Traffic isochrone visualization application method based on open source maps

Abstract

The present invention discloses a method for visualizing traffic isochrone circles based on open source maps, comprising: utilizing open source map technology to acquire information on urban roads, facilities, traffic flow, weather, public transportation, and geographical obstacles to establish a traffic travel system; users input real-time traffic mode, speed, and special event information into the traffic travel system; the system establishes a traffic prediction model based on initial information, dynamically adjusts the weights of various factors, and introduces machine learning to predict future traffic conditions; adopts a shortest path or grid diffusion algorithm, combines initial information and predicted traffic conditions, and calculates traffic nodes that can be reached from a specified starting point within a specific time; generates isochrone circle boundaries based on the calculation results, and utilizes Web technology to achieve dynamic display; dynamically adjusts the weights of various factors affecting road traffic flow, and combines machine learning algorithms to predict future traffic conditions, thereby helping users better plan travel routes and thus improving travel efficiency.

Description

Technical Field

[0001] The present invention relates to a traffic travel planning method or system technology, and in particular to a traffic isochrone visualization application method based on an open source map. Background Art

[0002] A transportation isochrone zone is a spatial area that can be reached within a specified timeframe, starting from a specific location and using a specific mode of transportation. Its shape is often irregular, and generally speaking, the larger the time threshold, the wider the isochrone zone. By integrating the dimensions of time and space, transportation isochrones intuitively demonstrate the role of transportation infrastructure in guiding, supporting, and guaranteeing regional development.

[0003] Existing technologies for visualizing traffic isochrones typically rely on closed map data and fixed traffic models. These methods often fail to reflect changing traffic conditions in real time, nor can they flexibly adapt to user needs. Furthermore, existing technologies often suffer from insufficient prediction accuracy and poor user experience when dealing with complex traffic networks and special events. Summary of the Invention

[0004] The present invention overcomes the shortcomings of the prior art and provides a traffic isochrone visualization application method based on open source maps.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a traffic isochrone visualization application method based on open source maps, comprising the following steps:

[0006] S1. Utilize Wikimapia open-source mapping technology to obtain initial information on urban road networks, transportation facilities, traffic flow data, weather data, real-time public transportation data, and geographic obstacles, and establish a transportation system.

[0007] S2. The user actively inputs the real-time changes in traffic mode, travel speed, and special events into the traffic system in step S1;

[0008] S3. The traffic travel system establishes a traffic prediction model based on the initial information. The traffic prediction model dynamically adjusts the weights of various factors affecting road traffic flow according to real-time changes, and introduces machine learning algorithms to predict traffic conditions within a unit of time in the future.

[0009] S4. Using a shortest path algorithm from graph theory or a grid-based diffusion algorithm, the initial information from step S1 is combined with the traffic status from step S3 to calculate all traffic nodes that can be reached within a specific time from the specified starting point.

[0010] S5. Based on the calculation result in step S4, the polygonal boundary of the isochrone circle is generated, and a front-end visualization platform is constructed using Web technology to realize the dynamic display of the isochrone circle.

[0011] In a preferred embodiment of the present invention, in step S1, a travel road system with object building point information is established based on the topological structure of the urban road network, traffic facilities and geographical obstacles; historical data of the traffic flow data, weather data and public transportation real-time data are obtained, and a historical learning algorithm is used to obtain the weights of the influencing factors affecting the travel planning of the travel road system, and the traffic travel system is established.

[0012] In a preferred embodiment of the present invention, in step S2, the user inputs the travel mode and travel speed selected by the user in real time into the transportation system, and the user also needs to input special events encountered temporarily during the travel as travel influencing factors into the transportation system.

[0013] In a preferred embodiment of the present invention, in step S3, the traffic prediction model establishes a data framework for understanding the basic operating laws and characteristics of the transportation system based on the initial information obtained in step S1; the traffic prediction model has a built-in dynamic weight adjustment algorithm, which automatically adjusts the relative weights of various influencing factors based on the real-time changes in traffic mode, travel speed and special events input by the user in step S2; the traffic prediction model incorporates a machine learning algorithm to analyze complex situations in historical data, learn the changing patterns of traffic flow over time, weather, and events, and predict the traffic status in future unit time based on the changing patterns.

