Electric vehicle charging path planning method and system

Abstract

The present application provides a method and system for planning a charging path for an electric vehicle. Among them, an initial path topology map is generated based on the remaining power of the vehicle, the real-time location and the destination coordinates, combined with the dynamic operation data of the charging stations in the area (such as the number of available charging piles, charging power, etc.). By considering the impact of road slope, ambient temperature and traffic speed fluctuations on power consumption, when the power is insufficient to complete continuous sections, the candidate path subgraph containing the charging station is activated. Further, a multidimensional decision function is generated based on the grid load association parameters and user behavior characteristics, and the candidate paths are prioritized through a hierarchical mechanism. In different scenarios (highways and urban areas), multiple parameters are used to optimize path selection. Finally, all information is integrated, and the energy consumption estimate is adjusted in real time to generate an adaptive charging path instruction set. The technical solution provided in the embodiment of the present application improves the feasibility and convenience of electric vehicle charging path planning.

Description

Technical Field

[0001] The present application relates to the cross-technical field of energy management, and in particular to a method and system for planning a charging path for an electric vehicle. Background Art

[0002] With the popularity of electric vehicles (EVs), users have put forward higher requirements for charging convenience and efficiency during long-distance travel. In practical applications, drivers not only need to know the remaining power of the vehicle and the power required to reach the destination, but also need to obtain real-time information about charging stations along the way, including the available number of charging piles, real-time charging power, and grid load conditions.

[0003] Most existing electric vehicle charging route planning schemes are calculated based on static data, that is, they use preset charging pile location information, basic power consumption model and other parameters to plan the route. These schemes usually consider the location of the charging station at the starting point, the end point and several fixed points along the way, and perform simple route planning based on the remaining power of the vehicle. In addition, some advanced systems also refer to historical traffic flow data to avoid congested sections during peak hours.

[0004] Although existing solutions can meet basic charging route planning needs to a certain extent, they generally have some significant defects. First, due to reliance on static or quasi-real-time data, it is difficult to accurately predict the actual power consumption during driving, especially in the face of complex terrain conditions and extreme weather. Secondly, existing solutions rarely consider the impact of factors such as grid load factor and service response delay on the selection of charging stations, which may lead to long waiting times or inability to charge in time during peak hours. Finally, these solutions generally lack the ability to differentiate between different driving scenarios (such as highways and urban roads), resulting in inaccurate route planning and poor user experience. Summary of the invention

[0005] The embodiments of the present application provide a method and system for planning a charging path for an electric vehicle, so as to solve the problems of insufficient feasibility and low convenience of planning a charging path for an electric vehicle in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for planning a charging path for an electric vehicle, comprising:

[0007] Based on the remaining power of the electric vehicle, the real-time location coordinates and the destination coordinate data, an initial path topology diagram of multimodal traffic data fusion is generated in combination with the dynamic operation data set of the charging station in the target area, wherein the dynamic operation data set of the charging station includes the available number of electric vehicle charging piles, the real-time charging power, the grid load factor and the service response delay parameter;

[0008] The initial path topology is dynamically estimated for power consumption using a road slope correction coefficient, an ambient temperature nonlinear influencing factor, and a traffic flow speed fluctuation parameter. When a charging demand is triggered by a relationship between the remaining power and the estimated consumption of consecutive path segments, a candidate path subgraph containing a charging station sequence is activated.

[0009] Based on the available number of the electric vehicle charging piles and the grid load association parameter of the real-time charging power, combined with the user behavior pattern feature vector, a multidimensional decision function of the candidate path subgraph is generated;

[0010] Based on the multi-dimensional decision function, a dynamic priority mapping is implemented on the candidate path subgraph using a multi-modal scenario classification mechanism. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load valley period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, the charging station topology is generated through multi-dimensional spatiotemporal coupling in combination with the traffic flow evolution parameter and the charging station gravity factor, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established;

[0011] The initial path topology map, the multi-level priority sequence, the charging station topology structure and the nonlinear mapping relationship are subjected to real-time data fusion, and the energy consumption valuation system is reconstructed through the dynamic coupling relationship between the service status mutation index and the road congestion coefficient. When it is detected that the grid load phase offset and the traffic flow density gradient form a composite trigger condition, an adaptive charging path instruction set based on spatiotemporal collaborative optimization is generated.

[0012] Optionally, based on the multidimensional decision function, a multimodal scenario classification mechanism is used to implement dynamic priority mapping on the candidate path subgraph. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load valley period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, the charging station topology is generated through multi-dimensional spatiotemporal coupling in combination with the traffic flow evolution parameter and the charging station gravity factor, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established, including:

[0013] In the highway scenario, a priority sequence of charging stations is generated based on the spatiotemporal matching relationship between the time window data of the low-load period of the power grid and the service response delay parameter, wherein the service response delay parameter is dynamically corrected by the power grid load association parameter of the available number of charging piles and the real-time charging power, and a gradient distribution model of the charging efficiency gain value is established based on the spatial distribution of the highway section nodes in the initial path topology diagram;

[0014] In the urban scenario, the second-order derivative of the traffic flow prediction data is used to generate the charging station topology through the convolution operation of the charging station gravity factor and the traffic flow pattern evolution parameter, wherein the nonlinear mapping relationship between the charging station spacing and the traffic flow density is phase-synchronized and calibrated through the user behavior pattern feature vector;

[0015] The charging station priority sequence is coupled with the charging station topology structure in multi-dimensional space-time. When it is detected that the grid load phase deviation exceeds a preset threshold, a dynamic feedback mechanism of the service response delay parameter and the road congestion coefficient is triggered, and an optimized path set with space-time constraints is generated by reconstructing the node connection weight values ​​in the candidate path subgraph;

[0016] Based on the superposition analysis of the optimized path set and the real-time charging station heat map, a composite trigger condition of the power grid load fluctuation phase difference and the traffic flow density gradient is established. When the composite trigger condition is met, an adaptive charging path instruction set including a charging station service response delay compensation coefficient and a path energy consumption correction factor is output.

[0017] Optionally, the charging station priority sequence is coupled with the charging station topology in a multi-dimensional space-time manner, and when it is detected that the grid load phase offset exceeds a preset threshold, a dynamic feedback mechanism of the service response delay parameter and the road congestion coefficient is triggered, and an optimized path set with space-time constraints is generated by reconstructing the node connection weight values ​​in the candidate path subgraph, including:

[0018] Constructing a coupling characteristic tensor including the spatiotemporal distribution of the charging station priority sequence and the dynamic characteristics of the urban topology, activating a feedback regulation channel through a power grid load phase offset detector, wherein the coupling characteristic tensor includes the spatial distribution parameters of the highway section nodes and the real-time charging power fluctuation characteristics;

[0019] Based on the dual-channel interaction mechanism, the service response delay parameter is dynamically corrected by utilizing the real-time charging power fluctuation characteristics in the coupling feature tensor, and a path node connection strength correction vector is generated in combination with the road congestion coefficient, wherein the service response delay parameter is associated with the time window data of the grid load valley period through the dynamic correction module of the available number of charging piles;

[0020] Applying the path node connection strength correction vector to the adjacency matrix of the candidate path subgraph to generate an updated path topology structure including a power grid load compatibility index;

[0021] Based on the running path optimization algorithm of the updated path topology structure, the real-time matching degree between the distance between the charging stations and the traffic flow evolution parameters is calculated to generate an optimized path set including a traffic flow density fitness level.

[0022] Optionally, based on the dual-channel interaction mechanism, the service response delay parameter is dynamically corrected by utilizing the real-time charging power fluctuation characteristics in the coupling feature tensor, and a path node connection strength correction vector is generated in combination with a road congestion coefficient, including:

[0023] Using the convolution matching result of the power grid load fluctuation cycle pattern and the valley period to perform dynamic priority allocation processing to generate a service response delay correction factor, and inputting the service response delay correction factor into the closed-loop constraint processing module;

[0024] Based on the congestion impact transfer function and the dual-channel attention mechanism, the service response delay correction factor and the road congestion coefficient are subjected to spatiotemporal coupling processing to generate a node connection strength dynamic attenuation factor, and the node connection strength dynamic attenuation factor is transmitted to the nonlinear superposition processing module;

[0025] Performing closed-loop constraint processing on the service response delay correction factor and the node connection strength dynamic attenuation factor through composite monitoring data of power grid phase offset and traffic flow density gradient to generate dynamic feedback verification parameters, and inputting the verification parameters into a boundary limitation processing module;

[0026] In a nonlinear superposition processing module, the service response delay correction factor is superimposed with the node connection strength dynamic attenuation factor to generate a preliminary path node connection strength correction vector, and the preliminary path node connection strength correction vector is transmitted to a boundary limitation processing module;

[0027] The dynamic feedback verification parameters are used to perform boundary limitation processing on the scope of action of the preliminary path node connection strength correction vector to generate a path node connection strength correction vector under the power grid-traffic coupling constraint condition, and the path node connection strength correction vector is synchronously injected into the path topology update module and the traffic flow fitness calculation module.

