Charging pile service guidance method and system based on digital twinning

Abstract

The application provides a charging pile service guidance method and system based on digital twinning, and relates to the technical field of intelligent charging management, wherein the method comprises: collecting charging pile position topology, vehicle real-time position and charging pile historical use rate data, constructing a charging pile parking vehicle dynamic matching graph to evaluate charging pile availability in real time; generating a guidance strategy based on the matching graph, allocating charging pile resources; calculating the optimal guidance path according to the vehicle position and the allocated charging pile, and synchronously sending it to the charging pile and the user terminal, guiding the vehicle to drive to the target position; when the vehicle enters the preset range of the charging pile and prepares to park, the charging interface position and the best parking posture are identified by fusing the vehicle contour point cloud and the parking trajectory image data; and the fine guidance instruction is generated and sent to the user terminal and the charging pile to assist the vehicle to accurately park in and complete the service guidance. The application improves the utilization efficiency of the charging pile and the user service experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent charging management, and in particular to a charging pile service guidance method and system based on digital twinning. BACKGROUND

[0002] With the rapid development of electric vehicles, the demand for charging pile services in scenarios such as large parking lots and highway service areas is increasing. Users need to quickly find available charging piles and complete accurate parking charging, and charging pile resources also need to be reasonably allocated and efficiently utilized, which puts higher requirements on the intelligent level of service guidance technology.

[0003] The existing scheme detects the parking space occupancy state by deploying geomagnetic sensors, obtains the vehicle position through the user mobile terminal, recommends the nearest available charging pile to the user based on the predetermined allocation rules, and provides a two-dimensional plane navigation path to guide the vehicle to the target area.

[0004] This scheme has limitations in vehicle accurate positioning and charging pile matching accuracy, and lacks support for charging interface orientation identification and parking posture adjustment, which leads to the situation that it is not convenient and the efficiency is reduced in the actual charging docking process, and the adaptability of the resource allocation strategy to the dynamically changing environment needs to be strengthened. SUMMARY

[0005] The present application provides a charging pile service guidance method and system based on digital twinning to solve the problems of low utilization efficiency of charging piles and poor user service experience in the prior art.

[0006] To solve the above technical problems, in a first aspect, the present application provides a charging pile service guidance method based on digital twinning, comprising:

[0007] Collecting charging pile position topology data, vehicle real-time position data and charging pile historical usage rate data in a target area;

[0008] According to the charging pile position topology data, the vehicle real-time position data and the charging pile historical usage rate data, a charging pile parking vehicle dynamic matching graph is constructed to evaluate the availability of charging piles in real time;

[0009] Based on the charging pile parking vehicle dynamic matching graph, a charging pile guidance strategy is generated in combination with a digital twinning model, the charging pile guidance strategy including the corresponding relationship between available charging piles and vehicles, for allocating charging pile resources;

[0010] According to the vehicle real-time position data and the available charging piles, an optimal guidance path from the current position of the vehicle to the available charging pile is calculated using a path planning algorithm, and the optimal guidance path information is sent to the charging pile and the user mobile terminal respectively to guide the vehicle to travel to the available charging pile.

[0011] When the vehicle drives to a preset range of the charging pile and is ready to park, vehicle contour point cloud data and parking trajectory image data are acquired, and the vehicle contour point cloud data and the parking trajectory image data are subjected to multi-sensor data fusion processing to identify a vehicle charging interface position and an optimal parking posture;

[0012] Based on the vehicle charging interface position and the optimal parking posture, fine guidance instructions are generated to assist the vehicle in parking into a charging pile parking space, and the fine guidance instructions are sent to a user mobile terminal and the charging pile to realize service guidance.

[0013] Optionally, the path characteristic analysis on each candidate path is performed to generate a path length value and a turning complexity value, and based on the path length value and the turning complexity value, a deep Q network model is combined to calculate a comprehensive generation value of each candidate path, including:

[0014] The path geometric feature analysis is performed on each candidate path to extract a path node sequence and a connected edge attribute, and based on the path node sequence and the connected edge attribute, an actual passing distance of each connected edge is calculated, and the path length value is generated by accumulating the actual passing distances of the connected edges;

[0015] The turning feature analysis is performed on each candidate path to count the number of turns in the candidate path, and the angle change amount of each turn is calculated, and the number of turns and the angle change amount are weighted to obtain the turning complexity value;

[0016] The path length value and the turning complexity value are subjected to normalization processing respectively, and the normalized path length value and the normalized turning complexity value are combined into a standardized path feature vector;

[0017] The standardized path feature vector is input into a deep Q network model, and path space features are extracted through a multi-layer convolutional network of the deep Q network model;

[0018] The path space features are subjected to value evaluation through a fully connected layer of the deep Q network model, and the comprehensive generation value of each candidate path is output.

[0019] Optionally, based on the charging pile parking space vehicle dynamic matching graph, a digital twin model is combined to generate a charging pile guidance strategy, including:

[0020] The charging pile parking space vehicle dynamic matching graph is input into a digital twin model, and a graph data processing module of the digital twin model is used to process the charging pile parking space vehicle dynamic matching graph to obtain a charging pile node with a real-time load coefficient and a temporary connected edge with a connection weight;

[0021] The load evaluation module of the digital twin model screens the charging pile nodes with a real-time load coefficient less than a preset coefficient threshold to form a candidate charging pile set;

[0022] The weight screening module of the digital twin model selects charging pile nodes with a connection weight greater than a preset weight threshold from the candidate charging pile set to determine as target charging piles;

[0023] The space analysis module of the digital twin model extracts the spatial coordinates of the parking node corresponding to the target charging pile and the position coordinates of the dynamic vehicle node, and calculates the path accessibility parameter between the position coordinates of the dynamic vehicle node and the spatial coordinates of the parking node;

[0024] The decision generation module of the digital twin model generates a matching priority ranking result of the dynamic vehicle node to the target charging pile based on the path accessibility parameter;

[0025] The strategy output module of the digital twin model determines an optimal charging pile allocation scheme according to the matching priority ranking result, and forms a charging pile guidance strategy based on the optimal charging pile allocation scheme.