[0014] In a preferred embodiment of the present invention, the calculation expression formula of the traffic prediction model is:

[0015]

[0016] Where, T pred (t+1) represents the traffic state predicted at the next unit time (t+1); n represents the number of factors affecting the traffic state; α i and β i represents the baseline weight and dynamic adjustment coefficient of the i-th influencing factor; G(E t ) represents a function about a special event, which is used to adjust the weight according to the nature and severity of the event; F i (t) represents the characteristic value or measurement value of the i-th influencing factor at time t; ML output (t) is the output of the machine learning algorithm at time t, which represents the traffic status prediction value obtained based on historical data and real-time data; ε(t) represents the random error term.

[0017] In a preferred embodiment of the present invention, in step S4, when the shortest path algorithm is selected, the improved Dijkstra algorithm is used to calculate the shortest time from the designated starting point to each traffic node based on the traffic status within the future unit time predicted in step S3; when the grid-based diffusion algorithm is selected, the traffic network is divided into multiple grid areas, and the diffusion process of traffic flow between grid areas is simulated based on the predicted traffic status. By calculating the grid areas that the traffic flow can reach at different time points, all traffic nodes that can be reached from the designated starting point within a specific time are determined.

[0018] In a preferred embodiment of the present invention, when the shortest path algorithm is selected, the calculation formula of the shortest time is:

[0019]

[0020] Where, T ij represents the shortest time from starting point i to traffic node j; k represents the possible path from i to j; P ij represents the set of all possible paths from i to j; t k Represents path P ij The estimated time for the kth segment of the journey.

[0021] In a preferred embodiment of the present invention, when the grid-based diffusion algorithm is used, the calculation formula for all traffic nodes that can be reached within a specific time from a specified starting point is:

[0022]

[0023] Where R(t) represents the set of grid areas that can be reached within a specific time t; i→n represents the estimated time from grid area i where the starting point is located to grid area n; k′ represents the number of grid areas passed from the starting point to grid area n.

[0024] In a preferred embodiment of the present invention, step S4 also includes a verification step; by comparing with actual traffic data, the accuracy of the traffic node arrival time calculated by the shortest path algorithm or the grid-based diffusion algorithm is verified, and the algorithm parameters are optimized and adjusted according to the verification results.

[0025] In a preferred embodiment of the present invention, in step S5, when generating the polygonal boundary of the isochrone circle, the geographic information system technology is used to smooth the boundary of the isochrone circle; at the same time, the front-end visualization platform supports user interaction functions, allowing the user to adjust the parameters of the starting point location and travel time, and view the updated isochrone circle dynamic display in real time.

[0026] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0027] (1) The present invention dynamically adjusts the weights of various factors affecting road traffic flow and combines machine learning algorithms to predict future traffic conditions, thereby providing users with more accurate isochrone information, which helps users better plan travel routes, avoid congested sections, and thus improve travel efficiency.

[0028] (2) By introducing multiple weights, the system can be flexibly adjusted for different traffic modes, road conditions, time periods, and other factors, thereby better adapting to the complex and ever-changing urban traffic environment. Dynamic weight adjustment can be made instantly based on factors such as real-time traffic conditions, weather changes, and special events, thereby promptly responding to real-time changes in urban traffic and improving the accuracy and timeliness of calculations.

[0029] (3) By dynamically adjusting the weights of different roads and modes of transportation, traffic flow can be distributed more evenly, avoiding excessive congestion on certain roads or modes of transportation, and improving overall traffic efficiency. Based on the dynamically adjusted weight information, more reasonable and efficient route planning suggestions can be provided to travelers, helping them avoid congested roads and saving travel time and costs.

[0030] (4) The front-end visualization platform supports user interaction functions, allowing users to adjust parameters such as the starting point location and travel time according to actual needs, and view the updated dynamic display of the isochrone circle in real time, so that users can understand the traffic conditions more intuitively and make corresponding travel decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive efforts.

[0032] Figure 1 It is a flow chart of the method implementation of the preferred embodiment of the present invention. DETAILED DESCRIPTION

[0033] 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.