[0028] Optionally, based on the superposition analysis of the optimized path set and the real-time charging station heat map, a composite trigger condition of the grid load fluctuation phase difference and the traffic flow density gradient is established. When the composite trigger condition is met, an adaptive charging path instruction set including a charging station service response delay compensation coefficient and a path energy consumption correction factor is output, including:

[0029] Using the spatiotemporal distribution characteristics of the real-time charging station heat map, dynamically meshing the nodes in the optimized path set to generate a thermal density correction parameter, and dynamically weighting the time series data of the grid load fluctuation phase difference based on the thermal density correction parameter to generate a spatiotemporal attenuation coefficient;

[0030] Combining the spatial distribution data of the traffic flow density gradient with the spatiotemporal attenuation coefficient to perform multi-source fusion processing, generating a spatiotemporal coupling constraint factor, using the spatiotemporal coupling constraint factor to dynamically calibrate the charging station gravity factor, and generating a compatibility gradient parameter;

[0031] Based on the user behavior pattern feature vector, the compatibility gradient parameter is subjected to phase synchronization processing to generate a dynamic compensation vector, the dynamic compensation vector and the path energy consumption correction factor are subjected to spatiotemporal weight distribution processing to generate a composite verification factor, and the composite verification factor is subjected to dynamic feedback calibration processing through multi-level constraint conditions to generate a power grid-traffic coupling verification parameter;

[0032] When the grid-traffic coupling verification parameter meets a preset spatiotemporal compatibility threshold, the verification parameter is hierarchically mapped based on a charging efficiency gradient distribution model to generate an adaptive charging path instruction set including a dynamic compensation level and a path energy consumption constraint.

[0033] Optionally, the generating of the node connection strength dynamic attenuation factor by performing spatiotemporal coupling processing on the service response delay correction factor and the road congestion coefficient based on the congestion impact transfer function and the dual-channel attention mechanism includes:

[0034] Using the time series characteristics of the service response delay correction factor and the spatial distribution characteristics of the road congestion coefficient to perform dynamic grid division processing, generate a time-space coupling characteristic vector, perform multi-source fusion processing on the power grid load gradient parameter based on the time-space coupling characteristic vector, and generate a time-space attenuation coefficient;

[0035] Combining the spatiotemporal attenuation coefficient with the traffic flow pattern evolution parameter to perform gradient constraint processing to generate a dynamic attenuation correction factor, and using the dynamic attenuation correction factor to perform phase synchronization processing on the charging station gravity factor to generate a compatibility gradient parameter;

[0036] Based on the compatibility gradient parameter, the grid phase offset is subjected to nonlinear mapping processing to generate a dynamic attenuation verification parameter, and the dynamic attenuation verification parameter is subjected to dynamic feedback calibration processing through multi-level constraint conditions to generate a grid-traffic coupling attenuation factor;

[0037] When the grid-traffic coupling attenuation factor meets the preset spatiotemporal compatibility threshold, the attenuation factor is hierarchically mapped based on the charging efficiency gradient distribution model to generate a node connection strength dynamic attenuation factor including a dynamic compensation level and a path energy consumption constraint.

[0038] Optionally, the spatial distribution data of the combined traffic flow density gradient and the spatiotemporal attenuation coefficient are subjected to multi-source fusion processing to generate a spatiotemporal coupling constraint factor, and the charging station gravity factor is dynamically calibrated using the spatiotemporal coupling constraint factor to generate a compatibility gradient parameter, including:

[0039] The spatial distribution data of the traffic flow density gradient is used to perform dynamic weight allocation processing on the spatiotemporal attenuation coefficient to generate a multi-source fusion feature tensor; based on the multi-source fusion feature tensor, the spatiotemporal distribution characteristics of the charging station gravity factor are dynamically grid matched to generate a spatiotemporal coupling constraint factor; the time series fluctuation characteristics of the charging station gravity factor are phase aligned in combination with the spatiotemporal coupling constraint factor to generate a compatibility gradient parameter, and the compatibility gradient parameter is used to perform dynamic feedback calibration processing on the spatial distribution characteristics of the path energy consumption correction factor to generate a composite verification factor.

[0040] In a second aspect, an embodiment of the present application provides an electric vehicle charging path planning system, comprising:

[0041] A generation module is used to generate an initial path topology map of multimodal traffic data fusion based on the remaining power of the electric vehicle, the real-time location coordinates and the destination coordinate data, combined with the dynamic operation data set of the charging station in the target area, wherein the dynamic operation data set of the charging station includes the available number of electric vehicle charging piles, the real-time charging power, the grid load factor and the service response delay parameter;

[0042] an estimation module, for dynamically estimating the power consumption of the initial path topology using a road slope correction coefficient, an ambient temperature nonlinear influencing factor, and a traffic flow speed fluctuation parameter, and activating a candidate path subgraph containing a charging station sequence when a charging demand is triggered by a relationship between the remaining power and the estimated consumption of consecutive path segments;

[0043] A processing module, configured to generate a multidimensional decision function of the candidate path subgraph based on the available number of the electric vehicle charging piles and the grid load association parameter of the real-time charging power in combination with a user behavior pattern feature vector;

[0044] A prediction module is used to implement dynamic priority mapping on the candidate path subgraph based on the multi-dimensional decision function and using a multi-modal scenario classification mechanism. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load valley period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, a charging station topology structure is generated through multi-dimensional spatiotemporal coupling in combination with traffic flow evolution parameters and charging station gravity factors, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established;

[0045] The fusion module is used to perform real-time data fusion of the initial path topology map, the multi-level priority sequence, the charging station topology structure and the nonlinear mapping relationship, reconstruct the energy consumption valuation system through the dynamic coupling relationship between the service status mutation index and the road congestion coefficient, and generate an adaptive charging path instruction set based on spatiotemporal collaborative optimization when it is detected that the grid load phase offset and the traffic flow density gradient form a composite trigger condition.

[0046] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an electric vehicle charging path planning method as described in the first aspect above.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a method for planning a charging path for an electric vehicle as described in the first aspect.

[0048] In an embodiment of the present application, an initial path topology map of multimodal traffic data fusion is generated based on the remaining power of the electric vehicle, the real-time location coordinates and the destination coordinate data, combined with the dynamic operation data set of the charging stations in the target area, wherein the dynamic operation data set of the charging station includes the available number of electric vehicle charging piles, the real-time charging power, the power grid load factor and the service response delay parameter; the road slope correction coefficient, the nonlinear influencing factor of the ambient temperature and the traffic flow speed fluctuation parameter are used to dynamically estimate the power consumption of the initial path topology map, and when the relationship between the remaining power and the consumption estimate of the continuous path segment triggers the charging demand, the candidate path subgraph containing the charging station sequence is activated; based on the available number of the electric vehicle charging piles and the power grid load association parameter of the real-time charging power, a multidimensional decision function of the candidate path subgraph is generated in combination with the user behavior pattern feature vector; based on the multidimensional decision function, the candidate path subgraph is classified into a plurality of groups using a multimodal scenario classification mechanism. Implement dynamic priority mapping. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load low period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, the charging station topology structure is generated through multi-dimensional spatiotemporal coupling in combination with the traffic flow evolution parameters and the charging station gravity factor, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established; the initial path topology map, the multi-level priority sequence, the charging station topology structure and the nonlinear mapping relationship are subjected to real-time data fusion, and the energy consumption valuation system is reconstructed through the dynamic coupling relationship between the service status mutation index and the road congestion coefficient. When it is detected that the grid load phase offset and the traffic flow density gradient form a composite trigger condition, an adaptive charging path instruction set based on spatiotemporal collaborative optimization is generated.

[0049] The technical solution of this application has the following beneficial effects:

[0050] This application achieves detailed planning of charging routes by comprehensively analyzing multiple factors such as the operating status of electric vehicles, road conditions, weather, and grid load. It not only improves driving safety and efficiency, but also reduces the risk of stagnation on the way due to insufficient power. It is particularly suitable for electric vehicle navigation systems in complex transportation networks, enhancing user experience and promoting the popularization of electric vehicles.

[0051] Furthermore, a dynamic priority mapping is implemented on the candidate path subgraphs by using a multimodal scenario classification mechanism in both highway and urban scenarios. Specifically, in the highway scenario, the priority sequence of charging stations is generated based on the spatiotemporal matching relationship between the time window of the grid load valley period and the service response delay parameter, and the grid load correlation parameter of the available number of charging piles and the real-time charging power is dynamically corrected; while in the urban scenario, the charging station topology is generated by combining the second-order derivative of the traffic flow prediction data, the charging station gravity factor and the traffic flow evolution parameter. In addition, the nonlinear mapping relationship between the distance between charging stations and the traffic flow density is calibrated by the user behavior pattern feature vector. When the grid load phase offset exceeds the threshold, the dynamic feedback mechanism of the service response delay parameter and the road congestion coefficient is activated to optimize the path set, and finally output an adaptive charging path instruction set containing the charging station service response delay compensation coefficient and the path energy consumption correction factor.