[0026] Optionally, the charging pile parking vehicle dynamic matching graph is constructed based on the charging pile location topology data, the vehicle real-time position data, and the charging pile historical usage rate data, including:

[0027] A charging pile node containing a charging pile position coordinate and a parking node containing a parking space coordinate are established;

[0028] Based on the charging pile location topology data, a fixed connection edge is established between the charging pile node and the parking node;

[0029] The vehicle real-time position data is converted into a dynamic vehicle node with a timestamp, and the position coordinates of the dynamic vehicle node are updated in real time;

[0030] Based on the charging pile historical usage rate data, the real-time load coefficient of each charging pile node is calculated;

[0031] According to the spatial proximity relationship between the updated position coordinates of the dynamic vehicle node and the spatial coordinates of the parking node, a temporary connection edge is established between the dynamic vehicle node and the parking node;

[0032] The real-time load coefficient of the charging pile node is used to assign a weight to the temporary connection edge to obtain a temporary connection edge with a connection weight;

[0033] Integrate the charging pile node with the real-time load coefficient, the parking space node, the dynamic vehicle node, the fixed connection edge, and the temporary connection edge with the connection weight to construct a charging pile parking space vehicle dynamic matching graph.

[0034] Optionally, the multi-sensor data fusion processing is performed on the vehicle contour point cloud data and the parking trajectory image data to identify the vehicle charging interface position and the optimal parking posture, including:

[0035] The three-dimensional structure reconstruction is performed on the vehicle contour point cloud data to generate a vehicle surface three-dimensional model;

[0036] The motion trajectory extraction is performed on the parking trajectory image data to obtain a vehicle pose change sequence;

[0037] The vehicle surface three-dimensional model and the vehicle pose change sequence are input into a multi-modal fusion neural network for spatio-temporal correlation to generate a three-dimensional posture sequence in the vehicle motion process;

[0038] In the vehicle surface three-dimensional model, the feature region of the charging interface is identified to determine the vehicle charging interface position;

[0039] According to the three-dimensional posture sequence, the relative position relationship between the vehicle and the charging pile is analyzed, and based on the relative position relationship, a deep reinforcement learning model is used to calculate the target docking posture of the charging interface corresponding to the charging pile socket;

[0040] Based on the vehicle charging interface position and the target docking posture, the optimal parking posture is determined.

[0041] Optionally, based on the vehicle charging interface position and the optimal parking posture, a fine guidance instruction is generated to assist the vehicle to park into the charging pile parking space, and the fine guidance instruction is sent to the user mobile terminal and the charging pile, including:

[0042] The horizontal deflection angle and the vertical distance of the vehicle charging interface position and the charging pile socket interface are calculated, and based on the horizontal deflection angle and the vertical distance, a lateral correction instruction is generated;

[0043] Based on the optimal parking posture, the forward direction and the rotation angle that need to be adjusted by the vehicle are determined, and based on the forward direction and the rotation angle, a longitudinal control instruction is generated;

[0044] The lateral correction instruction and the longitudinal control instruction are combined to form a fine guidance instruction;

[0045] Based on the fine guidance instruction, visual prompt information and device control signals are generated, the visual prompt information is sent to the user mobile terminal for graphical display, and the device control signals are sent to the charging pile to control the charging pile to prepare for charging service.

[0046] In a second aspect, the present application provides a charging pile service guidance system based on digital twinning, comprising:

[0047] A collection module is configured to collect charging pile position topological data, real-time vehicle position data, and charging pile historical usage rate data in a target area;

[0048] A construction module is configured to construct a charging pile berth vehicle dynamic matching graph based on the charging pile position topological data, the real-time vehicle position data, and the charging pile historical usage rate data, so as to evaluate charging pile availability in real time;

[0049] A generation module is configured to generate a charging pile guidance strategy based on the charging pile berth vehicle dynamic matching graph and in combination with a digital twinning model, the charging pile guidance strategy comprising a corresponding relationship between available charging piles and vehicles, and being used to allocate charging pile resources;

[0050] A calculation module is configured to calculate an optimal guidance path from a current position of a vehicle to an available charging pile by using a path planning algorithm based on the real-time vehicle position data and the available charging pile, and to send the optimal guidance path information to the charging pile and a user mobile terminal respectively, so as to guide the vehicle to travel to the available charging pile;

[0051] An acquisition module is configured to acquire vehicle contour point cloud data and parking trajectory image data when the vehicle travels to a preset range of the charging pile and prepares to park, and to perform multi-sensor data fusion processing on the vehicle contour point cloud data and the parking trajectory image data, so as to identify a vehicle charging interface position and an optimal parking posture;

[0052] A sending module is configured to generate fine guidance instructions based on the vehicle charging interface position and the optimal parking posture, to assist the vehicle to park into a charging pile berth, and to send the fine guidance instructions to the user mobile terminal and the charging pile, so as to realize service guidance.