[0034] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0035] Before describing the technical solutions provided by this invention in detail, it is important to note that the Wikimapia open-source mapping technology employed in this invention is a user-contributed mapping project that allows users to add and edit geographic information. Wikimapia's data coverage and update frequency may not be as extensive or timely as those in OSM. However, it provides a different perspective and data source, potentially containing information not covered by OSM.

[0036] like Figure 1 As shown in FIG, the traffic isochrone visualization application method based on the open source map includes the following steps:

[0037] S1. Utilize Wikimapia open-source mapping technology to obtain initial information on the city's road network, transportation facilities, traffic flow data, weather data, real-time public transportation data, and geographic obstacles, and establish a transportation system. After acquiring information on urban roads, facilities, traffic flow, weather, public transportation, and geographic obstacles, perform data cleaning to remove redundant and erroneous data and improve data quality. Furthermore, discretize continuous data for better application in subsequent steps. Divide the transportation system into multiple modules, such as data acquisition, data processing, predictive modeling, algorithm calculation, and visualization, to facilitate system maintenance and upgrades.

[0038] Furthermore, in step S1, based on the topological structure of the urban road network, traffic facilities and geographical obstacles, a travel road system with object building point information is established; historical data of traffic flow data, weather data and public transportation real-time data are obtained, and a historical learning algorithm is used to obtain the weights of influencing factors affecting travel planning of the travel road system, and a transportation travel system is established.

[0039] Specifically, the urban road network data obtained using Wikimapia open source map technology can include information such as road grade, width, length, and intersection location.

[0040] Transportation facility data may include location and capacity information of bus stops, subway stations, parking lots, gas stations, etc.

[0041] Traffic flow data can be data such as the number of vehicles passing, speed, etc. collected in real time by various sensors (such as cameras, geomagnetic sensors, etc.).

[0042] Weather data may include temperature, humidity, rainfall, wind speed, etc., which may affect road capacity and vehicle speed.

[0043] Real-time public transportation data may include the real-time location of buses, intervals between buses, occupancy rates, etc.

[0044] Geographical obstacles may include rivers, hills, buildings, etc., and these data need to be specially considered when building a transportation system.

[0045] When establishing a transportation system, historical learning algorithms can be used to calculate changes in road capacity under different traffic flows, weather, and public transportation conditions, as well as the weight of the impact of each factor on travel planning.

[0046] S2. The user actively inputs the real-time changes in traffic mode, travel speed, and special events into the traffic system in step S1; in addition, the traffic system can also intelligently recommend the optimal traffic mode and speed based on the user's historical travel data and current traffic conditions, reducing the user's input workload.

[0047] Furthermore, in step S2, the user inputs the travel mode and travel speed selected by the user in real time into the transportation system, and the user also needs to input special events encountered temporarily during the travel as travel influencing factors into the transportation system.

[0048] Specifically, the real-time transportation mode selected by the user may be driving, bus, subway or walking.

[0049] Travel speed may vary depending on the user's chosen mode of transportation, road conditions, weather conditions and other factors.

[0050] Special events may include traffic accidents, road construction, sudden weather changes (such as heavy rain, heavy snow), large-scale events, etc. Users can input this information into the system so that the system can more accurately predict future traffic conditions.

[0051] The transportation system has a special exception handling mechanism for traffic anomalies caused by special events (such as traffic accidents, road closures, etc.) to ensure that the algorithm can correctly handle and predict traffic nodes under these abnormal circumstances.

[0052] Among them, the exception handling mechanism is designed to monitor, identify and handle special events in the traffic network (such as traffic accidents, road closures, sudden weather changes, etc.) in real time, ensuring that the traffic prediction model can accurately reflect the impact of these events on traffic flow, thereby providing more accurate isochrone information.

[0053] Abnormal events are those that occur suddenly or planned and have a significant impact on traffic flow. Examples include sudden events such as traffic accidents and sudden weather changes, and planned events such as road construction and large-scale events.

[0054] Real-time traffic flow data is obtained through sensors, cameras and other devices, and natural language processing technology is used to analyze traffic-related posts on social media, such as road closure notices issued by traffic police departments.

[0055] Set thresholds for indicators such as traffic flow and speed. If the threshold is exceeded, it will be considered an abnormality, and machine learning algorithms will be used to identify abnormal traffic patterns.