[0052] The above method can significantly improve the charging convenience and path planning efficiency of electric vehicles during long-distance travel. By accurately calculating and dynamically adjusting the priority of charging stations and path selection in different scenarios, not only the time wasted waiting for charging is reduced, but also the load pressure of the power grid during peak hours is effectively avoided. At the same time, considering the evolution of traffic flow and user behavior patterns, the path planning is more in line with actual needs and improves the user experience. Especially in the face of complex road conditions and environmental changes, this method can optimize the driving route in real time to ensure the continuity and efficiency of the journey, thereby greatly enhancing the safety and comfort of driving.

[0053] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A flow chart of a method for planning a charging path for an electric vehicle provided by the present application is shown;

[0056] Figure 2 A schematic diagram of the structure of an electric vehicle charging path planning system provided by the present application is shown;

[0057] Figure 3 A schematic diagram of the structure of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0058] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution 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.

[0059] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0060] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0061] Figure 1 A flowchart of a method for planning a charging path for an electric vehicle is provided in an embodiment of the present application. Figure 1 As shown, the method includes:

[0062] 101. Generate an initial path topology map of multimodal traffic data fusion based on the remaining power, real-time location coordinates and destination coordinate data of the electric vehicle and the dynamic operation data set of the charging station in the target area, wherein the dynamic operation data set of the charging station includes the available number of electric vehicle charging piles, real-time charging power, power grid load factor and service response delay parameters;

[0063] Among them, the remaining power of the electric vehicle refers to the available power stored in the current electric vehicle battery, which is used to assess whether the vehicle can successfully reach the destination or the next charging station.

[0064] Real-time location coordinates: Indicates the current geographic location of the vehicle, obtained through GPS or other positioning systems, and used to determine the vehicle's precise location on the map.

[0065] Destination coordinate data: refers to the geographical coordinates of the destination set by the user, which is used to plan the best path from the current location to the target location.

[0066] Charging station dynamic operation data set: including information such as the number of available charging piles, real-time charging power, grid load factor, and service response delay parameters, which is used to optimize the selection of charging paths.

[0067] Multimodal traffic data: covers data on different types of transportation (such as cars, buses, bicycles, etc.), as well as influencing factors such as road conditions and weather, aiming to provide a comprehensive view of traffic conditions.

[0068] Initial route topology: A map model generated based on the above data, showing possible driving routes and the locations of charging stations along the way.

[0069] In actual operation, the remaining power, current location and destination coordinates of electric vehicles are first collected, and then combined with the dynamic operation data of charging stations in the area to generate an initial path topology map containing all feasible paths and their related information.

[0070] For example, in a smart city traffic management system, when an electric car is about to depart from point A to point B, the system first obtains the remaining power, real-time location, and destination coordinates of the car. Then, the system integrates the dynamic operation data of charging stations along the route, including the availability of charging piles, charging speed, and grid load status. Based on this information, the system creates a detailed initial path topology map, which provides a basis for subsequent path optimization.

[0071] 102. Dynamically estimate the power consumption of the initial path topology using the road slope correction coefficient, the nonlinear influence factor of the ambient temperature, and the traffic flow speed fluctuation parameter. When the estimated relationship between the remaining power and the continuous path segment consumption triggers a charging demand, activate the candidate path subgraph containing the charging station sequence.

[0072] Among them, road slope correction coefficient: a coefficient that adjusts vehicle energy consumption according to the road slope, used to more accurately estimate power consumption.

[0073] Ambient temperature nonlinear impact factor: Considers the impact of temperature changes on battery efficiency and is used to adjust energy consumption estimates.

[0074] Traffic flow speed fluctuation parameter: describes the changing trend of traffic flow speed, helping to more accurately predict power demand.

[0075] Dynamic energy consumption estimation: Adjusts the estimated energy consumption in real time based on different conditions encountered during vehicle operation, such as grade, temperature and traffic speed.

[0076] Charging demand trigger: When the remaining power of the electric vehicle is insufficient to support it to complete the continuous route segment, the system automatically identifies the need for charging.

[0077] In actual operation, the road slope correction coefficient, the nonlinear influencing factor of ambient temperature and the traffic flow speed fluctuation parameter are used to dynamically estimate the power consumption of the initial path topology. Once the estimated relationship between the remaining power and the continuous path segment consumption triggers the charging demand, the candidate path subgraph containing the charging station sequence is activated.

[0078] Continuing with the above embodiment, as the journey progresses, the system will consider the changes in the road slope, current ambient temperature and traffic flow at different sections to more accurately predict energy consumption. If the calculation result shows that the current remaining power is not enough to reach the next charging station, the system will recommend a new route plan that includes an intermediate charging point.

[0079] 103. Based on the available number of the electric vehicle charging piles and the grid load association parameter of the real-time charging power, combined with the user behavior pattern feature vector, a multidimensional decision function of the candidate path subgraph is generated;

[0080] Among them, the grid load associated parameter: the relationship between the available number of charging piles and the real-time charging power is used to evaluate the impact on the grid load.

[0081] Multidimensional decision function: A mathematical model generated by combining user behavior pattern feature vectors, grid load and other factors to determine the optimal charging path.

[0082] User behavior pattern feature vector: A feature set built based on the user's historical behavior data to understand the user's preferences and habits.

[0083] In actual operation, a multidimensional decision function of the candidate path subgraph is generated based on the grid load association parameters of the available number of charging piles and the real-time charging power, combined with the user behavior pattern feature vector.

[0084] Continuing with the above embodiment, considering that users tend to choose fast charging stations and avoid peak hours, the system uses these preference information to adjust the decision weights. For example, when formulating the final route, the system prioritizes those stations that provide efficient charging services during low-load periods while minimizing waiting time.

[0085] 104. Based on the multi-dimensional decision function, a multi-modal scenario classification mechanism is used to implement dynamic priority mapping on the candidate path subgraph. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load valley period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, the charging station topology is generated through multi-dimensional spatiotemporal coupling in combination with the traffic flow evolution parameter and the charging station gravity factor, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established;

[0086] Among them, the multimodal scenario classification mechanism: different strategies are used to prioritize paths according to different driving scenarios (such as highways and urban areas).

[0087] Charging station attraction factor: A measure of the attractiveness of a charging station in a specific area, based on factors such as its service quality and price.

[0088] Service response delay parameter: measures the time interval between requesting a service and actually providing the service, and is used to evaluate service quality.

[0089] Grid load off-peak period: The period of time when the grid load is relatively low, and the electricity price is usually also low.

[0090] In actual operation, a multimodal scenario classification mechanism is used to implement dynamic priority mapping of candidate path subgraphs, especially to generate the optimal path based on the different characteristics of highways and urban areas.

[0091] Continuing with the above example, as the journey approaches an urban area, the system notices increased traffic and rising demand for charging. It adopts a route optimization strategy that is more suitable for urban areas, such as choosing a charging station close to a transportation hub and using traffic flow prediction data to avoid congestion and ensure a smooth journey.

[0092] 105. The initial path topology diagram, the multi-level priority sequence, the charging station topology structure and the nonlinear mapping relationship are subjected to real-time data fusion, and the energy consumption valuation system is reconstructed through the dynamic coupling relationship between the service status mutation index and the road congestion coefficient. When it is detected that the grid load phase offset and the traffic flow density gradient form a composite trigger condition, an adaptive charging path instruction set based on spatiotemporal collaborative optimization is generated.

[0093] Among them, the service status mutation index reflects the degree of sudden change in service status, such as the sudden unavailability of a charging station.

[0094] Road congestion coefficient: an indicator to measure the degree of traffic congestion on a certain road section.

[0095] Spatiotemporal collaborative optimization: Comprehensively consider factors in both time and space dimensions to achieve optimal resource allocation.

[0096] Adaptive charging path instruction set: A series of optimal charging path suggestions dynamically generated based on real-time data analysis results.

[0097] In actual operation, the information of all previous steps is integrated, and the energy consumption valuation system is reconstructed through the dynamic coupling relationship between the service status mutation index and the road congestion coefficient to generate an adaptive charging path instruction set.

[0098] Continuing with the above example, the system finally integrates all data information, updates energy consumption estimates in real time, and adjusts route recommendations based on the latest grid load and service response delays. When approaching the destination, the system prompts the driver to choose the best route that saves time and ensures sufficient power, completing the journey smoothly while minimizing the risk of stalling on the way due to insufficient power.

[0099] Through the implementation of steps 101 to 105, by intelligently integrating multiple factors such as the operating status of the electric vehicle, road conditions, weather conditions, and grid load, detailed planning of the charging path is achieved, which not only improves driving safety and efficiency, but also greatly reduces the risk of stagnation on the way due to insufficient power, greatly enhances the user experience, and promotes the widespread use of electric vehicles.

