Traffic optimization and path planning method and system based on agent map, and medium

Abstract

The invention provides a traffic optimization and path planning method and system based on an intelligent agent map, and a medium. The method comprises the following steps: collecting travel information of a target user, extracting travel demand data and travel preference data, obtaining a plurality of alternative travel paths according to the travel demand data, processing according to the travel preference data to obtain user target preference data, obtaining traffic characteristic data corresponding to each alternative travel path, and sending the traffic characteristic data to the user. Comprising road information data, traffic flow data and traffic signal lamp information data, obtaining real-time weather condition data, processing through a preset path optimization algorithm in combination with user target preference data and traffic characteristic data, obtaining a path recommendation coefficient corresponding to each alternative travel path, and recommending the path recommendation coefficient to the user. And obtaining an optimal path according to the path recommendation coefficient, and pushing the optimal path to the target user, thereby realizing a traffic optimization and path planning technology based on the agent map.

Description

Technical Field

[0001] The present application relates to the field of transportation technology, and more specifically, to a method, system, and medium for traffic optimization and path planning based on an intelligent agent graph. Background Art

[0002] With the acceleration of urbanization and the continuous growth of the number of motor vehicles, urban traffic congestion is becoming increasingly serious. Traditional traffic planning and management methods have many limitations when dealing with complex and changing traffic conditions. For example, existing path planning algorithms often only consider single factors such as road distance and travel speed, lacking a comprehensive consideration of the global state of the entire traffic network, making it difficult to provide users with the optimal path in complex traffic scenarios. In terms of traffic flow prediction, traditional methods also find it difficult to accurately capture the spatiotemporal variation patterns of traffic flow, and cannot provide a reliable basis for traffic optimization and path planning.

[0003] In response to the above problems, effective technical solutions are urgently needed. Summary of the Invention

[0004] The purpose of this application is to provide a traffic optimization and route planning method, system and medium based on an intelligent agent graph. The method can extract the travel demand data and travel preference data of the target user, obtain multiple alternative travel routes according to the travel demand data, obtain the user's target preference data according to the travel preference data, obtain the traffic characteristic data corresponding to each alternative travel route, obtain real-time weather condition data, combine the user's target preference data and traffic characteristic data with a preset path optimization algorithm for processing, obtain the path recommendation coefficient corresponding to each alternative travel route, obtain the optimal path according to the path recommendation coefficient, and push it to the target user, thereby realizing a technology of traffic optimization and route planning based on an intelligent agent graph.

[0005] This application also provides a traffic optimization and path planning method based on an agent graph, which includes the following steps:

[0006] Collect travel information of target users and extract travel demand data and travel preference data;

[0007] Acquire multiple alternative travel routes based on the travel demand data, and obtain user target preference data based on the travel preference data;

[0008] Obtaining traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic signal light information data;

[0009] Acquire real-time weather condition data, combine it with the user's target preference data and traffic characteristic data, and process it through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path;

[0010] The optimal path is obtained according to the path recommendation coefficient and pushed to the target user.

[0011] Optionally, in the agent-graph-based traffic optimization and route planning method described in the present application, the collecting of target user's travel information and the extraction of travel demand data and travel preference data include:

[0012] Collect target users' travel information and obtain travel demand data and travel preference data through extraction and processing;

[0013] The travel demand data includes departure data, destination data and travel mode data;

[0014] The travel preference data includes one or more of shortest time preference data, shortest distance preference data, least fee preference data, and lowest fuel consumption preference data.

[0015] Optionally, in the agent-graph-based traffic optimization and route planning method described in the present application, the step of obtaining a plurality of alternative travel routes based on the travel demand data and obtaining user target preference data based on travel preference data includes:

[0016] Acquire multiple alternative travel routes based on the departure place data, destination data, and travel mode data;

[0017] If the travel preference data is one, then the travel preference data is the user target preference data;

[0018] If there are multiple travel preference data, weight coefficients are assigned to the multiple travel preference data according to a preset weighting method, and user target preference data are obtained through processing.