[0053] In a third aspect, the present application provides an electronic device, comprising:

[0054] A memory is configured to store a computer program;

[0055] A processor is configured to implement the steps of the charging pile service guidance method based on digital twinning according to the first aspect when executing the computer program.

[0056] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program can implement the steps of the charging pile service guidance method based on digital twinning according to the first aspect when executed by a processor.

[0057] The technical scheme provided in the application has the following beneficial effects:

[0058] The application establishes a complete charging service environment information library through multi-dimensional data collection, provides a data basis for subsequent analysis and decision-making, realizes visual management and real-time state monitoring of charging pile resources, and provides an intuitive basis for resource optimization configuration. Through intelligent decision-making, the application realizes reasonable allocation of charging pile resources and improves resource utilization efficiency. The application provides accurate driving guidance for users and shortens the time for finding charging piles. The application accurately identifies vehicle features and motion states, provides data support for accurate parking, realizes accurate docking of vehicles and charging piles, and improves user charging experience.

[0059] Further, the application also acquires the current position of the vehicle and the position of the target charging pile, establishes a path search area and extracts environmental data, then constructs a path topology graph, calculates multiple candidate paths under the premise of considering obstacle distribution, analyzes the length and turning complexity of each path, calculates the comprehensive cost value combined with an intelligent evaluation model, and finally selects the optimal path as the guide path.

[0060] Moreover, the scheme can plan an optimal route considering path length and traffic convenience according to real-time environmental data, effectively avoid obstacle areas, provide safe and efficient navigation guidance, and improve the convenience and driving safety of users in finding charging piles.

[0061] These aspects or other aspects of the application will be more apparent in the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical schemes in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0063] Figure 1 A flowchart of a charging pile service guidance method based on digital twinning provided by the embodiment of the application;

[0064] Figure 2 A specific implementation schematic diagram of a charging pile service guidance method based on digital twinning provided by the embodiment of the application;

[0065] Figure 3 A structural schematic diagram of a charging pile service guidance system based on digital twinning provided by the embodiment of the application. DETAILED DESCRIPTION

[0066] In view of the problems existing in the prior art, the application provides a charging pile service guiding method based on digital twinning. The method constructs a dynamic matching graph of charging piles, parking spaces and vehicles, simulates resource distribution and vehicle state in a virtual environment in real time, accurately identifies the charging interface position and parking posture of the vehicle based on multi-sensor fusion technology, and generates whole-process guiding instructions from a driving path to parking actions in stages. The scheme realizes dynamic optimization allocation of charging pile resources and accurate guiding of vehicles, effectively improves the overall efficiency of charging services and the convenience of user operation, and fundamentally solves the deficiencies of the prior art in matching accuracy and process guiding.

[0067] In order to enable personnel in the technical field to better understand the application scheme, the application will be further described in detail below in combination with the drawings and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor belong to the scope of protection of the application.

[0068] The core of the application is to provide a charging pile service guiding method based on digital twinning, and a specific embodiment of the method is shown in the flowchart as Figure 1 The method comprises the following steps.

[0069] Step 101: Collect charging pile position topology data, vehicle real-time position data and charging pile historical usage rate data in the target area.

[0070] In step 101, the charging pile position topology data represents the spatial connection relationship between the charging piles and the parking spaces. The vehicle refers to the vehicle to be charged. The method collects the real-time position data of the vehicle, establishes a node for it in the dynamic matching graph, plans a path to the charging pile for it, and assists it to complete parking and docking. The service object and target of the whole process are to guide the vehicle to complete the whole process from pile searching to parking.

[0071] In the embodiment of the application, the sensor network deployed in the parking lot collects the installation position and connection relationship of the charging pile, receives the real-time position of the vehicle satellite positioning signal, and retrieves the historical usage record of the charging pile from the server database. These data are integrated into a standardized format that can be processed by the system.

[0072] For example, in a certain large parking lot system, the position coordinates of 8 charging piles and the connection information of 12 parking spaces are collected, the real-time position coordinates of 3 electric vehicles are obtained, and the usage time data of each charging pile in the last 7 days is retrieved from the database, wherein the historical usage rate of charging pile C4 is 30%.

[0073] Step 102: Based on the charging pile location topology data, the vehicle real-time location data and the charging pile historical usage rate data, a charging pile parking vehicle dynamic matching graph is constructed to evaluate the charging pile availability in real time.

[0074] In step 102, the charging pile parking vehicle dynamic matching graph is a graph structure, in which the nodes include charging pile nodes representing charging device locations, parking space nodes representing parking space locations, and vehicle nodes representing real-time locations of vehicles to be charged, and the edges include fixed connection edges representing the fixed membership relationship between charging piles and parking spaces, and temporary connection edges representing the dynamic association relationship between vehicles and parking spaces.

[0075] In the embodiments of the present application, a graph structure framework is established, charging pile nodes and parking space nodes are created based on charging pile location topology data and fixed connection edges are established, vehicle real-time location data is converted into vehicle nodes with timestamps, the load coefficient of the charging pile node is calculated based on historical usage rate data, temporary connection edges are established based on the spatial distance between the vehicle node and the parking space node and are assigned weights, and finally all nodes and edges are integrated to construct a complete dynamic matching graph.