[0100] In order to solve the problem of charging station selection in different driving scenarios and further improve the accuracy and adaptability of path planning, in some embodiments, the multi-dimensional decision function described in step 104 is used to implement dynamic priority mapping on the candidate path subgraph using a multimodal scenario classification mechanism. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load valley period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, the charging station topology is generated through multi-dimensional spatiotemporal coupling in combination with the traffic flow evolution parameter and the charging station gravity factor, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established, including:

[0101] In the highway scenario, a charging station priority sequence is generated based on the spatiotemporal matching relationship between the time window data of the grid load off-peak period and the service response delay parameter, wherein the service response delay parameter is dynamically corrected by the grid load association parameter of the available number of charging piles and the real-time charging power, and a gradient distribution model of the charging efficiency gain value is established based on the spatial distribution of the highway section nodes in the initial path topology diagram; in the urban scenario, the second-order derivative of the traffic flow prediction data is used to generate the charging station topology structure through the convolution operation of the charging station gravity factor and the traffic flow evolution parameter, wherein the nonlinear mapping relationship between the distance between charging stations and the traffic flow density is obtained through the user behavior The mode feature vector is phase synchronized and calibrated; the charging station priority sequence is coupled with the charging station topology in multi-dimensional space-time; when it is detected that the grid load phase offset exceeds a preset threshold, the dynamic feedback mechanism of the service response delay parameter and the road congestion coefficient is triggered, and the node connection weight values ​​in the candidate path subgraph are reconstructed to generate an optimized path set with space-time constraints; based on the superposition analysis of the optimized path set and the real-time charging station heat map, a composite trigger condition of the grid load fluctuation phase difference and the traffic flow density gradient is established; when the composite trigger condition is met, an adaptive charging path instruction set including the charging station service response delay compensation coefficient and the path energy consumption correction factor is output.

[0102] In this embodiment, multi-dimensional space-time coupling: data in the time and space dimensions (such as traffic flow changes, power grid load fluctuations) are combined for analysis to achieve more efficient resource allocation.

[0103] Gradient distribution model of charging efficiency gain value: Based on the spatial distribution of highway sections, the charging efficiency of charging stations at different locations is evaluated to form a spatial distribution map reflecting the charging efficiency.

[0104] Convolution operation: A mathematical operation method used to process the relationship between two variables. It is used here to combine the charging station gravity factor and the traffic flow evolution parameters to generate the charging station topology structure.

[0105] Phase synchronization calibration: The nonlinear mapping relationship between the distance between charging stations and traffic flow density is adjusted according to the characteristic vector of user behavior pattern to ensure that it meets the actual usage requirements.

[0106] Service response delay compensation coefficient: A correction coefficient set to compensate for the time loss caused by service response delay.

[0107] Path energy consumption correction factor: A coefficient that adjusts the energy consumption on the path by taking into account various influencing factors (such as slope, temperature, etc.).

[0108] In the embodiment of the present application, firstly, according to the characteristics of different driving scenarios (highways and urban areas), corresponding strategies are adopted to dynamically prioritize the candidate path subgraphs.

[0109] On highways, a priority sequence is generated based on the grid load off-peak period and service response delay parameters, and a gradient distribution model for charging efficiency gain values ​​is established;

[0110] In urban areas, the charging station topology is generated by combining the second-order derivative of traffic flow prediction data with the charging station gravity factor. Finally, after integrating all the information, when it is detected that specific conditions are met, an adaptive charging path instruction set containing compensation coefficients and correction factors is output.

[0111] Here is a specific example:

[0112] In a smart city traffic management system, an electric car plans to travel from City A to City B, passing through a section of highway and multiple urban areas. The system first recognizes that the vehicle is about to enter the highway area, at which point it uses the time window data of the grid load valley period and the service response delay parameters to generate a list of charging stations with the highest priority. These charging stations are arranged near the highway nodes that the vehicle is expected to pass through to minimize charging waiting time and improve overall driving efficiency.

[0113] As the vehicle approaches the urban area, the system switches to a route optimization strategy suitable for the urban environment. It uses the second-order derivative of traffic flow forecast data to evaluate traffic conditions in the future and combines charging station attraction factors (such as service quality, price, etc.) to generate a detailed charging station topology. This helps drivers avoid congested sections during peak hours and find the best charging point.

[0114] When the grid load fluctuates significantly or the traffic flow density changes abnormally, the system will automatically trigger the dynamic feedback mechanism of the service response delay parameter and the road congestion coefficient, and recalculate and recommend a new set of optimized paths. This not only improves the accuracy of path planning, but also greatly enhances the user's travel experience. In the end, the system outputs a complete set of adaptive charging path instructions, including compensation for possible service response delays and adjusting the energy consumption estimate on the path according to the latest road conditions. This refined path planning solution effectively solves the charging problem during long-distance travel and improves the convenience and reliability of electric vehicle use.

[0115] In order to solve the impact of grid load fluctuations and service response delays on charging path planning and further improve the spatiotemporal adaptability and user satisfaction of path planning, in some embodiments, the charging station priority sequence is coupled with the charging station topology in a multi-dimensional spatiotemporal manner. When it is detected that the grid load phase offset exceeds a preset threshold, a dynamic feedback mechanism of the service response delay parameter and the road congestion coefficient is triggered, and an optimized path set with spatiotemporal constraints is generated by reconstructing the node connection weight values ​​in the candidate path subgraph, including:

[0116] A coupling feature tensor including the spatiotemporal distribution of the priority sequence of charging stations and the dynamic characteristics of the urban topology is constructed, and a feedback adjustment channel is activated through a power grid load phase offset detector, wherein the coupling feature tensor includes the spatial distribution parameters of the nodes on the highway section and the real-time charging power fluctuation characteristics; based on a dual-channel interaction mechanism, the real-time charging power fluctuation characteristics in the coupling feature tensor are used to dynamically correct the service response delay parameters, and a path node connection strength correction vector is generated in combination with the road congestion coefficient, wherein the service response delay parameters are associated with the time window data of the power grid load valley period through a dynamic correction module of the available number of charging piles; the path node connection strength correction vector is applied to the adjacency matrix of the candidate path subgraph to generate an updated path topology structure including a power grid load compatibility index; based on the running path optimization algorithm of the updated path topology structure, the real-time matching degree between the spacing of the charging stations and the traffic flow evolution parameters is calculated to generate an optimized path set including a traffic flow density fitness level.

[0117] In this embodiment, the coupled feature tensor: a multidimensional data structure including the spatiotemporal distribution of the priority sequence of charging stations and the dynamic characteristics of the urban topology, is used to comprehensively analyze the impact of different factors on path planning.

[0118] Grid load phase shift detector: used to monitor changes in grid load and trigger corresponding feedback adjustment mechanism when it is detected that the preset threshold is exceeded.

[0119] Dual-channel interaction mechanism: A processing method that optimizes system performance through two independent but related channels (such as real-time charging power fluctuation characteristics and service response delay parameters).

[0120] Path node connection strength correction vector: a set of weight values ​​calculated based on the current traffic conditions and service response delay parameters, used to adjust the connection strength between nodes in the candidate path subgraph.

[0121] Grid load compatibility index: A criterion for measuring whether the path selection takes into account the grid load situation, aiming to reduce the pressure on electricity consumption during peak hours.

[0122] Traffic density adaptation level: A hierarchical model that adjusts the distance between charging stations according to changes in traffic flow, ensuring that path planning is more in line with actual road conditions.

[0123] In the embodiment of the present application, a coupled characteristic tensor including the spatiotemporal distribution of the priority sequence of charging stations and the dynamic characteristics of the urban topology is first constructed. When the grid load phase offset exceeds the preset threshold, the feedback adjustment channel is activated, and the service response delay parameter is dynamically corrected using the dual-channel interaction mechanism. Combined with the road congestion coefficient, a path node connection strength correction vector is generated, and then the adjacency matrix of the candidate path subgraph is updated to generate a new path topology structure including the grid load compatibility index.

[0124] Finally, the path optimization algorithm is run based on the updated path topology structure to calculate the matching degree between the charging station spacing and the traffic flow evolution parameters, and generate an optimized path set.

[0125] Here is a specific example:

[0126] According to the above embodiment, the system first constructs a coupling feature tensor, which includes the priority sequence of charging stations along the way and their spatiotemporal distribution, as well as the dynamic characteristics of urban traffic. As the grid load fluctuates significantly during vehicle driving, the grid load phase offset detector in the system triggers the feedback regulation mechanism.

[0127] At this time, the system uses a dual-channel interaction mechanism to analyze the real-time charging power fluctuation characteristics on the one hand, and to make dynamic corrections based on the available number of charging piles and service response delay parameters on the other hand. This information is integrated into a path node connection strength correction vector, which is used to adjust the connection weights between nodes in the candidate path subgraph. For example, during peak hours, the system may recommend avoiding certain high-load areas and instead choosing time windows or sections with lower grid load for charging.

[0128] Next, the system applies the path node connection strength correction vector to the adjacency matrix of the candidate path subgraph to generate a new path topology that includes the grid load compatibility index. Based on this updated path topology, the system runs a path optimization algorithm to calculate the match between each possible charging station location and the current traffic flow evolution parameters. Finally, the system outputs a set of optimized paths that not only take into account changes in grid load and traffic flow, but also improve the overall efficiency of the path and user experience.