[0056] The weights of various influencing factors in the traffic forecast model are dynamically adjusted based on the nature and severity of the abnormal event. For example, when a traffic accident occurs, the weights of the roads surrounding the accident site should be increased to reflect their impact on traffic flow.

[0057] If the abnormal event lasts for a long time or affects a large area, you can consider retraining the traffic prediction model to better adapt to the new traffic conditions.

[0058] After an abnormal event is detected, the shortest path or reachable range from the specified starting point to each traffic node is recalculated. For the grid-based diffusion algorithm, the grid division and diffusion process are adjusted according to the impact range of the abnormal event.

[0059] Abnormal event information, such as accident locations, closed roads, etc., is displayed in real time on the front-end visualization platform. The boundaries of the isochrone zones are updated in real time based on the adjusted traffic prediction model and algorithm calculation results.

[0060] Backtest the exception handling mechanism using historical traffic data and abnormal event data to verify its accuracy and effectiveness. Optimize and adjust the parameters of the exception handling mechanism based on the verification results. Improve and upgrade the exception monitoring and handling algorithms based on the problems and deficiencies discovered.

[0061] S3. The traffic travel system establishes a traffic prediction model based on the initial information. The traffic prediction model dynamically adjusts the weights of various factors affecting road traffic flow according to real-time changes, and introduces machine learning algorithms to predict traffic conditions within a unit of time in the future.

[0062] Furthermore, in step S3, the traffic prediction model establishes a data framework for understanding the basic operating laws and characteristics of the transportation system based on the initial information obtained in step S1; the traffic prediction model has a built-in dynamic weight adjustment algorithm, which automatically adjusts the relative weights of various influencing factors according to the real-time changes in traffic mode, travel speed and special events input by the user in step S2; the traffic prediction model incorporates a machine learning algorithm to analyze complex situations in historical data, learn the changing patterns of traffic flow over time, weather, and events, and predict the traffic status in future unit time based on the changing patterns.

[0063] Furthermore, the calculation formula of the traffic prediction model is:

[0064]

[0065] Where, T pred (t+1) represents the traffic state predicted at the next unit time (t+1); n represents the number of factors affecting the traffic state; α i and β i represents the baseline weight and dynamic adjustment coefficient of the i-th influencing factor; G(E t ) represents a function about a special event, which is used to adjust the weight according to the nature and severity of the event; F i (t) represents the characteristic value or measurement value of the i-th influencing factor at time t; ML output (t) is the output of the machine learning algorithm at time t, which represents the traffic status prediction value obtained based on historical data and real-time data; ε(t) represents the random error term.

[0066] More specifically, for the established prediction model, further deepen and refine the prediction model:

[0067] 1. Deepening the prediction model

[0068] In addition to the initial information, such as road networks, transportation facilities, traffic flow, weather, public transportation, and geographical obstacles, more relevant features can be introduced, such as road type (freeways, main roads, secondary roads, etc.), time periods (peak and off-peak hours), holiday information, and historical accident records, to expand the feature set. The original features can also be processed, such as normalization, standardization, and discretization, to improve the model's learning efficiency and predictive performance.

[0069] Ensemble learning methods (such as random forests, gradient boosting trees, bagging, and boosting) are used to fuse the prediction results of multiple machine learning models to improve prediction stability and accuracy. Traditional machine learning algorithms (such as linear regression, decision trees, and support vector machines) and deep learning models (such as LSTM, GRU, and CNN) are combined to leverage their respective strengths to handle different types of features and data structures.

[0070] Time series analysis methods (such as ARIMA, SARIMA, Prophet, etc.) are used to capture the time dependence of traffic flow and predict the changing trend of future traffic conditions.

[0071] In response to seasonal changes in traffic flow (such as weekdays and weekends, morning and evening rush hours, etc.), seasonal adjustments are made to the forecasting model to improve the accuracy of the forecast.