[0076] For example, based on the data of step 101, a graph structure containing 8 charging pile nodes and 12 parking space nodes is established in the digital twin system, in which the charging pile C4 is connected to the parking spaces P5, P6 and P7 by fixed connection edges, the real-time locations of 3 vehicles are converted into vehicle nodes V1, V2 and V3, the load coefficient of C4 is calculated to be 0.3, and a temporary connection edge is established between V1 and P5 with a distance of 12.2 meters and a weight of 0.63, and the dynamic matching graph construction is completed.

[0077] Step 103: Based on the charging pile parking vehicle dynamic matching graph, a charging pile guidance strategy is generated in combination with a digital twin model, the charging pile guidance strategy including the corresponding relationship between available charging piles and vehicles for allocating charging pile resources.

[0078] In step 103, the charging pile guidance strategy is a resource allocation scheme generated by the system, containing the matching relationship between available charging piles and vehicles, for guiding charging service allocation.

[0079] In the embodiments of the present application, the dynamic matching graph is loaded in the digital twin model, the node and edge information is extracted by a graph data processing module, the low-load charging piles are selected to form a candidate set by a load evaluation module, the charging piles with high-weight connections are selected as target charging piles by a weight screening module, the path accessibility parameters are calculated by a spatial analysis module, and finally the matching priority ranking is generated by a decision generation module to form the guidance strategy.

[0080] For example, from the dynamic matching graph, the charging piles C4, C6, C7 and C8 with a load coefficient less than 0.5 are identified to form a candidate set, and C4 with a connection weight greater than 0.8 is selected as the target charging pile. The path reachability parameter from V1 to C4 is calculated to be 111.25, and the matching priority is sorted to determine that C4 is assigned to V1 as the guidance strategy.

[0081] Step 104: According to the real-time position data of the vehicle and the available charging piles, an optimal guidance path from the current position of the vehicle to the available charging piles is calculated by using a path planning algorithm, and the optimal guidance path information is sent to the charging piles and the user mobile terminal respectively to guide the vehicle to travel to the available charging piles.

[0082] In step 104, the current position of the vehicle refers to the instantaneous coordinate of the vehicle in the physical space when the path planning is performed. The current position of the vehicle is obtained by fusing the accurate positioning results of the vehicle output by multiple sensors. The available charging pile refers to a charging pile device that is currently in an idle state and whose spatial position matches the parking attitude of the vehicle and can provide charging service. The available charging pile is determined by judging and screening the state in the digital twin environment by comprehensively considering the historical usage rate data of the charging pile, the vehicle dynamic matching graph of the parking position of the charging pile and the accurate positioning result of the vehicle. The optimal guidance path is a navigation route from the current position of the vehicle to the target charging pile, which comprehensively considers the path length and the passing complexity.

[0083] In the embodiment of the present application, the current position coordinate of the vehicle and the coordinate of the target charging pile are obtained, the path search area is established, the channel network and obstacle data are extracted, the path topology graph is constructed, and then a path planning algorithm is used to calculate multiple candidate paths. The path length and turning complexity of each path are analyzed, the comprehensive generation value is calculated by combining the deep Q network model, the optimal path is selected and converted into navigation instructions for sending.

[0084] For example, the current position 10580 of V1 and the coordinate 135210 of the target charging pile C4 are obtained, 12 channels and 3 obstacles are extracted after the search area is established, a topology graph containing 86 nodes and 124 edges is constructed, 5 candidate paths are calculated, the length of path 1 is 285 meters and the turning complexity is 5.8, the generation value is 0.68 after the deep Q network evaluation, and the optimal path is selected and the navigation instructions are sent.

[0085] Step 105: When the vehicle travels to a predetermined range of the charging pile and prepares to park, the vehicle contour point cloud data and the parking trajectory image data are obtained, and the vehicle contour point cloud data and the parking trajectory image data are fused by multiple sensors to identify the position of the vehicle charging interface and the best parking attitude.

[0086] In step 105, the preset range represents a range with a charging pile as the center and a radius R. The vehicle contour point cloud data is a set of three-dimensional coordinates of the vehicle surface collected by the laser radar, and the parking trajectory image data is a sequence of vehicle motion images collected by the camera.

[0087] In the embodiments of the present application, the vehicle surface point cloud data is obtained by laser radar scanning and a three-dimensional model is reconstructed, the vehicle pose change is extracted from a continuous image sequence collected by a camera, the three-dimensional model and the pose sequence are input into a multi-modal fusion neural network for spatio-temporal correlation to generate a three-dimensional pose sequence, the charging interface region is identified in the model to determine the position, the relative position relationship between the vehicle and the charging pile is analyzed, and a target docking pose is calculated by a deep reinforcement learning model.

[0088] For example, when the vehicle enters the preset range of C4, 12560 point cloud data are collected by the laser radar to reconstruct a three-dimensional model, 30 images are collected by the camera to extract a pose sequence, a three-dimensional pose sequence is generated by the multi-modal fusion neural network, it is identified that the charging interface is at the left rear side 0.85 meters from the ground and 0.35 meters from the tail, it is analyzed that the relative position between the vehicle and C4 is 2.5 meters with a 15-degree deviation, and the deep reinforcement learning model outputs a target docking pose of right turning 12 degrees and advancing 1.8 meters.

[0089] Step 106: based on the vehicle charging interface position and the optimal parking pose, generating fine guidance instructions to assist the vehicle to park in the charging pile parking space, and sending the fine guidance instructions to the user mobile terminal and the charging pile to realize service guidance.

[0090] In step 106, the fine guidance instructions are a set of operation instructions for guiding the vehicle to complete accurate parking, including lateral correction and longitudinal control instructions.