[0129] In order to solve the impact of grid load fluctuations and service response delays on path planning and further improve the dynamic adaptability and user satisfaction of path planning, in some embodiments, the dual-channel interaction mechanism is based on the real-time charging power fluctuation characteristics in the coupling feature tensor to dynamically correct the service response delay parameter, and the path node connection strength correction vector is generated in combination with the road congestion coefficient, including:

[0130] The convolution matching result of the power grid load fluctuation cycle pattern and the valley period is used to perform dynamic priority allocation processing to generate a service response delay correction factor, and the service response delay correction factor is input into the closed-loop constraint processing module; based on the congestion impact transfer function and the dual-channel attention mechanism, the service response delay correction factor and the road congestion coefficient are subjected to spatiotemporal coupling processing to generate a node connection strength dynamic attenuation factor, and the node connection strength dynamic attenuation factor is transmitted to the nonlinear superposition processing module; the composite monitoring data of the power grid phase offset and the traffic flow density gradient is used to perform closed-loop constraint on the action intensity of the service response delay correction factor and the node connection strength dynamic attenuation factor. The beam processing generates dynamic feedback verification parameters, and the verification parameters are input into the boundary limitation processing module; in the nonlinear superposition processing module, the service response delay correction factor and the node connection strength dynamic attenuation factor are superimposed to generate a preliminary path node connection strength correction vector, and the preliminary path node connection strength correction vector is transmitted to the boundary limitation processing module; the dynamic feedback verification parameters are used to perform boundary limitation processing on the scope of action of the preliminary path node connection strength correction vector to generate a path node connection strength correction vector under the power grid-traffic coupling constraint condition, and the path node connection strength correction vector is synchronously injected into the path topology update module and the traffic flow fitness calculation module.

[0131] In this embodiment, the convolution matching result: the grid load fluctuation periodic pattern is combined with the data of the valley period through a convolution operation to identify the optimal service response delay correction factor.

[0132] Closed-loop constraint processing module: A module used to ensure the stability of system output and adjust the service response delay correction factor through a feedback mechanism.

[0133] Congestion impact transfer function: A mathematical model that describes how traffic congestion affects path selection and is used to calculate the dynamic attenuation factor of node connection strength.

[0134] Dual-channel attention mechanism: A processing method that allows the system to simultaneously pay attention to information in two dimensions: real-time charging power fluctuation and service response latency.

[0135] Nonlinear superposition processing module: used to process the complex relationship between different factors (such as service response delay correction factor and node connection strength dynamic attenuation factor) and generate a preliminary path node connection strength correction vector.

[0136] Boundary limitation processing module: ensures that the scope of action of the path node connection strength correction vector is within a reasonable range to avoid excessive or insufficient adjustment.

[0137] In the embodiment of the present application, firstly, a dynamic priority allocation process is performed using the convolution matching result of the grid load fluctuation cycle pattern and the valley period to generate a service response delay correction factor.

[0138] Then, the service response delay correction factor and the road congestion coefficient are spatiotemporally coupled through the congestion impact transfer function and the dual-channel attention mechanism to generate a dynamic attenuation factor of the node connection strength.

[0139] Next, the composite monitoring data of power grid phase offset and traffic flow density gradient are used to perform closed-loop constraint processing and generate dynamic feedback verification parameters.

[0140] Finally, in the nonlinear superposition processing module, the service response delay correction factor and the node connection strength dynamic attenuation factor are superimposed to generate a preliminary path node connection strength correction vector, which is then optimized through the boundary limitation processing module to generate the final path node connection strength correction vector.

[0141] Here is a specific example:

[0142] According to the above embodiment, the system first analyzes the fluctuation pattern of the grid load along the route and its valley period, generates the service response delay correction factor through convolution matching, and inputs it into the closed-loop constraint processing module. For example, when the grid load is low at night, the system will recommend the driver to choose this time period for charging to reduce waiting time and reduce electricity costs.

[0143] As the vehicle approaches the city, the system begins to monitor traffic congestion and calculates the dynamic attenuation factor of node connection strength through the congestion impact transfer function and the dual-channel attention mechanism. This enables the system to adjust the node connection weights on the path according to the current traffic conditions and recommend routes that avoid peak congestion sections.

[0144] When the grid load changes significantly or the traffic density is abnormal, the system uses the composite monitoring data of the grid phase offset and the traffic density gradient to perform closed-loop constraint processing and generate dynamic feedback verification parameters. These parameters are transmitted to the boundary limitation processing module to ensure that the scope of action of the path node connection strength correction vector is reasonable, neither over-adjusting nor ignoring important information.

[0145] Finally, the system superimposes all relevant factors in the nonlinear superposition processing module, generates a path node connection strength correction vector under the grid-traffic coupling constraint, and simultaneously injects it into the path topology update module and the traffic flow fitness calculation module. This series of operations not only improves the accuracy and adaptability of path planning, but also significantly improves the user's travel experience. In this way, the system successfully solves the challenges brought by grid load fluctuations and service response delays, and realizes more intelligent and efficient path planning.

[0146] In order to solve the impact of grid load fluctuations and traffic flow density changes on charging path planning and further improve the dynamic adaptability and user satisfaction of path planning, in some embodiments, the composite triggering condition of the grid load fluctuation phase difference and the traffic flow density gradient is established based on the superposition analysis of the optimized path set and the real-time charging station heat map. When the composite triggering condition is met, an adaptive charging path instruction set including a charging station service response delay compensation coefficient and a path energy consumption correction factor is output, including:

[0147] The nodes in the optimized path set are dynamically meshed using the spatiotemporal distribution characteristics of the real-time charging station heat map to generate thermal density correction parameters. Based on the thermal density correction parameters, the time series data of the grid load fluctuation phase difference are dynamically weighted to generate a spatiotemporal attenuation coefficient. The spatial distribution data of the traffic flow density gradient and the spatiotemporal attenuation coefficient are combined for multi-source fusion processing to generate a spatiotemporal coupling constraint factor. The charging station gravity factor is dynamically calibrated using the spatiotemporal coupling constraint factor to generate a compatibility gradient parameter. The compatibility gradient parameter is phase-synchronized based on the user behavior pattern feature vector to generate a dynamic compensation vector. The dynamic compensation vector and the path energy consumption correction factor are processed through spatiotemporal weight allocation to generate a composite verification factor. The composite verification factor is dynamically feedback-calibrated through multi-level constraint conditions to generate a grid-traffic coupling verification parameter. When the grid-traffic coupling verification parameter meets the preset spatiotemporal compatibility threshold, the verification parameter is hierarchically mapped based on the charging efficiency gradient distribution model to generate an adaptive charging path instruction set containing a dynamic compensation level and a path energy consumption constraint.

[0148] In this embodiment, real-time charging station heat map: a map showing the current usage of charging stations, showing the busyness of each station through color or heat.

[0149] Thermal density correction parameter: a parameter calculated based on the spatiotemporal distribution characteristics of the charging station heat map, used to adjust the weight of the path node.

[0150] Space-time attenuation coefficient: A coefficient generated based on the time series data of the phase difference of power grid load fluctuations and the thermal density correction parameter, which is used to evaluate the importance at different time points.

[0151] Space-time coupling constraint factor: The factor obtained by fusing the spatial distribution data of traffic flow density gradient with the space-time attenuation coefficient is used to calibrate the gravity factor of the charging station.

[0152] Compatibility gradient parameter: The gravity factor of the charging station after dynamic calibration, taking into account changes in grid load and traffic flow.

[0153] Dynamic compensation vector: A vector generated by phase synchronization of compatibility gradient parameters based on the user behavior pattern feature vector, used for path adjustment.

[0154] Composite verification factor: A factor generated by the spatiotemporal weight distribution process, combined with a dynamic compensation vector and a path energy consumption correction factor, to ensure the effectiveness of path optimization.

[0155] Grid-transportation coupling verification parameters: Parameters generated after dynamic feedback calibration of composite verification factors under multi-level constraints to ensure that the path meets the preset spatiotemporal compatibility threshold.

[0156] Charging efficiency gradient distribution model: A model that evaluates the differences in charging efficiency of charging stations at different locations and is used to generate the final path instruction set.

[0157] In the embodiment of the present application, the spatiotemporal distribution characteristics of the real-time charging station heat map are first used to dynamically grid the nodes in the optimized path set to generate thermal density correction parameters.

[0158] Then, based on these parameters, dynamic weight allocation is performed on the time series data of the grid load fluctuation phase difference to generate the spatiotemporal attenuation coefficient.

[0159] Then, the spatial distribution data of traffic flow density gradient and the spatiotemporal attenuation coefficient are combined for multi-source fusion processing to generate spatiotemporal coupling constraint factors, which are used to dynamically calibrate the gravity factor of the charging station to generate compatibility gradient parameters. Based on the user behavior pattern feature vector, the compatibility gradient parameters are phase synchronized to generate a dynamic compensation vector, which is then combined with the path energy consumption correction factor through spatiotemporal weight allocation to generate a composite verification factor.