[0072] Using the above-mentioned deepening scheme, the calculation expression of the traffic prediction model is optimized. The optimized calculation expression is:

[0073]

[0074] Where, T p ' red (t+1) represents the traffic state predicted at the next unit time (t+1); n represents the number of factors affecting the traffic state; α i and β i represents the baseline weight and dynamic adjustment coefficient of the i-th influencing factor; G(E t ) represents a function about a special event, which is used to adjust the weight according to the nature and severity of the event; X i,t Represents the characteristic value or measurement value of the i-th influencing factor at time t. These characteristic values ​​may include road type, time period, holiday information, historical accident records, etc., and are processed by normalization, standardization or discretization; MLA t It represents the output of the machine learning algorithm at time t, representing the traffic status prediction value obtained by learning based on historical data and real-time data. This can be obtained by integrating the prediction results of multiple machine learning models through ensemble learning methods (such as random forest, gradient boosting tree, etc.); TSA t It represents the output of time series analysis at time t, which is used to capture the time dependence of traffic flow. This can be the forecast value obtained by time series analysis methods such as ARIMA, SARIMA, Prophet, etc. t The seasonal adjustment output at time t is used to adjust for seasonal variations in traffic flow (such as weekdays versus weekends, morning and evening rush hours, etc.). This can be achieved by adding seasonal factors or adjusting model parameters.

[0075] 2. Prediction Model Refinement

[0076] Develop an adaptive weight adjustment algorithm that dynamically adjusts the relative weights of various influencing factors based on real-time traffic conditions, weather changes, special events, and other factors. This algorithm can continuously learn and optimize based on a feedback mechanism to adapt to the ever-changing traffic environment.

[0077] Conduct sensitivity analysis on the weights of different influencing factors to determine which factors have the greatest impact on the forecast results, so as to make targeted weight adjustments.

[0078] Select an appropriate machine learning algorithm based on the data type and prediction target, and tune the algorithm parameters (such as learning rate, number of iterations, regularization parameters, etc.) to improve the prediction performance of the model.

[0079] Online learning algorithms (such as Online Gradient Descent, Stochastic Gradient Descent, etc.) are used to enable the model to update and adapt to new traffic data and environmental changes in real time.

[0080] Establish an abnormal event identification and classification mechanism to accurately identify and classify different types of abnormal events such as traffic accidents, road construction, sudden weather changes, etc.

[0081] The impact scope and duration of abnormal events are evaluated so that the impact of these events on traffic flow can be accurately reflected in the prediction model.

[0082] After the abnormal event ends, the prediction model is post-processed to restore the model's normal prediction ability.

[0083] The specific implementation steps for identifying and classifying abnormal events include:

[0084] Collect traffic data in real time, including road volume, speed, occupancy, weather information, and public transportation operation status. Perform data preprocessing, such as denoising, normalization, and standardization, to improve the accuracy of subsequent analysis. Use streaming data processing frameworks (such as Apache Kafka and Apache Flink) to process traffic data in real time. Use distributed databases (such as Hadoop and Cassandra) to store both historical and real-time data.

[0085] Use statistical methods (such as Z-score, IQR, etc.) or machine learning algorithms (such as Isolation Forest, One-Class SVM, etc.) to detect anomalies in the data. Set thresholds so that when certain indicators exceed the threshold, anomaly detection is triggered.

[0086] Based on the nature of abnormal events (such as traffic accidents, road construction, sudden weather changes, etc.), design classifiers (such as decision trees, random forests, support vector machines, etc.) to classify abnormal events. Use historical data and expert knowledge to train classifiers to improve classification accuracy.

[0087] For identified abnormal events, assess the scope and duration of their impact on traffic flow. Spatial propagation models (such as heat map diffusion models) can be used to predict the impact scope of abnormal events. Based on historical and real-time data, the duration of abnormal events can be estimated.

[0088] Then use online learning algorithms (such as Online Gradient Descent, Stochastic Gradient Descent, etc.) to update the prediction model in real time so that it can adapt to new traffic data and environmental changes.

[0089] After detecting an abnormal event, relevant information about the abnormal event (such as type, impact, and duration) is input into the prediction model as features to adjust the model's prediction results. Use programming languages ​​such as Python and Java to implement the abnormal event identification and prediction model algorithms. Use containerization technologies (such as Docker and Kubernetes) to deploy and scale the algorithm services.

[0090] After the abnormal event ends, the prediction model is post-processed to restore the model's normal prediction ability. Historical data can be used to retrain the model, or recovery mechanisms such as forgetting factor and weight decay can be used to gradually eliminate the impact of abnormal events on the model.