[0019] Optionally, in the agent-graph-based traffic optimization and path planning method described in the present application, the obtaining of traffic characteristic data corresponding to each alternative travel path, including road information data, traffic flow data, and traffic signal light information data, includes:

[0020] The road information data includes road length data, lane number data, lane width data, road capacity data and road grade data;

[0021] The traffic flow data includes real-time traffic flow data, real-time average vehicle speed data, real-time vehicle density data and historical traffic flow data;

[0022] The traffic light information data includes traffic light quantity data, traffic light cycle data, and traffic light duration data.

[0023] Optionally, in the agent-graph-based traffic optimization and route planning method described in the present application, obtaining real-time weather condition data, combining the user target preference data and traffic characteristic data with a preset route optimization algorithm to obtain a route recommendation coefficient corresponding to each alternative travel route, includes:

[0024] Acquire real-time weather condition data, combine it with the road information data, and process it using a preset weather impact assessment model to obtain a capacity adjustment coefficient corresponding to each of the alternative travel routes;

[0025] According to the capacity adjustment coefficient, the user target preference data and the traffic characteristic data are processed through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path.

[0026] Optionally, in the agent-graph-based traffic optimization and path planning method described in the present application, obtaining the optimal path according to the path recommendation coefficient and pushing it to the target user includes:

[0027] Sorting and comparing the path recommendation coefficients, and filtering out the maximum value data of the path recommendation coefficients;

[0028] The alternative travel path corresponding to the maximum value data is the optimal path;

[0029] The optimal route is pushed to the target user via a mobile device, vehicle-mounted device or wearable device.

[0030] In a second aspect, the present application provides a traffic optimization and path planning system based on an agent graph, the system comprising: a memory and a processor, the memory comprising a program for a traffic optimization and path planning method based on an agent graph, the program for the traffic optimization and path planning method based on an agent graph, when executed by the processor, implementing the following steps:

[0031] Collect travel information of target users and extract travel demand data and travel preference data;

[0032] Acquire multiple alternative travel routes based on the travel demand data, and obtain user target preference data based on the travel preference data;

[0033] Obtaining traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic signal light information data;

[0034] Acquire real-time weather condition data, combine it with the user's target preference data and traffic characteristic data, and process it through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path;

[0035] The optimal path is obtained according to the path recommendation coefficient and pushed to the target user.

[0036] Optionally, in the agent-graph-based traffic optimization and route planning system described in the present application, the collecting of target user's travel information and the extraction of travel demand data and travel preference data include:

[0037] Collect target users' travel information and obtain travel demand data and travel preference data through extraction and processing;

[0038] The travel demand data includes departure data, destination data and travel mode data;

[0039] The travel preference data includes one or more of shortest time preference data, shortest distance preference data, least fee preference data, and lowest fuel consumption preference data.

[0040] Optionally, in the agent-graph-based traffic optimization and route planning system described in the present application, the step of obtaining a plurality of alternative travel routes based on the travel demand data and obtaining user target preference data based on the travel preference data includes:

[0041] Acquire multiple alternative travel routes based on the departure place data, destination data, and travel mode data;

[0042] If the travel preference data is one, then the travel preference data is the user target preference data;

[0043] If there are multiple travel preference data, weight coefficients are assigned to the multiple travel preference data according to a preset weighting method, and user target preference data are obtained through processing.

[0044] In a third aspect, the present application also provides a computer-readable storage medium, which stores a traffic optimization and path planning method program based on an intelligent agent graph. When the traffic optimization and path planning method program based on an intelligent agent graph is executed by a processor, the steps of the traffic optimization and path planning method based on an intelligent agent graph as described in any one of the above items are implemented.