[0160] Finally, the grid-traffic coupling verification parameters are generated by dynamically feedback calibrating the composite verification factors. When the preset spatiotemporal compatibility threshold is met, an adaptive charging path instruction set including dynamic compensation levels and path energy consumption constraints is generated based on the charging efficiency gradient distribution model.

[0161] Here is a specific example:

[0162] According to the above embodiment, the system first uses the real-time charging station heat map to analyze the busyness of the charging stations along the way, and dynamically meshes the nodes in the optimized path set according to the heat density correction parameter. For example, during peak hours, some charging stations may be very crowded, and the system will suggest that the driver choose a relatively idle charging station to reduce waiting time.

[0163] Next, the system combines the time series data of the phase difference of the grid load fluctuation to generate the spatiotemporal attenuation coefficient to help identify the best time to charge. At the same time, the system collects the spatial distribution data of the traffic flow density gradient and generates the spatiotemporal coupling constraint factor through multi-source fusion processing, which is used to dynamically calibrate the gravity factor of the charging station, thereby generating the compatibility gradient parameter.

[0164] Based on the user's travel habits (such as preference for fast charging or avoiding peak hours), the system performs phase synchronization processing on the compatibility gradient parameters, generates a dynamic compensation vector, and combines it with the path energy consumption correction factor to generate a composite verification factor. In order to ensure the effectiveness of path optimization, the system dynamically feedbacks and calibrates the composite verification factor through multi-level constraints to generate grid-traffic coupling verification parameters.

[0165] When all conditions meet the preset time-space compatibility threshold, the system generates the final adaptive charging path instruction set based on the charging efficiency gradient distribution model. This instruction set not only takes into account the changes in grid load and traffic flow, but also maximizes the overall efficiency of the path and user experience. This refined path planning method effectively solves the challenges caused by grid load fluctuations and service response delays, and significantly improves the feasibility and convenience of long-distance travel for electric vehicles.

[0166] In order to solve the impact of grid load fluctuations and road congestion on path planning and further improve the spatiotemporal adaptability and user satisfaction of path planning, in some embodiments, the congestion impact transfer function and the dual-channel attention mechanism are used to perform spatiotemporal coupling processing on the service response delay correction factor and the road congestion coefficient to generate a node connection strength dynamic attenuation factor, including:

[0167] The time series characteristics of the service response delay correction factor and the spatial distribution characteristics of the road congestion coefficient are used to perform dynamic grid division processing to generate a spatiotemporal coupling feature vector, and the grid load gradient parameter is subjected to multi-source fusion processing based on the spatiotemporal coupling feature vector to generate a spatiotemporal attenuation coefficient; the spatiotemporal attenuation coefficient is combined with the traffic flow evolution parameter for gradient constraint processing to generate a dynamic attenuation correction factor, and the charging station gravity factor is subjected to phase synchronization processing using the dynamic attenuation correction factor to generate a compatibility gradient parameter; the grid phase offset is subjected to nonlinear mapping processing based on the compatibility gradient parameter to generate a dynamic attenuation verification parameter, and the dynamic attenuation verification parameter is subjected to dynamic feedback calibration processing through multi-level constraint conditions to generate a grid-traffic coupling attenuation factor; when the grid-traffic coupling attenuation factor meets the preset spatiotemporal compatibility threshold, the attenuation factor is subjected to hierarchical mapping processing based on the charging efficiency gradient distribution model to generate a node connection strength dynamic attenuation factor containing dynamic compensation levels and path energy consumption constraints.

[0168] In this embodiment, Congestion Impact Transfer Function: A mathematical model used to describe how traffic congestion affects path selection and service response delay.

[0169] Spatiotemporal coupling feature vector: A data structure generated by combining the time series characteristics and the temporal distribution of the service response delay correction factor with the spatial distribution of the road congestion coefficient.

[0170] Grid load gradient parameters: a data set that reflects the changing trend of grid load in different time and space.

[0171] Dynamic attenuation correction factor: A correction factor adjusted according to the spatiotemporal attenuation coefficient and traffic flow evolution parameters, used to optimize the charging station gravity factor.

[0172] Nonlinear mapping processing: The process of converting one variable into another variable, which is used here to convert the compatibility gradient parameters into dynamic attenuation verification parameters.

[0173] Grid-traffic coupling attenuation factor: The final factor generated reflects the combined impact of grid load and traffic flow status and is used for route optimization.

[0174] In the embodiment of the present application, firstly, the time series characteristics of the service response delay correction factor and the spatial distribution characteristics of the road congestion coefficient are used to perform dynamic grid division processing to generate a time-space coupling feature vector.

[0175] Next, based on the characteristic vector, the grid load gradient parameters are processed by multi-source fusion to generate the spatiotemporal attenuation coefficient. Then, the spatiotemporal attenuation coefficient is combined with the traffic flow evolution parameters to perform gradient constraint processing to generate the dynamic attenuation correction factor.

[0176] Next, the dynamic attenuation correction factor is used to perform phase synchronization processing on the gravity factor of the charging station to generate compatibility gradient parameters. Based on the compatibility gradient parameters, the grid phase offset is nonlinearly mapped to generate dynamic attenuation verification parameters.

[0177] Finally, the dynamic attenuation verification parameters are dynamically calibrated through multi-level constraints to generate the grid-traffic coupling attenuation factor. When the preset spatiotemporal compatibility threshold is met, the attenuation factor is hierarchically mapped based on the charging efficiency gradient distribution model to generate a node connection strength dynamic attenuation factor that includes dynamic compensation levels and path energy consumption constraints.

[0178] Here is a specific example:

[0179] The system first analyzes the time series characteristics of road congestion and service response delay correction factors along the way to generate a spatiotemporal coupling feature vector. For example, during peak hours, some sections of the road may be very congested, and the system will advise drivers to avoid these sections and choose a less crowded route to reduce waiting time.

[0180] Next, the system generates a spatiotemporal attenuation coefficient based on the grid load gradient parameters to help identify the best time and location for charging. The system also collects traffic flow evolution parameters and generates a dynamic attenuation correction factor through gradient constraint processing. This enables the system to adjust the node connection weights on the path according to the current traffic conditions and recommend routes that avoid peak congestion sections.

[0181] Subsequently, the system uses the dynamic attenuation correction factor to perform phase synchronization processing on the charging station gravity factor to generate compatibility gradient parameters. Based on these parameters, the system performs nonlinear mapping processing on the grid phase offset to generate dynamic attenuation verification parameters. In order to ensure the effectiveness of path optimization, the system performs dynamic feedback calibration processing on the dynamic attenuation verification parameters through multi-level constraints to generate the grid-traffic coupling attenuation factor.

[0182] When all conditions meet the preset time-space compatibility threshold, the system generates the final node connection strength dynamic attenuation factor based on the charging efficiency gradient distribution model. This factor not only takes into account the changes in grid load and traffic flow, but also maximizes the overall efficiency of the path and user experience. This refined path planning method effectively solves the challenges caused by grid load fluctuations and service response delays, and significantly improves the feasibility and convenience of long-distance travel for electric vehicles.

[0183] In order to solve the impact of traffic flow density changes on charging station selection and further improve the spatiotemporal adaptability and user satisfaction of path planning, in some embodiments, the spatial distribution data of the combined traffic flow density gradient and the spatiotemporal attenuation coefficient are subjected to multi-source fusion processing to generate a spatiotemporal coupling constraint factor, and the spatiotemporal coupling constraint factor is used to dynamically calibrate the charging station gravity factor to generate a compatibility gradient parameter, including:

[0184] The spatial distribution data of the traffic flow density gradient is used to perform dynamic weight allocation processing on the spatiotemporal attenuation coefficient to generate a multi-source fusion feature tensor; based on the multi-source fusion feature tensor, the spatiotemporal distribution characteristics of the charging station gravity factor are dynamically grid matched to generate a spatiotemporal coupling constraint factor; the time series fluctuation characteristics of the charging station gravity factor are phase aligned in combination with the spatiotemporal coupling constraint factor to generate a compatibility gradient parameter, and the compatibility gradient parameter is used to perform dynamic feedback calibration processing on the spatial distribution characteristics of the path energy consumption correction factor to generate a composite verification factor.

[0185] In this embodiment, the spatial distribution data of the traffic flow density gradient: a data set describing the density of traffic flow at different geographical locations, is used to evaluate the congestion of a road section.

[0186] Time-space attenuation coefficient: A coefficient generated based on the time series data of the phase difference of power grid load fluctuations and the thermal density correction parameter, which is used to evaluate the importance of different times and locations.

[0187] Multi-source fusion feature tensor: A multi-dimensional data structure formed by combining data from multiple sources (such as traffic flow density gradient and spatiotemporal attenuation coefficient) for comprehensive analysis.

[0188] Dynamic Grid Matching Processing: A method that identifies and optimizes the distribution of features within a specific area by mapping data into a grid.

