and MSE is the mean square error;

[0117] Transmit the model's prediction results and mean square error.

[0118] Reference Figure 4 As shown, the real-time traffic analysis module specifically includes:

[0119] Real-time data collection unit: obtain real-time traffic data, including vehicle location, traffic flow, speed and road conditions, collect weather information, and obtain road condition change data;

[0120] Real-time traffic condition analysis unit: obtain real-time traffic flow, speed and density, identify traffic congestion areas, and analyze traffic patterns in different time periods;

[0121] Weather and Road Condition Impact Analysis Unit: Evaluate the impact of weather conditions on traffic flow, monitor and analyze the impact of changing road conditions on traffic.

[0122] Reference Figure 5 As shown, the route optimization module specifically includes:

[0123] Data integration unit: collects and integrates real-time traffic data and vehicle owner behavior prediction data, wherein the real-time traffic data includes real-time speed, traffic flow and road conditions of road sections;

[0124] Route optimization model building unit: establishes a route optimization model based on real-time traffic data and driver behavior prediction data, and calculates the comprehensive scores of different routes;

[0125] Model result output unit: Calculate the comprehensive score of each path based on the route optimization model, compare the scores of all candidate paths, and select the path with the highest score as the recommended route.

[0126] The route optimization model building module specifically includes:

[0127] Among them, the route optimization model includes:

[0128]

[0129] Where S is the comprehensive score of the path, T is the total time of the road segment, D is the total distance of the road segment, P is the adjustment factor based on the prediction of the driver's behavior, α is the weight coefficient of the total time of the road segment, β is the weight coefficient of the total distance of the road segment, γ is the weight coefficient of the adjustment factor of the driver's behavior prediction, and d i is the length of road segment i, v i is the real-time speed of road segment i.

[0130] Reference Figure 6 As shown, the user interaction module specifically includes:

[0131] Route display unit: graphically displays the recommended route and uses a map interface to display the route and traffic information;

[0132] Route information unit: provides detailed information of the route, including total distance, estimated time and road conditions;

[0133] User feedback receiving unit: allows users to submit feedback about the route, including satisfaction, congestion encountered, and road conditions;

[0134] Feedback collection unit: records and stores user feedback information;

[0135] Adjustment suggestion unit: adjust the recommendation algorithm based on user feedback and real-time data;

[0136] Re-recommendation unit: recalculates and displays the recommended route based on the adjusted score;

[0137] Data synchronization unit: Synchronizes user feedback with real-time traffic data to ensure the timeliness and accuracy of recommended routes.

[0138] The adjustment suggestion unit specifically includes:

[0139] The adjustment formula is:

[0140] A 调 =S+τ·F

[0141] In the formula, A 调 is the adjusted comprehensive score of the path, S is the score of the original recommended path, F is the user feedback value, and F is the weight coefficient of the user feedback value.

[0142] The use process of the present invention is:

[0143] Step 1: Obtain data from the vehicle-mounted GPS device through the API interface;

[0144] Step 2: Store the collected GPS data in the database;

[0145] Step 3: Clean and preprocess the raw data to remove outliers, smooth the data, and interpolate and complete;

[0146] Step 4: Convert GPS data through distance calculation;

[0147] Step 5: Use the API interface to synchronize the collected data to the analysis system;

[0148] Step 6: Use regularization calculation method to extract features from raw data;

[0149] Step 7: Based on the extracted features, establish a car owner behavior prediction model;

[0150] Step 8: Training based on the owner behavior prediction model;

[0151] Step 9: Use the trained model to predict future driving behavior. Based on the output of the model, predict the owner's driving habits and driving routes under specific conditions.

[0152] Step 10: Calculate the mean square error of the model and evaluate the performance of the model based on the mean square error of the model.