[0045] From the above, it can be seen that the traffic optimization and path planning method, system and medium based on the intelligent agent graph provided by this application collects the travel information of the target user, extracts travel demand data and travel preference data, obtains multiple alternative travel paths according to the travel demand data, obtains user target preference data according to the travel preference data, obtains traffic characteristic data corresponding to each alternative travel path, including road information data, traffic flow data and traffic light information data, obtains real-time weather condition data, and combines the user target preference data and traffic characteristic data through a preset path optimization algorithm for processing, obtains the path recommendation coefficient corresponding to each alternative travel path, obtains the optimal path according to the path recommendation coefficient, and pushes it to the target user, thereby realizing the technology of traffic optimization and path planning based on the intelligent agent graph.

[0046] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A flow chart of the agent-based traffic optimization and path planning method provided in an embodiment of the present application;

[0049] Figure 2 A flow chart of extracting travel demand data and travel preference data for the agent-based traffic optimization and route planning method provided in an embodiment of the present application;

[0050] Figure 3 A flow chart of obtaining a path recommendation coefficient for the agent-based traffic optimization and path planning method provided in an embodiment of the present application;

[0051] Figure 4 A flow chart of obtaining the optimal path for the traffic optimization and path planning method based on the intelligent agent graph provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0053] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0054] Please refer to Figure 1 , Figure 1 This is a flow chart of an agent-based traffic optimization and path planning method in some embodiments of the present application. This agent-based traffic optimization and path planning method is used in a terminal device, such as a computer or mobile phone terminal. This agent-based traffic optimization and path planning method includes the following steps:

[0055] S11. Collect travel information of target users and extract travel demand data and travel preference data;

[0056] S12. Acquire multiple alternative travel routes based on the travel demand data, and obtain user target preference data based on the travel preference data;

[0057] S13. Obtaining traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic signal light information data;

[0058] S14: Acquire real-time weather condition data, combine it with the user's target preference data and traffic characteristic data, and process it using a preset route optimization algorithm to obtain a route recommendation coefficient corresponding to each alternative travel route;

[0059] S15. Obtain the optimal path according to the path recommendation coefficient and push it to the target user.

[0060] It should be noted that users often have their own needs when traveling, and the needs of each user are different. Many users even hope to combine several goals, such as considering factors such as time, distance, and fees at the same time, which traditional traffic flow optimization and route planning cannot meet. In this regard, in this embodiment, first, by collecting the travel information of the target user, such as travel mode and destination, and then extracting travel demand data and travel preference data, several possible travel routes are screened out based on the travel demand data, and then the user's target preference data is obtained based on the travel preference data. If the user has multiple preferences, it is necessary to obtain the final target preference by assigning weights, obtain the traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic light information data, obtain real-time weather condition data, and combine the user's target preference data and traffic characteristic data through a preset path optimization algorithm to obtain the path recommendation coefficient corresponding to each alternative travel route. The optimal path is obtained based on the path recommendation coefficient and pushed to the target user, thereby realizing the technology of traffic optimization and route planning based on the intelligent agent map.

[0061] Please refer to Figure 2 , Figure 2 This is a flow chart of extracting travel demand data and travel preference data from an agent-based traffic optimization and route planning method in some embodiments of the present application. According to an embodiment of the present invention, collecting travel information of a target user and extracting travel demand data and travel preference data includes:

[0062] S21. Collect travel information of target users and obtain travel demand data and travel preference data through extraction and processing;

[0063] S22, the travel demand data includes departure data, destination data and travel mode data;

[0064] S23. The travel preference data includes one or more of the shortest time preference data, the shortest distance preference data, the lowest fee preference data, and the lowest fuel consumption preference data.

[0065] It should be noted that in order to plan the optimal route for the target user, it is necessary to first understand the target user's travel information, including the departure place, destination and travel mode, so that a matching alternative route can be preliminarily selected. To ultimately obtain the optimal route, it is necessary to fully understand the target user's personal travel preferences, which may be one of the preferences for shortest time, shortest distance, least toll and lowest fuel consumption, or a combination of multiple preferences.