[0189] Space-time coupling constraint factor: It integrates the data of traffic flow density gradient and space-time attenuation coefficient and is used to adjust the gravity factor of the charging station.

[0190] Phase alignment processing: Ensure the synchronization of time series data between different time periods to reduce errors and improve forecast accuracy.

[0191] In the embodiment of the present application, firstly, the spatial distribution data of the traffic flow density gradient is used to perform dynamic weight allocation processing on the spatiotemporal attenuation coefficient to generate a multi-source fusion feature tensor.

[0192] Then, based on the multi-source fusion feature tensor, the spatiotemporal distribution characteristics of the charging station gravity factor are dynamically grid matched to generate the spatiotemporal coupling constraint factor.

[0193] Next, the time series fluctuation characteristics of the charging station gravity factor are phase-aligned in combination with the space-time coupling constraint factor to generate the compatibility gradient parameters.

[0194] Finally, the compatibility gradient parameter is used to perform dynamic feedback calibration on the spatial distribution characteristics of the path energy consumption correction factor to generate a composite verification factor.

[0195] Here is a specific example:

[0196] The system first collects traffic flow density gradient data of each section along the way, and combines the spatiotemporal attenuation coefficient to perform dynamic weight allocation processing to generate a multi-source fusion feature tensor. For example, during peak hours, some sections may be very congested, and the system will suggest drivers avoid these sections and choose a less busy route to reduce waiting time.

[0197] Next, the system dynamically grid-matches the spatiotemporal distribution characteristics of the charging station gravity factor based on the multi-source fusion feature tensor to generate spatiotemporal coupling constraint factors. This enables the system to adjust the selection priority of charging stations according to current traffic conditions and grid load conditions. For example, in certain periods of time, it is recommended to use charging stations with lower grid loads to save electricity costs and reduce waiting time.

[0198] Subsequently, the system combines the time-space coupling constraint factor to perform phase alignment on the time series fluctuation characteristics of the charging station gravity factor to generate compatibility gradient parameters. This process ensures the consistency and accuracy of the selection of charging stations in different time periods and avoids selection bias caused by time differences.

[0199] Finally, the system uses the compatibility gradient parameter to dynamically feedback and calibrate the spatial distribution characteristics of the path energy consumption correction factor to generate a composite verification factor. This factor not only takes into account the changes in traffic flow density and the impact of power grid load, but also maximizes the overall efficiency of the path and user experience. This refined path planning method effectively solves the challenges caused by changes in traffic flow density and service response delays, and significantly improves the feasibility and convenience of long-distance travel for electric vehicles. In this way, the system successfully achieves more intelligent and efficient path planning and enhances the user's travel experience.

[0200] Figure 2 A schematic diagram of a charging path planning device (or system) for an electric vehicle is provided in an embodiment of the present application, such as Figure 2 As shown, the device comprises:

[0201] A generation module 21 is used to generate an initial path topology map of multimodal traffic data fusion based on the remaining power of the electric vehicle, the real-time location coordinates and the destination coordinate data, combined with the dynamic operation data set of the charging station in the target area, wherein the dynamic operation data set of the charging station includes the available number of electric vehicle charging piles, the real-time charging power, the grid load factor and the service response delay parameter;

[0202] An estimation module 22, configured to dynamically estimate the power consumption of the initial path topology using a road slope correction coefficient, an ambient temperature nonlinear influencing factor, and a traffic flow speed fluctuation parameter, and activate a candidate path subgraph containing a charging station sequence when a charging demand is triggered by a relationship between the remaining power and the estimated consumption of consecutive path segments;

[0203] A processing module 23, configured to generate a multidimensional decision function of the candidate path subgraph based on the available number of the electric vehicle charging piles and the grid load association parameter of the real-time charging power in combination with a user behavior pattern feature vector;

[0204] Prediction module 24, used to implement dynamic priority mapping on the candidate path subgraph based on the multi-dimensional decision function and using a multi-modal scenario classification mechanism, generate a multi-level priority sequence through the spatiotemporal coupling of the service response delay parameter and the grid load valley period in the highway scenario, and establish weight distribution based on the grid load fluctuation phase difference and the service response delay threshold, and generate a charging station topology structure through multi-dimensional spatiotemporal coupling in the urban scenario by combining the traffic flow evolution parameter and the charging station gravity factor, and use the second-order derivative of the preset traffic flow prediction data to characterize the dynamic characteristics of the road network, and establish a nonlinear mapping relationship between the distance between charging stations and the traffic flow density;

[0205] The fusion module 25 is used to perform real-time data fusion of the initial path topology map, the multi-level priority sequence, the charging station topology structure and the nonlinear mapping relationship, reconstruct the energy consumption valuation system through the dynamic coupling relationship between the service status mutation index and the road congestion coefficient, and generate an adaptive charging path instruction set based on spatiotemporal collaborative optimization when it is detected that the grid load phase offset and the traffic flow density gradient form a composite trigger condition.

[0206] Figure 2 The electric vehicle charging path planning device can execute Figure 1 The implementation principle and technical effect of the electric vehicle charging path planning method described in the embodiment are not described in detail. The specific way in which each module and unit performs operations in the electric vehicle charging path planning device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0207] In one possible design, Figure 2An electric vehicle charging path planning device of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0208] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0209] The processing component 32 is used for the above Figure 1 The embodiment provides a method for planning a charging path for an electric vehicle.

[0210] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0211] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0212] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0213] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0214] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0215] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0216] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1A method for planning a charging path for an electric vehicle according to the embodiment shown.

[0217] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0218] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0219] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0220] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for planning a charging path for an electric vehicle, characterized in that: include: Based on the remaining power of the electric vehicle, the real-time location coordinates and the destination coordinate data, an initial path topology diagram of multimodal traffic data fusion is generated in combination with the dynamic operation data set of the charging station in the target area, wherein the dynamic operation data set of the charging station includes the available number of electric vehicle charging piles, the real-time charging power, the grid load factor and the service response delay parameter; The initial path topology is dynamically estimated for power consumption using a road slope correction coefficient, an ambient temperature nonlinear influencing factor, and a traffic flow speed fluctuation parameter. When a charging demand is triggered by a relationship between the remaining power and the estimated consumption of consecutive path segments, a candidate path subgraph containing a charging station sequence is activated. Based on the available number of the electric vehicle charging piles and the grid load association parameter of the real-time charging power, combined with the user behavior pattern feature vector, a multidimensional decision function of the candidate path subgraph is generated; Based on the multi-dimensional decision function, a dynamic priority mapping is implemented on the candidate path subgraph using a multi-modal scenario classification mechanism. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load valley period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, the charging station topology is generated through multi-dimensional spatiotemporal coupling in combination with the traffic flow evolution parameter and the charging station gravity factor, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established; The initial path topology map, the multi-level priority sequence, the charging station topology structure and the nonlinear mapping relationship are subjected to real-time data fusion, and the energy consumption valuation system is reconstructed through the dynamic coupling relationship between the service status mutation index and the road congestion coefficient. When it is detected that the grid load phase offset and the traffic flow density gradient form a composite trigger condition, an adaptive charging path instruction set based on spatiotemporal collaborative optimization is generated.

2. The method according to claim 1, characterized in that Based on the multi-dimensional decision function, the candidate path subgraph is dynamically mapped using a multi-modal scenario classification mechanism. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load valley period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, the charging station topology is generated through multi-dimensional spatiotemporal coupling in combination with the traffic flow evolution parameter and the charging station gravity factor, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established, including: In the highway scenario, a priority sequence of charging stations is generated based on the spatiotemporal matching relationship between the time window data of the low-load period of the power grid and the service response delay parameter, wherein the service response delay parameter is dynamically corrected by the power grid load association parameter of the available number of charging piles and the real-time charging power, and a gradient distribution model of the charging efficiency gain value is established based on the spatial distribution of the highway section nodes in the initial path topology diagram; In the urban scenario, the second-order derivative of the traffic flow prediction data is used to generate the charging station topology through the convolution operation of the charging station gravity factor and the traffic flow pattern evolution parameter, wherein the nonlinear mapping relationship between the charging station spacing and the traffic flow density is phase-synchronized and calibrated through the user behavior pattern feature vector; The charging station priority sequence is coupled with the charging station topology structure in multi-dimensional space-time. When it is detected that the grid load phase deviation exceeds a preset threshold, a dynamic feedback mechanism of the service response delay parameter and the road congestion coefficient is triggered, and an optimized path set with space-time constraints is generated by reconstructing the node connection weight values ​​in the candidate path subgraph; Based on the superposition analysis of the optimized path set and the real-time charging station heat map, a composite trigger condition of the power grid load fluctuation phase difference and the traffic flow density gradient is established. When the composite trigger condition is met, an adaptive charging path instruction set including a charging station service response delay compensation coefficient and a path energy consumption correction factor is output.