[0091] Establish a feedback mechanism to continuously monitor and evaluate the performance of the prediction model. Based on the deviation between the prediction results and the actual traffic conditions, adjust the model parameters and algorithms to improve the accuracy and stability of the prediction.

[0092] S4. Using a shortest path algorithm from graph theory or a grid-based diffusion algorithm, the initial information from step S1 is combined with the traffic status from step S3 to calculate all traffic nodes that can be reached within a specific time from the specified starting point.

[0093] Furthermore, in step S4, when the shortest path algorithm is selected, the improved Dijkstra algorithm is used to calculate the shortest time from the designated starting point to each traffic node based on the traffic status within the future unit time predicted in step S3; when the grid-based diffusion algorithm is selected, the traffic network is divided into multiple grid areas, and the diffusion process of traffic flow between grid areas is simulated based on the predicted traffic status. By calculating the grid areas that the traffic flow can reach at different time points, all traffic nodes that can be reached from the designated starting point within a specific time are determined.

[0094] The improved Dijkstra algorithm involves combining it with the A* algorithm. This approach uses a heuristic function to estimate the cost from the current node to the target node, thereby guiding the search process, reducing unnecessary node visits, and improving algorithm efficiency. Furthermore, the improved Dijkstra algorithm uses a priority queue to manage nodes to be visited. To further improve efficiency, the priority queue's sorting strategy can be dynamically adjusted to prioritize candidates with a high probability of becoming nodes on the shortest path based on real-time traffic conditions and forecast information.

[0095] Specifically, the process of combining the Dijkstra algorithm with the A* algorithm involves: A heuristic function h(n) is used to estimate the cost from the current node n to the target node. In a transportation network, the heuristic function is designed based on a variety of factors, such as geographic distance, real-time traffic speed, historical average speed, and road type (e.g., highway, ordinary road). For example, Euclidean distance or Manhattan distance can be used as a heuristic function for geographic distance, and then weighted according to real-time traffic speed or historical average speed.

[0096] Cost function: The total cost function is f(n) = g(n) + h(n), where g(n) is the actual cost from the starting point to node n (the path length in Dijkstra's algorithm), and h(n) is the estimated value of the heuristic function. During the search process, nodes with smaller f(n) values ​​are preferentially selected for expansion.

[0097] Use a priority queue to manage the nodes to be visited and sort them according to the f(n) value. Each time, take the node with the smallest f(n) value from the queue for expansion.

[0098] For the current node, traverse all its neighboring nodes and calculate the cost of reaching the neighboring node through the current node. If the cost of reaching the neighboring node through the current node is less than the cost of the currently recorded neighboring node, update the cost of the neighboring node and add it to the priority queue.

[0099] The heuristic function h(n) plays a guiding role in the search process, making the search process more inclined to move closer to the target node, thereby reducing unnecessary node visits.

[0100] Priority queues can be implemented using efficient data structures such as binary heaps and Fibonacci heaps. These data structures support fast insertion, deletion, and finding the minimum element.

[0101] The priority queue sorting strategy is dynamically adjusted based on real-time traffic conditions and forecast information. For example, if traffic conditions at a certain node suddenly deteriorate, its priority can be temporarily increased to more quickly find a path around the node.

[0102] Priority queue operation: Add the starting point to the priority queue and set its cost to 0. Extract the node with the lowest cost from the priority queue for expansion, update the costs of its neighboring nodes, and add the updated neighboring nodes to the priority queue. During the search, the priority queue's sorting status is continuously maintained to ensure that the node with the lowest cost is always extracted.

[0103] At the same time, for large-scale transportation networks, the Dijkstra algorithm will be improved for parallel processing, using multi-core processors or distributed computing resources to simultaneously process the shortest path calculations of multiple nodes, thereby significantly shortening the calculation time.

[0104] The traffic network data is distributed and stored on multiple nodes. Each node is responsible for processing the shortest path calculation in its local area, and information exchange and result integration are carried out through the network to realize an efficient distributed improved Dijkstra algorithm.

[0105] Specifically, the traffic network is divided into multiple sub-areas, each corresponding to a computing task. Sub-areas can be divided based on factors such as geographic location, road type, and traffic volume. Computational tasks are then assigned to multiple processors or computing nodes, with each node responsible for processing one or more sub-areas.