[0066] According to an embodiment of the present invention, the step of obtaining a plurality of alternative travel routes based on the travel demand data and obtaining user target preference data based on the travel preference data includes:

[0067] Acquire multiple alternative travel routes based on the departure place data, destination data, and travel mode data;

[0068] If the travel preference data is one, then the travel preference data is the user target preference data;

[0069] If there are multiple travel preference data, weight coefficients are assigned to the multiple travel preference data according to a preset weighting method, and user target preference data are obtained through processing.

[0070] It should be noted that multiple alternative travel routes are generated based on the departure place, destination and travel mode. These routes need to be further evaluated later. As for the user's target preference data, it must be determined according to the travel preference. For target users with only one travel preference, such as the shortest time, then the target preference data is the corresponding shortest time. If the travel preference data is greater than one, then it is necessary to assign weights to these multiple travel preferences according to the weighting method and combine them to obtain the final user target preference data. Among them, the common weighting methods are subjective weighting method, objective weighting method and combined weighting method. You can choose the appropriate weighting method according to the actual scenario.

[0071] According to an embodiment of the present invention, the acquiring of traffic characteristic data corresponding to each alternative travel path, including road information data, traffic flow data, and traffic light information data, includes:

[0072] The road information data includes road length data, lane number data, lane width data, road capacity data and road grade data;

[0073] The traffic flow data includes real-time traffic flow data, real-time average vehicle speed data, real-time vehicle density data and historical traffic flow data;

[0074] The traffic light information data includes traffic light quantity data, traffic light cycle data, and traffic light duration data.

[0075] It should be noted that a crucial part of screening the optimal route is to fully understand the traffic characteristics of the alternative routes every day, including road information data, traffic flow data and traffic light information data. Among them, road information data includes road length, number of lanes, lane width, road capacity and road grade data. These data reflect information such as theoretical travel time, road capacity and road carrying capacity. Traffic flow data includes real-time traffic flow, real-time average speed, real-time vehicle density and historical traffic flow data. Real-time traffic flow, real-time average speed and real-time vehicle density reflect the current traffic status, while historical traffic flow data can be used as a reference for future travel time periods and for predicting traffic conditions. Traffic light information data includes the number of lights, light cycles and light duration data. These data reflect the timing plan of the lights and directly affect the traffic efficiency of vehicles.

[0076] Please refer to Figure 3 , Figure 3 This is a flow chart for obtaining a route recommendation coefficient for an agent-based traffic optimization and route planning method in some embodiments of the present application. According to embodiments of the present invention, obtaining real-time weather condition data, combining it with the user's target preference data and traffic characteristics data, and processing it using a preset route optimization algorithm to obtain a route recommendation coefficient corresponding to each alternative travel route includes:

[0077] S31. Acquire real-time weather condition data, combine it with the road information data, and process it using a preset weather impact assessment model to obtain a capacity adjustment coefficient corresponding to each alternative travel path;

[0078] S32. Processing the capacity adjustment coefficient in combination with the user target preference data and the traffic characteristic data through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path.

[0079] It should be noted that weather is one of the important factors affecting traffic, especially severe weather (such as heavy rain, heavy snow, heavy fog, etc.) will significantly affect the driving speed and safety of vehicles, leading to traffic congestion, and different roads are affected differently by weather. Therefore, it is necessary to obtain real-time weather condition data, and combine it with road information data to process it through a preset weather impact assessment model to obtain the capacity adjustment coefficient corresponding to each alternative travel path. Among them, the weather impact assessment model is a neural network model. The initialized weather impact assessment model is trained based on a large amount of historical weather condition data and road information data to obtain a trained weather impact assessment model. Furthermore, the user target preference data and the traffic characteristic data corresponding to each alternative path are processed through a preset path optimization algorithm to obtain the path recommendation coefficient corresponding to each alternative travel path. Among them, the path optimization algorithm is selected according to the actual scenario needs. For example, the NSGA-II algorithm or the weighted sum method in the multi-objective optimization algorithm can be used.