3. The method according to claim 2, characterized in that The charging station priority sequence is coupled with the charging station topology structure in multi-dimensional space-time, and when it is detected that the grid load phase deviation exceeds a preset threshold, a dynamic feedback mechanism of the service response delay parameter and the road congestion coefficient is triggered, and an optimized path set with space-time constraints is generated by reconstructing the node connection weight values ​​in the candidate path subgraph, including: Constructing a coupling characteristic tensor including the spatiotemporal distribution of the charging station priority sequence and the dynamic characteristics of the urban topology, activating a feedback regulation channel through a power grid load phase offset detector, wherein the coupling characteristic tensor includes the spatial distribution parameters of the highway section nodes and the real-time charging power fluctuation characteristics; Based on the dual-channel interaction mechanism, the service response delay parameter is dynamically corrected by utilizing the real-time charging power fluctuation characteristics in the coupling feature tensor, and a path node connection strength correction vector is generated in combination with the road congestion coefficient, wherein the service response delay parameter is associated with the time window data of the grid load valley period through the dynamic correction module of the available number of charging piles; Applying the path node connection strength correction vector to the adjacency matrix of the candidate path subgraph to generate an updated path topology structure including a power grid load compatibility index; Based on the running path optimization algorithm of the updated path topology structure, the real-time matching degree between the distance between the charging stations and the traffic flow evolution parameters is calculated to generate an optimized path set including a traffic flow density fitness level.

4. The method according to claim 3, characterized in that Based on the dual-channel interaction mechanism, the real-time charging power fluctuation characteristics in the coupling feature tensor are used to dynamically correct the service response delay parameter, and a path node connection strength correction vector is generated in combination with the road congestion coefficient, including: Using the convolution matching result of the power grid load fluctuation cycle pattern and the valley period to perform dynamic priority allocation processing to generate a service response delay correction factor, and inputting the service response delay correction factor into the closed-loop constraint processing module; Based on the congestion impact transfer function and the dual-channel attention mechanism, the service response delay correction factor and the road congestion coefficient are subjected to spatiotemporal coupling processing to generate a node connection strength dynamic attenuation factor, and the node connection strength dynamic attenuation factor is transmitted to the nonlinear superposition processing module; Performing closed-loop constraint processing on the service response delay correction factor and the node connection strength dynamic attenuation factor through composite monitoring data of power grid phase offset and traffic flow density gradient to generate dynamic feedback verification parameters, and inputting the verification parameters into a boundary limitation processing module; In a nonlinear superposition processing module, the service response delay correction factor is superimposed with the node connection strength dynamic attenuation factor to generate a preliminary path node connection strength correction vector, and the preliminary path node connection strength correction vector is transmitted to a boundary limitation processing module; The dynamic feedback verification parameters are used to perform boundary limitation processing on the scope of action of the preliminary path node connection strength correction vector to generate a path node connection strength correction vector under the power grid-traffic coupling constraint condition, and the path node connection strength correction vector is synchronously injected into the path topology update module and the traffic flow fitness calculation module.

5. The method according to claim 2, characterized in that The composite triggering condition of the grid load fluctuation phase difference and the traffic flow density gradient is established based on the superposition analysis of the optimized path set and the real-time charging station heat map. When the composite triggering condition is met, an adaptive charging path instruction set including a charging station service response delay compensation coefficient and a path energy consumption correction factor is output, including: Using the spatiotemporal distribution characteristics of the real-time charging station heat map, dynamically meshing the nodes in the optimized path set to generate a thermal density correction parameter, and dynamically weighting the time series data of the grid load fluctuation phase difference based on the thermal density correction parameter to generate a spatiotemporal attenuation coefficient; Combining the spatial distribution data of the traffic flow density gradient with the spatiotemporal attenuation coefficient to perform multi-source fusion processing, generating a spatiotemporal coupling constraint factor, using the spatiotemporal coupling constraint factor to dynamically calibrate the charging station gravity factor, and generating a compatibility gradient parameter; Based on the user behavior pattern feature vector, the compatibility gradient parameter is subjected to phase synchronization processing to generate a dynamic compensation vector, the dynamic compensation vector and the path energy consumption correction factor are subjected to spatiotemporal weight distribution processing to generate a composite verification factor, and the composite verification factor is subjected to dynamic feedback calibration processing through multi-level constraint conditions to generate a power grid-traffic coupling verification parameter; When the grid-traffic coupling verification parameter meets a preset spatiotemporal compatibility threshold, the verification parameter is hierarchically mapped based on a charging efficiency gradient distribution model to generate an adaptive charging path instruction set including a dynamic compensation level and a path energy consumption constraint.

6. The method according to claim 4, characterized in that The method of performing spatiotemporal coupling processing on the service response delay correction factor and the road congestion coefficient based on the congestion impact transfer function and the dual-channel attention mechanism to generate a node connection strength dynamic attenuation factor includes: Using the time series characteristics of the service response delay correction factor and the spatial distribution characteristics of the road congestion coefficient to perform dynamic grid division processing, generate a time-space coupling characteristic vector, perform multi-source fusion processing on the power grid load gradient parameter based on the time-space coupling characteristic vector, and generate a time-space attenuation coefficient; Combining the spatiotemporal attenuation coefficient with the traffic flow pattern evolution parameter to perform gradient constraint processing to generate a dynamic attenuation correction factor, and using the dynamic attenuation correction factor to perform phase synchronization processing on the charging station gravity factor to generate a compatibility gradient parameter; Based on the compatibility gradient parameter, the grid phase offset is subjected to nonlinear mapping processing to generate a dynamic attenuation verification parameter, and the dynamic attenuation verification parameter is subjected to dynamic feedback calibration processing through multi-level constraint conditions to generate a grid-traffic coupling attenuation factor; When the grid-traffic coupling attenuation factor meets the preset spatiotemporal compatibility threshold, the attenuation factor is hierarchically mapped based on the charging efficiency gradient distribution model to generate a node connection strength dynamic attenuation factor including a dynamic compensation level and a path energy consumption constraint.

7. The method according to claim 5, characterized in that The multi-source fusion processing of the spatial distribution data of the traffic flow density gradient and the spatiotemporal attenuation coefficient is performed to generate a spatiotemporal coupling constraint factor, and the spatiotemporal coupling constraint factor is used to dynamically calibrate the charging station gravity factor to generate a compatibility gradient parameter, including: The spatial distribution data of the traffic flow density gradient is used to perform dynamic weight allocation processing on the spatiotemporal attenuation coefficient to generate a multi-source fusion feature tensor; based on the multi-source fusion feature tensor, the spatiotemporal distribution characteristics of the charging station gravity factor are dynamically grid matched to generate a spatiotemporal coupling constraint factor; the time series fluctuation characteristics of the charging station gravity factor are phase aligned in combination with the spatiotemporal coupling constraint factor to generate a compatibility gradient parameter, and the compatibility gradient parameter is used to perform dynamic feedback calibration processing on the spatial distribution characteristics of the path energy consumption correction factor to generate a composite verification factor.

8. An electric vehicle charging path planning system, characterized in that: include: A generation module is used to generate an initial path topology map of multimodal traffic data fusion based on the remaining power of the electric vehicle, the real-time location coordinates and the destination coordinate data, combined with the dynamic operation data set of the charging station in the target area, wherein the dynamic operation data set of the charging station includes the available number of electric vehicle charging piles, the real-time charging power, the grid load factor and the service response delay parameter; an estimation module, for dynamically estimating the power consumption of the initial path topology using a road slope correction coefficient, an ambient temperature nonlinear influencing factor, and a traffic flow speed fluctuation parameter, and activating a candidate path subgraph containing a charging station sequence when a charging demand is triggered by a relationship between the remaining power and the estimated consumption of consecutive path segments; A processing module, configured to generate a multidimensional decision function of the candidate path subgraph based on the available number of the electric vehicle charging piles and the grid load association parameter of the real-time charging power in combination with a user behavior pattern feature vector; A prediction module is used to implement dynamic priority mapping on the candidate path subgraph based on the multi-dimensional decision function and using a multi-modal scenario classification mechanism. In the highway scenario, a multi-level priority sequence is generated through the spatiotemporal coupling of the service response delay parameter and the grid load valley period, and a weight distribution is established based on the grid load fluctuation phase difference and the service response delay threshold. In the urban scenario, a charging station topology structure is generated through multi-dimensional spatiotemporal coupling in combination with traffic flow evolution parameters and charging station gravity factors, and the second-order derivative of the preset traffic flow prediction data is used to characterize the dynamic characteristics of the road network, and a nonlinear mapping relationship between the distance between charging stations and the traffic flow density is established; The fusion module is used to perform real-time data fusion of the initial path topology map, the multi-level priority sequence, the charging station topology structure and the nonlinear mapping relationship, reconstruct the energy consumption valuation system through the dynamic coupling relationship between the service status mutation index and the road congestion coefficient, and generate an adaptive charging path instruction set based on spatiotemporal collaborative optimization when it is detected that the grid load phase offset and the traffic flow density gradient form a composite trigger condition.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an electric vehicle charging path planning method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an electric vehicle charging path planning method as described in any one of claims 1 to 7 is implemented.

Images