[0106] Each node independently executes the improved Dijkstra algorithm in the sub-area it is responsible for, and calculates the shortest path from the specified starting point (or a node in its sub-area) to all nodes in the sub-area.

[0107] During the computation process, nodes need to communicate to exchange information about edge nodes. This can be achieved through network protocols (such as TCP / IP) or distributed messaging systems (such as Kafka). During this communication process, data consistency must be ensured. Technologies such as distributed locks, version control, or consistent hashing can be used to ensure data consistency.

[0108] Paths that cross sub-area boundaries require special handling, which can be addressed by setting flags on boundary nodes or recording boundary paths.

[0109] During parallel computing, it is necessary to regularly synchronize the computation results of each node to ensure that the paths between different sub-areas are connected. Synchronization and communication can be achieved through methods such as the Message Passing Interface (MPI) or shared memory.

[0110] After the parallel calculation is completed, the local calculation results of each node are integrated to construct the shortest path from the specified starting point to the entire transportation network.

[0111] During the integration process, the paths can be optimized, for example, by removing duplicate paths and merging adjacent paths.

[0112] Furthermore, when the shortest path algorithm is selected, the calculation formula for the shortest time is:

[0113]

[0114] Where, T ij represents the shortest time from starting point i to traffic node j; k represents the possible path from i to j; P ij represents the set of all possible paths from i to j; t k Represents path P ij The estimated time for the kth segment of the journey.

[0115] When using the grid-based diffusion algorithm, the calculation formula for all traffic nodes that can be reached within a specific time from a specified starting point is:

[0116]

[0117] Where R(t) represents the set of grid areas that can be reached within a specific time t; i→n represents the estimated time from grid area i where the starting point is located to grid area n; k′ represents the number of grid areas passed from the starting point to grid area n.

[0118] Preferably, step S4 also includes a verification step; by comparing with actual traffic data, the accuracy of the traffic node arrival time calculated by the shortest path algorithm or the grid-based diffusion algorithm is verified, and the algorithm parameters are optimized and adjusted according to the verification results.

[0119] S5. Based on the calculation result in step S4, the polygonal boundary of the isochrone circle is generated, and a front-end visualization platform is constructed using Web technology to realize the dynamic display of the isochrone circle.

[0120] Furthermore, in step S5, when the polygonal boundary of the isochrone circle is generated, the geographic information system technology is used to smooth the boundary of the isochrone circle; at the same time, the front-end visualization platform supports user interaction functions, allowing users to adjust the parameters of the starting position and travel time, and view the updated dynamic display of the isochrone circle in real time.

[0121] This invention, by combining various advanced technologies such as open-source mapping, machine learning algorithms, and geographic information systems, can dynamically adjust the weights of various factors influencing road traffic flow and predict future traffic conditions per unit time. On this basis, we can employ shortest path algorithms from graph theory or grid-based diffusion algorithms to calculate all traffic nodes reachable from a specified starting point within a specific timeframe and generate the polygonal boundaries of the isochrone circles. Finally, we utilize web technology to build a front-end visualization platform, enabling dynamic display of the isochrone circles, providing citizens with intuitive accessibility information and travel decision support.

[0122] The above description is based on the ideal embodiment of the present invention. Based on the above description, relevant personnel can make various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the content of the specification and must be determined according to the scope of the claims.

Claims

1. Traffic isochrone visualization application method based on open source maps, characterized by: The following steps are involved: S1. Utilize Wikimapia open-source mapping technology to obtain initial information on urban road networks, transportation facilities, traffic flow data, weather data, real-time public transportation data, and geographic obstacles, and establish a transportation system. S2. The user actively inputs the real-time changes in traffic mode, travel speed, and special events into the traffic system in step S1; S3. The traffic travel system establishes a traffic prediction model based on the initial information. The traffic prediction model dynamically adjusts the weights of various factors affecting road traffic flow according to real-time changes, and introduces machine learning algorithms to predict traffic conditions within a unit of time in the future. S4. Using a shortest path algorithm from graph theory or a grid-based diffusion algorithm, the initial information from step S1 is combined with the traffic status from step S3 to calculate all traffic nodes that can be reached within a specific time from the specified starting point. S5. Based on the calculation result in step S4, the polygonal boundary of the isochrone circle is generated, and a front-end visualization platform is constructed using Web technology to realize the dynamic display of the isochrone circle.