[0080] Please refer to Figure 4 , Figure 4 This is a flow chart of obtaining the optimal path for a traffic optimization and path planning method based on an agent graph in some embodiments of the present application. According to an embodiment of the present invention, obtaining the optimal path based on the path recommendation coefficient and pushing it to the target user includes:

[0081] S41, performing sorting and comparison processing according to the path recommendation coefficients, and screening out the maximum value data of the path recommendation coefficients;

[0082] S42: The alternative travel path corresponding to the maximum value data is the optimal path;

[0083] S43: Push the optimal path to the target user via a mobile device, a vehicle-mounted device, or a wearable device.

[0084] It should be noted that the path recommendation coefficients are sorted and the maximum value among all path recommendation coefficients is screened out. The alternative travel path corresponding to the maximum value is the optimal path, and then the optimal path is pushed to the target user through mobile devices, vehicle-mounted devices or wearable devices.

[0085] According to an embodiment of the present invention, the further embodiment includes:

[0086] Real-time monitoring of the road conditions of the optimal path and extraction of road condition data, including average vehicle speed data, traffic volume data, and maximum vehicle queue length data;

[0087] Obtaining a preset road congestion threshold set, including a preset vehicle average speed abnormal point threshold, a preset traffic flow exceeding threshold, and a preset vehicle queue length exceeding threshold;

[0088] Performing a threshold comparison based on the road condition data and three thresholds corresponding to the preset road congestion condition threshold set;

[0089] If the comparison results of the three thresholds are all less than the corresponding thresholds of the preset road congestion threshold set, the optimal path remains unchanged;

[0090] If the comparison results of the three thresholds are not all smaller than the corresponding thresholds of the preset road congestion threshold set, the optimal path is no longer suitable, and the path needs to be replanned and the target user is reminded.

[0091] It should be noted that when the target user adopts the optimal route pushed by the system to pass through, the road traffic conditions of the optimal route are monitored in real time, including the average vehicle speed, traffic volume and maximum length of vehicle queues, and compared with the corresponding preset threshold set. If any of the comparison data exceeds the threshold, it means that the road conditions have suddenly deteriorated, and the route needs to be re-evaluated and the target user needs to be reminded accordingly.

[0092] In a second aspect, the present invention further discloses an agent-based traffic optimization and path planning system, comprising a memory and a processor, wherein the memory includes an agent-based traffic optimization and path planning method program, and when the agent-based traffic optimization and path planning method program is executed by the processor, the following steps are implemented:

[0093] Collect travel information of target users and extract travel demand data and travel preference data;

[0094] Acquire multiple alternative travel routes based on the travel demand data, and obtain user target preference data based on the travel preference data;

[0095] Obtaining traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic signal light information data;

[0096] Acquire real-time weather condition data, combine it with the user's target preference data and traffic characteristic data, and process it through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path;

[0097] The optimal path is obtained according to the path recommendation coefficient and pushed to the target user.

[0098] It should be noted that users often have their own needs when traveling, and the needs of each user are different. Many users even hope to combine several goals, such as considering factors such as time, distance, and fees at the same time, which traditional traffic flow optimization and route planning cannot meet. In this regard, in this embodiment, first, by collecting the travel information of the target user, such as travel mode and destination, and then extracting travel demand data and travel preference data, several possible travel routes are screened out based on the travel demand data, and then the user's target preference data is obtained based on the travel preference data. If the user has multiple preferences, it is necessary to obtain the final target preference by assigning weights, obtain the traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic light information data, obtain real-time weather condition data, and combine the user's target preference data and traffic characteristic data through a preset path optimization algorithm to obtain the path recommendation coefficient corresponding to each alternative travel route. The optimal path is obtained based on the path recommendation coefficient and pushed to the target user, thereby realizing the technology of traffic optimization and route planning based on the intelligent agent map.

[0099] According to an embodiment of the present invention, collecting the target user's travel information and extracting travel demand data and travel preference data includes:

[0100] Collect target users' travel information and obtain travel demand data and travel preference data through extraction and processing;

[0101] The travel demand data includes departure data, destination data and travel mode data;

[0102] The travel preference data includes one or more of shortest time preference data, shortest distance preference data, least fee preference data, and lowest fuel consumption preference data.