[0091] In the embodiments of the present application, the lateral correction instructions are generated according to the horizontal deviation angle and the vertical distance from the charging interface to the charging pile, the longitudinal control instructions are generated based on the optimal parking pose to determine the advancing direction and the rotation angle, the complete guidance instruction sequence is integrated, and the visual prompt information and the device control signal are converted and sent to the user terminal and the charging pile respectively.

[0092] For example, the lateral correction instruction of steering wheel right turning 12 degrees is generated according to the horizontal deviation angle of 12 degrees and the vertical distance of 0.02 meters, the longitudinal control instruction of advancing 1.8 meters is generated based on the target docking pose, the three-step guidance sequence is integrated, the graphic prompt is converted and sent to the user's mobile phone, and the preparation instruction is sent to the charging pile C4.

[0093] The method realizes intelligent allocation of charging pile resources by constructing a dynamic matching graph in a digital twin environment, provides accurate guidance from pile searching to parking by combining multi-sensor data fusion technology, effectively improves the utilization efficiency and service quality of charging piles, and improves the charging experience of users.

[0094] To solve the problem of single route and insufficient consideration of actual traffic convenience in path planning of the existing charging guidance scheme, in some embodiments, step 104: according to the real-time position data of the vehicle and the available charging piles, an optimal guidance path from the current position of the vehicle to the available charging piles is calculated by using a path planning algorithm, as shown in the following formula: Figure 2

[0095] Step 201: obtaining a current coordinate point corresponding to the real-time position data of the vehicle and a target parking coordinate point corresponding to the available charging pile.

[0096] In step 201, the current coordinate point is a specific position point corresponding to the real-time position data of the vehicle, and the target parking coordinate point is a specific parking position point corresponding to the available charging pile.

[0097] In the embodiments of the present application, the system extracts the accurate position information of the vehicle from the real-time data stream, and obtains the parking position information of the allocated charging pile, to provide accurate start and end coordinates for path planning.

[0098] Step 202: establishing a path search area with the current coordinate point as the start point and the target parking coordinate point as the end point, and extracting channel network data and obstacle distribution data from the path search area.

[0099] In step 202, the path search area is a spatial range delimited by the current coordinate point and the target parking coordinate point, the channel network data is the road connection information available for traffic in the area, and the obstacle distribution data is the position information of fixed or temporary obstacles affecting traffic in the area.

[0100] In the embodiments of the present application, the system automatically delimits the search range according to the start and end coordinates, extracts the topological relationship of all feasible roads by analyzing the electronic map data of the area, and identifies the spatial distribution of various obstacles.

[0101] Step 203: based on the channel network data, constructing a path topological graph containing path nodes and connection edges, and based on the obstacle distribution data, calculating a plurality of candidate paths from the start point to the end point by using a path planning algorithm in the path topological graph.

[0102] In step 203, the path topological graph is a network graph composed of path nodes and connection edges, the path nodes represent road intersections or characteristic points, and the connection edges represent the passable road sections between the nodes.

[0103] ​In the embodiments of the present application, the system constructs a complete path network structure based on the channel network data, and under the premise of considering the distribution of obstacles, uses a path search algorithm to calculate multiple feasible routes from the starting point to the ending point in the topological graph as candidate paths.

[0104] Step 204: Perform path characteristic analysis on each candidate path to generate a path length value and a turning complexity value, and calculate a comprehensive generation value of each candidate path according to the path length value and the turning complexity value in combination with a deep Q network model.

[0105] In step 204, the path length value is a total length measurement of the candidate path, the turning complexity value is a complexity measurement of turning operations in the path, and the comprehensive generation value is a quantitative score of the overall quality of the path by an intelligent evaluation model.

[0106] In the embodiments of the present application, the system performs geometric feature analysis on each candidate path, calculates the total length and turning complexity of the path, and inputs these feature parameters into a trained deep Q network model to output a comprehensive score of each path through the value evaluation network of the model.

[0107] Step 205: Select a candidate path with a comprehensive generation value less than a preset generation cost threshold as an optimal guide path.

[0108] In step 205, the preset generation cost threshold is a path quality qualification standard set by the system.

[0109] In the embodiments of the present application, the system compares the comprehensive generation values of the candidate paths with a preset threshold, and selects the path with the optimal score as the final guide route.

[0110] The following is a specific example:

[0111] After determining to assign the charging pile C4 to the vehicle V1 and establish the guidance task from the current position coordinate point [105, 80] of V1 to the target parking coordinate point [135, 210] based on the foregoing embodiments, the system establishes a path search area with the two points as the start and end points, extracts the channel network data of 12 channels and the obstacle distribution data of 3 obstacles from the area, constructs a path topology graph containing 86 path nodes and 124 connection edges based on the channel network data, and calculates 5 candidate paths by using the A-star path planning algorithm in the premise of considering the obstacle distribution. When performing path characteristic analysis on the first candidate path, the path length value 285 meters is obtained by accumulating the actual lengths of 18 connection edges in the path, and 7 turning points in the path are identified and the turning angle value of each turning point is calculated. The formula for calculating the turning complexity is as follows: the turning complexity is equal to the number of turns multiplied by the weight coefficient k1 plus the average turning angle multiplied by the weight coefficient k2, where k1 is 0.4 and k2 is 0.1. The average turning angle is 85 degrees, and the turning complexity value is 7*0.4+85*0.1=2.8+8.5=11.3. The path length value 285 meters and the turning complexity value 11.3 are normalized to form a standardized path characteristic vector [0.72, 0.65], which is input into the pre-trained deep Q network model to output the comprehensive cost value 0.68. The cost values of the remaining 4 paths are 0.71, 0.75, 0.82 and 0.79 respectively. The first candidate path with the cost value 0.68 less than the preset cost threshold 0.70 is selected as the optimal guidance path, and the path planning from the current position of the vehicle to the charging pile C4 is completed.