2. The traffic isochrone visualization application method based on open source maps according to claim 1 is characterized by: In step S1, based on the topological structure of the urban road network, traffic facilities and geographical obstacles, a travel road system with object building point information is established; historical data of the traffic flow data, weather data and public transportation real-time data are obtained, and a historical learning algorithm is used to obtain the weights of the influencing factors affecting the travel planning of the travel road system, and the traffic travel system is established.

3. The traffic isochrone visualization application method based on open source maps according to claim 1 is characterized by: In step S2, the user inputs the travel mode and travel speed selected by the user in real time into the transportation system, and the user also needs to input special events encountered temporarily during the travel as travel influencing factors into the transportation system.

4. The traffic isochrone visualization application method based on open source maps according to claim 1 is characterized by: In step S3, the traffic prediction model establishes a data framework for understanding the basic operating laws and characteristics of the transportation system based on the initial information obtained in step S1; the traffic prediction model has a built-in dynamic weight adjustment algorithm, which automatically adjusts the relative weights of various influencing factors according to the real-time changes in traffic mode, travel speed and special events input by the user in step S2; the traffic prediction model incorporates a machine learning algorithm to analyze complex situations in historical data, learn the changing patterns of traffic flow over time, weather, and events, and predict the traffic status in future unit time based on the changing patterns.

5. The traffic isochrone visualization application method based on open source maps according to claim 4 is characterized by: The calculation expression formula of the traffic prediction model is: Where, T pred (t+1) represents the traffic state predicted at the next unit time (t+1); n represents the number of factors affecting the traffic state; α i and β i represents the baseline weight and dynamic adjustment coefficient of the i-th influencing factor; G(E t ) represents a function about a special event, which is used to adjust the weight according to the nature and severity of the event; F i (t) represents the characteristic value or measurement value of the i-th influencing factor at time t; ML output (t) is the output of the machine learning algorithm at time t, which represents the traffic status prediction value obtained based on historical data and real-time data; ε(t) represents the random error term.

6. The traffic isochrone visualization application method based on open source maps according to claim 1 is characterized by: In step S4, when the shortest path algorithm is selected, the improved Dijkstra algorithm is used to calculate the shortest time from the designated starting point to each traffic node according to the traffic state within the future unit time predicted in step S3; When the grid-based diffusion algorithm is selected, the traffic network is divided into multiple grid areas, and the diffusion process of traffic flow between grid areas is simulated based on the predicted traffic status. By calculating the grid areas that traffic flow can reach at different time points, all traffic nodes that can be reached from a specified starting point within a specific time are determined.

7. The traffic isochrone visualization application method based on open source maps according to claim 6 is characterized by: When the shortest path algorithm is used, the calculation formula of the shortest time is: Where, T ij represents the shortest time from starting point i to traffic node j; k represents the possible path from i to j; P ij represents the set of all possible paths from i to j; t k Represents path P ij The estimated time for the kth segment of the journey.

8. The traffic isochrone visualization application method based on open source maps according to claim 6 is characterized by: When the grid-based diffusion algorithm is used, the calculation formula for all traffic nodes that can be reached within a specific time from a specified starting point is: Where R(t) represents the set of grid areas that can be reached within a specific time t; i→n It represents the estimated time from grid area i where the starting point is located to grid area n; k′ represents the number of grid areas passed from the starting point to grid area n.

9. The traffic isochrone visualization application method based on open source maps according to claim 6 is characterized by: In step S4, a verification step is also included; by comparing with actual traffic data, the accuracy of the traffic node arrival time calculated by the shortest path algorithm or the grid-based diffusion algorithm is verified, and the algorithm parameters are optimized and adjusted according to the verification results.

10. The traffic isochrone visualization application method based on open source maps according to claim 1 is characterized by: In step S5, when the polygonal boundary of the isochrone circle is generated, the geographic information system technology is used to smooth the isochrone circle boundary; at the same time, the front-end visualization platform supports user interaction functions, allowing the user to adjust the parameters of the starting point location and travel time, and view the updated isochrone circle dynamic display in real time.

Images