[0103] It should be noted that in order to plan the optimal route for the target user, it is necessary to first understand the target user's travel information, including the departure place, destination and travel mode, so that a matching alternative route can be preliminarily selected. To ultimately obtain the optimal route, it is necessary to fully understand the target user's personal travel preferences, which may be one of the preferences for shortest time, shortest distance, least toll and lowest fuel consumption, or a combination of multiple preferences.

[0104] According to an embodiment of the present invention, the step of obtaining a plurality of alternative travel routes based on the travel demand data and obtaining user target preference data based on the travel preference data includes:

[0105] Acquire multiple alternative travel routes based on the departure place data, destination data, and travel mode data;

[0106] If the travel preference data is one, then the travel preference data is the user target preference data;

[0107] If there are multiple travel preference data, weight coefficients are assigned to the multiple travel preference data according to a preset weighting method, and user target preference data are obtained through processing.

[0108] It should be noted that multiple alternative travel routes are generated based on the departure place, destination and travel mode. These routes need to be further evaluated later. As for the user's target preference data, it must be determined according to the travel preference. For target users with only one travel preference, such as the shortest time, then the target preference data is the corresponding shortest time. If the travel preference data is greater than one, then it is necessary to assign weights to these multiple travel preferences according to the weighting method and combine them to obtain the final user target preference data. Among them, the common weighting methods are subjective weighting method, objective weighting method and combined weighting method. You can choose the appropriate weighting method according to the actual scenario.

[0109] According to an embodiment of the present invention, the acquiring of traffic characteristic data corresponding to each alternative travel path, including road information data, traffic flow data, and traffic light information data, includes:

[0110] The road information data includes road length data, lane number data, lane width data, road capacity data and road grade data;

[0111] The traffic flow data includes real-time traffic flow data, real-time average vehicle speed data, real-time vehicle density data and historical traffic flow data;

[0112] The traffic light information data includes traffic light quantity data, traffic light cycle data, and traffic light duration data.

[0113] It should be noted that a crucial part of screening the optimal route is to fully understand the traffic characteristics of the alternative routes every day, including road information data, traffic flow data and traffic light information data. Among them, road information data includes road length, number of lanes, lane width, road capacity and road grade data. These data reflect information such as theoretical travel time, road capacity and road carrying capacity. Traffic flow data includes real-time traffic flow, real-time average speed, real-time vehicle density and historical traffic flow data. Real-time traffic flow, real-time average speed and real-time vehicle density reflect the current traffic status, while historical traffic flow data can be used as a reference for future travel time periods and for predicting traffic conditions. Traffic light information data includes the number of lights, light cycles and light duration data. These data reflect the timing plan of the lights and directly affect the traffic efficiency of vehicles.

[0114] According to an embodiment of the present invention, the real-time weather condition data is acquired, combined with the user target preference data and traffic characteristic data, and processed using a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path, including:

[0115] Acquire real-time weather condition data, combine it with the road information data, and process it using a preset weather impact assessment model to obtain a capacity adjustment coefficient corresponding to each of the alternative travel routes;

[0116] According to the capacity adjustment coefficient, the user target preference data and the traffic characteristic data are processed through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path.

[0117] It should be noted that weather is one of the important factors affecting traffic, especially severe weather (such as heavy rain, heavy snow, heavy fog, etc.) will significantly affect the driving speed and safety of vehicles, leading to traffic congestion, and different roads are affected differently by weather. Therefore, it is necessary to obtain real-time weather condition data, and combine it with road information data to process it through a preset weather impact assessment model to obtain the capacity adjustment coefficient corresponding to each alternative travel path. Among them, the weather impact assessment model is a neural network model. The initialized weather impact assessment model is trained based on a large amount of historical weather condition data and road information data to obtain a trained weather impact assessment model. Furthermore, the user target preference data and the traffic characteristic data corresponding to each alternative path are processed through a preset path optimization algorithm to obtain the path recommendation coefficient corresponding to each alternative travel path. Among them, the path optimization algorithm is selected according to the actual scenario needs. For example, the NSGA-II algorithm or the weighted sum method in the multi-objective optimization algorithm can be used.