[0112] In the embodiments of the present application, the path planning scheme can generate an optimal route considering path length and passing convenience according to actual environmental characteristics, effectively avoid obstacle areas, provide safe and efficient navigation guidance, and improve user convenience and driving comfort when finding charging piles.

[0113] In order to further improve the accuracy and practicality of path evaluation, in some embodiments, step 204: the path characteristic analysis of each candidate path generates a path length value and a turning complexity value, and the comprehensive cost value of each candidate path is calculated based on the path length value and the turning complexity value in combination with a deep Q network model, including:

[0114] Step 301: performing path geometric feature analysis on each candidate path to extract path node sequences and connection edge attributes, and calculating the actual passing distance of each connection edge based on the path node sequences and the connection edge attributes, and generating a path length value by accumulating the actual passing distance of each connection edge.

[0115] In step 301, the path node sequence is an ordered arrangement of individual path nodes contained in the candidate path, and the connection edge attribute is an actual travel distance parameter possessed by the connection edge.

[0116] In the embodiment of the present application, the system extracts the path node sequence constituting the path in the travel order of the candidate path, obtains the actual travel distance attribute of the connection edge between adjacent nodes in the sequence, and sequentially accumulates the actual travel distances of these connection edges to obtain the path length value reflecting the total length of the path.

[0117] Step 302: Perform turn feature analysis on each candidate path, count the number of turns in the candidate path, and calculate the angle change amount of each turn, and perform weighted calculation on the number of turns and the angle change amount to obtain a turn complexity value.

[0118] In step 302, the number of turns is the number of times the vehicle needs to change the driving direction in the candidate path, and the angle change amount is the directional angle value that the vehicle needs to adjust at each turn.

[0119] In the embodiment of the present application, the system identifies the position of the turning point by analyzing the direction change of adjacent connection edges in the path node sequence, counts the number of turning points to obtain the number of turns, calculates the included angle of adjacent connection edges at each turning point as the angle change amount, and performs weighted summation on the number of turns and the angle change amount to obtain the turn complexity value.

[0120] Step 303: Normalize the path length value and the turn complexity value respectively, and combine the normalized path length value and the normalized turn complexity value into a standardized path feature vector.

[0121] In step 303, the standardized path feature vector is a multi-dimensional data representation composed of normalized path features.

[0122] In the embodiment of the present application, the system converts the path length value and the turn complexity value into values in the range of zero to one through normalization algorithm respectively, and combines the two normalized values to form a standardized path feature vector containing path core features.

[0123] Step 304: Input the standardized path feature vector into the deep Q network model, and extract path space features through the multi-layer convolutional network of the deep Q network model.

[0124] In step 304, the path space feature is a high-dimensional feature representation reflecting the geometric shape and spatial distribution law of the path.

[0125] In the embodiment of the present application, the system inputs the standardized path feature vector into the deep Q network model, and performs nonlinear transformation and feature extraction on the input features through the multi-layer convolution network in the model to obtain path space features that can better reflect the essential characteristics of the path.

[0126] Step 305: performing value evaluation on the path space features through the fully connected layer of the deep Q network model, and outputting the comprehensive generation cost of each candidate path.

[0127] In the embodiment of the present application, the system inputs the path space features into the fully connected layer of the deep Q network model, and outputs the generation cost reflecting the comprehensive quality of the path through nonlinear calculation and weight analysis of the fully connected layer.

[0128] The following is a specific example:

[0129] On the basis of obtaining 5 candidate paths based on the foregoing embodiment, the system performs path geometric feature analysis on the first candidate path, extracts 18 path node sequences N1 to N18 and 17 connection edge attributes contained in the path, obtains the path length value 285 meters based on the actual travel distance data in the connection edge attributes by accumulating the actual travel distances of the 17 connection edges, then performs turning feature analysis on the path, identifies 7 turning points by comparing the direction vectors of adjacent connection edges, counts the number of turns as 7, calculates the angle change amount of each turn as 90 degrees, 45 degrees, 90 degrees, 135 degrees, 90 degrees, 45 degrees, and 90 degrees, respectively, adopts the formula that the turning complexity is equal to the number of turns multiplied by the weight coefficient k1 plus the average turning angle multiplied by the weight coefficient k2, wherein k1 is a dimensionless coefficient of 0.4, k2 is a dimensionless coefficient of 0.1, the number of turns is 7, and the average turning angle is 85 degrees, and the turning complexity value is equal to 7 multiplied by 0.4 plus 85 multiplied by 0.1, which is equal to 2.8 plus 8.5, which is equal to 11.3, the path length value 285 meters and the turning complexity value 11.3 are normalized respectively, the path length value is converted to 0.72 in the range of 0 to 1 using the maximum and minimum value normalization method, and the turning complexity value is converted to 0.65 in the range of 0 to 1, the two normalized values are combined to form the standardized path feature vector [0.72, 0.65], the vector is input into the deep Q network model, the path space features are extracted through the multi-layer convolution network of the model, and the value of these features is evaluated through the fully connected layer, and finally the comprehensive generation cost 0.68 of the candidate path is output. The remaining 4 candidate paths are processed in the same way to obtain the comprehensive generation costs 0.71, 0.75, 0.82, and 0.79, respectively, and the comprehensive evaluation of all candidate paths is completed.