[0153] Step 11: Obtain real-time traffic data, including vehicle location, traffic flow, speed, and road conditions, collect weather information, and obtain road condition change data;

[0154] Step 12: Obtain real-time traffic flow, speed and density, identify traffic congestion areas, and analyze traffic patterns in different time periods;

[0155] Step 13: Assess the impact of weather conditions on traffic flow, monitor and analyze the impact of changes in road conditions on traffic;

[0156] Step 14: Collect and integrate real-time traffic data and vehicle owner behavior prediction data, wherein the real-time traffic data includes real-time speed, traffic flow and road conditions of the road segment;

[0157] Step 15: Establish a route optimization model based on real-time traffic data and driver behavior prediction data, and calculate the comprehensive scores of different routes;

[0158] Step 16: Calculate the comprehensive score of each path based on the route optimization model, compare the scores of all candidate paths, and select the path with the highest score as the recommended route.

[0159] Step 17: Graphically display the recommended route and use the map interface to display the route and traffic information;

[0160] Step 18: Provide detailed information of the route, including total distance, estimated time, and road conditions;

[0161] Step 19: Allow the user to submit feedback about the route, including satisfaction, congestion encountered, and road conditions;

[0162] Step 20: Record and store user feedback information;

[0163] Step 21: Adjust the recommendation algorithm based on user feedback and real-time data;

[0164] Step 22: Recalculate and display the recommended route based on the adjusted score;

[0165] Step 23: Synchronize user feedback with real-time traffic data to ensure the timeliness and accuracy of the recommended route.

[0166] In summary, the advantages of the present invention are: the present invention proposes that by analyzing the car owner's historical driving data and driving habits, the system can provide route recommendations that meet personal preferences, improve user experience, and integrate real-time traffic data and weather information to ensure that the recommended routes adapt to current traffic conditions and road conditions. Combined with predicted behavior and real-time data for route optimization, more accurate and efficient driving routes can be provided. The present invention designs a user feedback system to allow the recommendation algorithm to be adjusted according to actual usage, gradually improving the system's recommendation accuracy and user satisfaction. The system takes into account multiple factors and increases the comprehensiveness and practicality of the recommended routes.

[0167] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. Intelligent route allocation system based on vehicle owner behavior prediction, characterized by: The distribution system includes: Data collection module: used to obtain the owner's historical driving data based on the API interface of the vehicle GPS device; Behavior prediction module: The behavior prediction module is electrically connected to the data acquisition module, and is used to analyze the driving habits of the owner based on the owner's historical driving data and predict the owner's behavior; Real-time traffic analysis module: The real-time traffic analysis module is electrically connected to the behavior prediction module and the data acquisition module, and is used to obtain real-time traffic data and analyze real-time traffic conditions, weather information, and road condition changes; Route optimization module: The route optimization module is electrically connected to the real-time traffic analysis module, the behavior prediction module and the data acquisition module. The route optimization module is used to calculate the optimal route based on the prediction results and real-time data, and make recommendations; User interaction module: The user interaction module is electrically connected to the route optimization module, the real-time traffic analysis module, the behavior prediction module and the data acquisition module. The user interaction module is used to display the recommended route and receive user feedback and adjustment suggestions.

2. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 1 is characterized in that: The data acquisition module specifically includes: GPS data interface unit: obtains data from vehicle-mounted GPS devices through API interface; Data storage unit: stores the collected GPS data in the database; Data preprocessing unit: cleans and preprocesses the raw data, removes outliers, smoothes data, and interpolates and completes them; Data conversion unit: convert GPS data through distance calculation; The distance calculation formula is: Where d is the distance between two points, r is the radius of the earth, is the latitude difference between two points, Δ∈ is the longitude difference between two points, is the latitude of the first point, is the latitude of the second point, arcsin is the inverse sine function; Data synchronization unit: Use the API interface to synchronize the collected data to the analysis system.

3. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 2 is characterized in that: The behavior prediction module specifically includes: Feature extraction unit: extracts features from raw data using regularized calculation methods; Model building unit: building a car owner behavior prediction model based on the extracted features; Model training unit: training based on the owner behavior prediction model; Behavior prediction unit: Use the trained model to predict future driving behavior. Based on the output of the model, predict the owner's driving habits and driving routes under specific conditions. Model evaluation unit: Calculates the mean square error of the model and evaluates the performance of the model based on the mean square error of the model.

4. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 3 is characterized in that: The feature extraction unit specifically include: Among them, the regularization calculation formula is: In the formula, m is the value of minimizing the objective function, n is the number of samples, and y i is the true target value of the i-th sample, x i is the feature vector of the i-th sample, The transpose of the feature vector of the i-th sample, the parameters of the β model, β j The regression coefficient of the jth feature, γ is the regularization parameter; Based on the regularization calculation results, some regression coefficients β are made zero; Check the regression coefficient β; Features with zero coefficients are automatically selected out, while non-zero features are retained in the model; The features corresponding to non-zero coefficients are selected features.

5. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 4 is characterized in that: The model building unit specifically includes: Based on the selected features, a prediction model of the owner's behavior is established; Among them, the formula of the owner behavior prediction model is: In the formula, is the predicted value, x is the feature vector, x T is the transpose of the eigenvector, β is the regression coefficient vector; Based on the model's predicted values, calculate the mean square error; The mean square error calculation formula is: In the formula, y i is the ith actual value, is the i-th predicted value, n is the number of samples, and MSE is the mean square error; Transmit the model's prediction results and mean square error.

6. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 5 is characterized in that: The real-time traffic analysis module specifically includes: Real-time data collection unit: obtain real-time traffic data, including vehicle location, traffic flow, speed and road conditions, collect weather information, and obtain road condition change data; Real-time traffic condition analysis unit: obtain real-time traffic flow, speed and density, identify traffic congestion areas, and analyze traffic patterns in different time periods; Weather and Road Condition Impact Analysis Unit: Evaluate the impact of weather conditions on traffic flow, monitor and analyze the impact of changing road conditions on traffic.

7. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 6 is characterized in that: The route optimization module specifically includes: Data integration unit: collects and integrates real-time traffic data and vehicle owner behavior prediction data, wherein the real-time traffic data includes real-time speed, traffic flow and road conditions of road sections; Route optimization model building unit: establishes a route optimization model based on real-time traffic data and driver behavior prediction data, and calculates the comprehensive scores of different routes; Model result output unit: Calculate the comprehensive score of each path based on the route optimization model, compare the scores of all candidate paths, and select the path with the highest score as the recommended route.

8. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 7 is characterized in that: The route optimization model establishment module specifically include: Among them, the route optimization model includes: Where S is the comprehensive score of the path, T is the total time of the road segment, D is the total distance of the road segment, P is the adjustment factor based on the prediction of the driver's behavior, α is the weight coefficient of the total time of the road segment, β is the weight coefficient of the total distance of the road segment, γ is the weight coefficient of the adjustment factor of the driver's behavior prediction, and d i is the length of road segment i, v i is the real-time speed of road segment i.

9. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 8 is characterized in that: The user interaction module specifically includes: Route display unit: graphically displays the recommended route and uses a map interface to display the route and traffic information; Route information unit: provides detailed information of the route, including total distance, estimated time and road conditions; User feedback receiving unit: allows users to submit feedback about the route, including satisfaction, congestion encountered, and road conditions; Feedback collection unit: records and stores user feedback information; Adjustment suggestion unit: adjust the recommendation algorithm based on user feedback and real-time data; Re-recommendation unit: recalculates and displays the recommended route based on the adjusted score; Data synchronization unit: Synchronizes user feedback with real-time traffic data to ensure the timeliness and accuracy of recommended routes.

10. The intelligent route allocation system based on vehicle owner behavior prediction according to claim 9, characterized in that: The adjustment suggestion unit specifically include: The adjustment formula is: A 调 =S+τ·F In the formula, A 调 is the adjusted comprehensive score of the path, S is the score of the original recommended path, F is the user feedback value, and F is the weight coefficient of the user feedback value.

Images