[0118] According to an embodiment of the present invention, obtaining the optimal path according to the path recommendation coefficient and pushing it to the target user includes:

[0119] Sorting and comparing the path recommendation coefficients, and filtering out the maximum value data of the path recommendation coefficients;

[0120] The alternative travel path corresponding to the maximum value data is the optimal path;

[0121] The optimal route is pushed to the target user via a mobile device, vehicle-mounted device or wearable device.

[0122] It should be noted that the path recommendation coefficients are sorted and the maximum value among all path recommendation coefficients is screened out. The alternative travel path corresponding to the maximum value is the optimal path, and then the optimal path is pushed to the target user through mobile devices, vehicle-mounted devices or wearable devices.

[0123] According to an embodiment of the present invention, the further embodiment includes:

[0124] Real-time monitoring of the road conditions of the optimal path and extraction of road condition data, including average vehicle speed data, traffic volume data, and maximum vehicle queue length data;

[0125] Obtaining a preset road congestion threshold set, including a preset vehicle average speed abnormal point threshold, a preset traffic flow exceeding threshold, and a preset vehicle queue length exceeding threshold;

[0126] Performing a threshold comparison based on the road condition data and three thresholds corresponding to the preset road congestion condition threshold set;

[0127] If the comparison results of the three thresholds are all less than the corresponding thresholds of the preset road congestion threshold set, the optimal path remains unchanged;

[0128] If the comparison results of the three thresholds are not all smaller than the corresponding thresholds of the preset road congestion threshold set, the optimal path is no longer suitable, and the path needs to be replanned and the target user is reminded.

[0129] It should be noted that when the target user adopts the optimal route pushed by the system to pass through, the road traffic conditions of the optimal route are monitored in real time, including the average vehicle speed, traffic volume and maximum length of vehicle queues, and compared with the corresponding preset threshold set. If any of the comparison data exceeds the threshold, it means that the road conditions have suddenly deteriorated, and the route needs to be re-evaluated and the target user needs to be reminded accordingly.

[0130] The third aspect of the present invention provides a readable storage medium, which stores a traffic optimization and path planning method program based on an intelligent agent graph. When the traffic optimization and path planning method program based on an intelligent agent graph is executed by a processor, the steps of the traffic optimization and path planning method based on an intelligent agent graph as described in any one of the above items are implemented.

[0131] The present invention discloses a method, system and medium for traffic optimization and route planning based on an intelligent agent graph. The method collects travel information of target users, extracts travel demand data and travel preference data, obtains multiple alternative travel routes based on the travel demand data, obtains user target preference data based on the travel preference data, obtains traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data and traffic light information data, obtains real-time weather condition data, and processes the user target preference data and traffic characteristic data through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel route. The optimal path is obtained based on the path recommendation coefficient and pushed to the target user, thereby realizing a technology for traffic optimization and route planning based on an intelligent agent graph.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0133] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0134] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0135] Those skilled in the art will understand that all or part of the steps of the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc. Various media that can store program codes.

[0136] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. Traffic optimization and path planning method based on agent graph, characterized by: The following steps are involved: Collect travel information of target users and extract travel demand data and travel preference data; Acquire multiple alternative travel routes based on the travel demand data, and obtain user target preference data based on the travel preference data; Obtaining traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic signal light information data; Acquire real-time weather condition data, combine it with the user's target preference data and traffic characteristic data, and process it through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path; The optimal path is obtained according to the path recommendation coefficient and pushed to the target user.

2. The agent-based traffic optimization and path planning method according to claim 1, characterized in that: The collecting of target user's travel information and extracting travel demand data and travel preference data includes: Collect travel information of target users and obtain travel demand data and travel preference data through extraction and processing; The travel demand data includes departure data, destination data and travel mode data; The travel preference data includes one or more of shortest time preference data, shortest distance preference data, least fee preference data, and lowest fuel consumption preference data.