[0130] In the embodiment of the present application, the path evaluation scheme can comprehensively consider multiple-dimensional characteristics such as path length and turning complexity, accurately quantify the comprehensive quality of the path through an intelligent evaluation model, provide a scientific basis for selecting the optimal guiding path, and effectively improve the rationality and practicality of path planning.

[0131] In order to further improve the intelligent level of charging pile resource allocation, in some embodiments, step 103: the charging pile parking vehicle dynamic matching graph is combined with a digital twin model to generate a charging pile guiding strategy, including:

[0132] Step 401: input the charging pile parking vehicle dynamic matching graph into the digital twin model, process the charging pile parking vehicle dynamic matching graph through a graph data processing module of the digital twin model, to obtain charging pile nodes with real-time load coefficients and temporary connection edges with connection weights.

[0133] In the embodiment of the present application, the system inputs the charging pile parking vehicle dynamic matching graph into the digital twin model, analyzes the node and edge information in the graph through the graph data processing module, and extracts real-time load coefficient data attached to the charging pile nodes and connection weight data attached to the temporary connection edges.

[0134] Step 402: filter the charging pile nodes with real-time load coefficients less than a preset coefficient threshold through a load evaluation module of the digital twin model, to form a candidate charging pile set.

[0135] In step 402, the preset coefficient threshold is a load level qualification standard set by the system, and the candidate charging pile set is a group of available charging piles after preliminary screening.

[0136] In the embodiment of the present application, the system compares the real-time load coefficients of each charging pile node with the preset coefficient threshold through the load evaluation module, and selects charging pile nodes with load levels meeting the requirements to form a candidate set.

[0137] Step 403: select charging pile nodes with connection weights greater than a preset weight threshold from the candidate charging pile set through a weight screening module of the digital twin model, to determine as target charging piles.

[0138] In step 403, the preset weight threshold is a connection strength qualification standard set by the system, and the target charging pile is the charging device finally determined to be suitable for serving the current vehicle.

[0139] In the embodiment of the present application, the system checks whether the connection weight of the corresponding temporary connection edge of each charging pile node in the candidate charging pile set meets the preset weight threshold requirement through the weight screening module, and selects the charging pile node meeting the condition to determine as the target charging pile.

[0140] Step 404: Extract the spatial coordinates of the target charging pile corresponding to the parking node and the position coordinates of the dynamic vehicle node through the spatial analysis module of the digital twin model, and calculate the path accessibility parameter between the position coordinates of the dynamic vehicle node and the spatial coordinates of the parking node.

[0141] In step 404, the path accessibility parameter is a comprehensive index reflecting the degree of convenience from the vehicle position to the charging pile parking.

[0142] In the embodiments of the present application, the system obtains the spatial coordinates of the target charging pile corresponding to the parking node and the position coordinates of the associated dynamic vehicle node through the spatial analysis module, and calculates the path accessibility parameter based on the spatial relationship and environmental characteristics between two points.

[0143] Step 405: Based on the path accessibility parameter, generate a matching priority ranking result of the dynamic vehicle node to the target charging pile through the decision generation module of the digital twin model.

[0144] In step 405, the matching priority ranking result is the sequential arrangement of the priority degree of the vehicle matching with multiple candidate charging piles.

[0145] In the embodiments of the present application, the system generates a matching priority ranking result of the dynamic vehicle node to different target charging piles through the decision generation module based on the size of the path accessibility parameter of each candidate charging pile.

[0146] Step 406: According to the matching priority ranking result, determine the optimal charging pile allocation scheme through the strategy output module of the digital twin model, and form a charging pile guidance strategy based on the optimal charging pile allocation scheme.

[0147] In step 406, the optimal charging pile allocation scheme is the best resource allocation scheme determined by the system.

[0148] In the embodiments of the present application, the system selects the optimal matching pair according to the matching priority ranking result through the strategy output module, forms a charging pile allocation scheme, and formulates a charging pile guidance strategy containing specific execution steps based on the scheme.

[0149] The following is a specific example:

[0150] After the charging pile parking vehicle dynamic matching graph containing 8 charging pile nodes, 12 parking node and 3 dynamic vehicle nodes is constructed based on the foregoing embodiment, the system inputs the dynamic matching graph into the digital twin model, and processes the real-time load coefficients of the charging pile nodes through the graph data processing module to be 0.8, 0.6, 0.9, 0.3, 0.7, 0.4, 0.5 and 0.2 respectively, and the connection weights of the temporary connection edges are 0.7, 0.8, 0.6, 0.9 and 0.5 respectively, the charging pile nodes with a real-time load coefficient less than a preset coefficient threshold 0.5 are screened through the load evaluation module, four charging piles numbered 4, 6, 7 and 8 are obtained to form a candidate charging pile set, the charging pile node with a connection weight greater than a preset weight threshold 0.8 is selected from the set through the weight screening module, the charging pile numbered 4 is determined as the target charging pile, the space coordinates 135210 of the parking node corresponding to the target charging pile and the position coordinates 10580 of the dynamic vehicle node V1 are extracted through the space analysis module, and the path accessibility parameter between the two is calculated. The formula path accessibility parameter equals to straight line distance divided by path complexity coefficient, wherein the straight line distance is calculated by the distance formula between two points as , the path complexity coefficient is determined as 1.2 according to the number of path turns and the number of obstacles, and the path accessibility parameter is equal to 133.5 divided by 1.2, that is, 111.25. The matching priority ranking result of the dynamic vehicle node to each candidate charging pile is generated based on the path accessibility parameter through the decision generation module, wherein the priority score of the charging pile numbered 4 is the highest, which is 8.5 points, the charging pile numbered 6 is 7.2 points, the charging pile numbered 7 is 6.8 points, and the charging pile numbered 8 is 6.5 points. The optimal charging pile allocation scheme is determined according to the ranking result through the strategy output module, and the charging pile guidance strategy of allocating the charging pile numbered 4 to the dynamic vehicle node V1 is formed.