3. The traffic optimization and path planning method based on agent graph according to claim 2 is characterized in that: The step of obtaining a plurality of alternative travel routes according to the travel demand data and obtaining user target preference data according to the travel preference data includes: Acquire multiple alternative travel routes based on the departure place data, destination data, and travel mode data; If the travel preference data is one, then the travel preference data is the user target preference data; If there are multiple travel preference data, weight coefficients are assigned to the multiple travel preference data according to a preset weighting method, and user target preference data are obtained through processing.

4. The agent-based traffic optimization and path planning method according to claim 3, characterized in that: The obtaining of traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic light information data, includes: The road information data includes road length data, lane number data, lane width data, road capacity data and road grade data; The traffic flow data includes real-time traffic flow data, real-time average vehicle speed data, real-time vehicle density data and historical traffic flow data; The traffic light information data includes traffic light quantity data, traffic light cycle data, and traffic light duration data.

5. The agent-based traffic optimization and path planning method according to claim 4, characterized in that: The real-time weather condition data is acquired, combined with the user target preference data and traffic characteristic data, and processed by a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path, including: Acquire real-time weather condition data, combine it with the road information data, and process it using a preset weather impact assessment model to obtain a capacity adjustment coefficient corresponding to each of the alternative travel routes; According to the capacity adjustment coefficient, the user target preference data and the traffic characteristic data are processed through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path.

6. The agent-based traffic optimization and path planning method according to claim 5, characterized in that: The obtaining of the optimal path according to the path recommendation coefficient and pushing the optimal path to the target user includes: Sorting and comparing the path recommendation coefficients, and filtering out the maximum value data of the path recommendation coefficients; The alternative travel path corresponding to the maximum value data is the optimal path; The optimal route is pushed to the target user via a mobile device, vehicle-mounted device or wearable device.

7. Traffic optimization and path planning system based on agent graph, characterized by: The system includes: a memory and a processor, wherein the memory includes a program for a traffic optimization and path planning method based on an agent graph, and when the program for the traffic optimization and path planning method based on an agent graph is executed by the processor, the following steps are implemented: Collect travel information of target users and extract travel demand data and travel preference data; Acquire multiple alternative travel routes based on the travel demand data, and obtain user target preference data based on the travel preference data; Obtaining traffic characteristic data corresponding to each alternative travel route, including road information data, traffic flow data, and traffic signal light information data; Acquire real-time weather condition data, combine it with the user's target preference data and traffic characteristic data, and process it through a preset path optimization algorithm to obtain a path recommendation coefficient corresponding to each alternative travel path; The optimal path is obtained according to the path recommendation coefficient and pushed to the target user.

8. The agent-based traffic optimization and path planning system according to claim 7, characterized in that: The collecting of target user's travel information and extracting travel demand data and travel preference data includes: Collect travel information of target users and obtain travel demand data and travel preference data through extraction and processing; The travel demand data includes departure data, destination data and travel mode data; The travel preference data includes one or more of shortest time preference data, shortest distance preference data, least fee preference data, and lowest fuel consumption preference data.

9. The agent-based traffic optimization and path planning system according to claim 8, characterized in that: The step of obtaining a plurality of alternative travel routes according to the travel demand data and obtaining user target preference data according to the travel preference data includes: Acquire multiple alternative travel routes based on the departure place data, destination data, and travel mode data; If the travel preference data is one, then the travel preference data is the user target preference data; If there are multiple travel preference data, weight coefficients are assigned to the multiple travel preference data according to a preset weighting method, and user target preference data are obtained through processing.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a traffic optimization and path planning method program based on an intelligent agent graph. When the traffic optimization and path planning method program based on an intelligent agent graph is executed by a processor, the steps of the traffic optimization and path planning method based on an intelligent agent graph as described in any one of claims 1 to 6 are implemented.

Images