[0151] In the embodiments of the present application, the charging pile guidance strategy generation scheme can comprehensively consider the charging pile load state, the spatial position relationship and the path passing condition, realize intelligent allocation of charging pile resources through multi-module collaborative processing, and effectively improve the efficiency and quality of charging service.

[0152] In order to further improve the accuracy and real-time performance of charging pile resource management, in some embodiments, step 102: constructing a charging pile parking vehicle dynamic matching graph according to the charging pile position topology data, the vehicle real-time position data and the charging pile historical usage rate data, comprises:

[0153] Step 501: establishing a charging pile node containing charging pile position coordinates and a parking node containing parking space coordinates.

[0154] In step 501, the charging pile node is a point element representing the spatial position of the charging device, and the parking node is a point element representing the spatial position of the parking space.

[0155] In the embodiment of the present application, the system creates a charging pile node according to the actual installation position of the charging pile and creates a parking space node according to the actual spatial distribution of the parking space in the digital twin environment, and establishes a basic spatial position framework.

[0156] Step 502: based on the charging pile position topology data, a fixed connection edge is established between the charging pile node and the parking space node.

[0157] In step 502, the fixed connection edge is a connection line representing the fixed membership relationship between the charging pile and the parking space.

[0158] In the embodiment of the present application, the system establishes a fixed and unchanging connection edge between the corresponding charging pile node and the parking space node based on the corresponding relationship between the charging pile and the parking space recorded in the charging pile position topology data.

[0159] Step 503: convert the vehicle real-time position data into a dynamic vehicle node with a time stamp, and update the position coordinates of the dynamic vehicle node in real time.

[0160] In step 503, the dynamic vehicle node is a point element representing the real-time position of the vehicle to be charged, and the time stamp is a marker recording the position collection time.

[0161] In the embodiment of the present application, the system continuously receives vehicle real-time position data, converts these data into dynamic vehicle nodes with time stamps, and updates the coordinate information of these nodes in real time in the digital twin environment.

[0162] Step 504: based on the charging pile historical usage rate data, calculate the real-time load coefficient of each charging pile node.

[0163] In step 504, the real-time load coefficient is a dynamic parameter reflecting the current use pressure of the charging pile.

[0164] In the embodiment of the present application, the system calculates and analyzes the real-time load state index of each charging pile node based on the charging pile historical usage rate data.

[0165] Step 505: according to the spatial proximity relationship between the updated position coordinates of the dynamic vehicle node and the spatial coordinates of the parking space node, establish a temporary connection edge between the dynamic vehicle node and the parking space node.

[0166] In step 505, the spatial proximity relationship is the proximity degree of the spatial position of the dynamic vehicle node and the parking space node in the digital twin environment. This relationship is formed by calculating the Euclidean distance between the real-time position coordinates of the dynamic vehicle node and the fixed spatial coordinates of the parking space node, and judging whether the distance is less than the set proximity threshold.

[0167] In the embodiment of the present application, the system establishes a temporary connection edge when the distance between the updated dynamic vehicle node position coordinates and the parking space node spatial coordinates reaches the set condition according to the distance relationship.

[0168] Step 506: Assign a weight value to the temporary connection edge using the real-time load coefficient of the charging pile node to obtain a temporary connection edge with a connection weight.

[0169] In step 506, the connection weight is a quantitative value of the association strength represented by the temporary connection edge.

[0170] In the embodiment of the present application, the system uses the real-time load coefficient of the charging pile node to assign a corresponding weight value to the temporary connection edge according to the set calculation rule.

[0171] Step 507: Integrate the charging pile node with the real-time load coefficient, the parking space node, the dynamic vehicle node, the fixed connection edge, and the temporary connection edge with the connection weight to construct a charging pile parking vehicle dynamic matching graph.

[0172] In the embodiment of the present application, the system integrates the charging pile node with the real-time load coefficient, the parking space node, the dynamic vehicle node, the fixed connection edge, and the temporary connection edge with the connection weight to construct a complete dynamic matching graph.

[0173] In the embodiment of the present application, the dynamic matching graph construction scheme can reflect the dynamic changes of the charging pile resource state and the vehicle position in real time, establish an accurate resource and demand association relationship, and provide a reliable data foundation for subsequent intelligent guidance.

[0174] In order to further improve the accuracy and automation level of vehicle charging docking, in some embodiments, step 105: performing multi-sensor data fusion processing on the vehicle contour point cloud data and the parking trajectory image data to identify the vehicle charging interface position and the best parking posture, comprising:

[0175] Step 601: Reconstruct the three-dimensional structure of the vehicle contour point cloud data to generate a vehicle surface three-dimensional model.

[0176] In step 601, the vehicle surface three-dimensional model is a three-dimensional digital representation of the vehicle external contour obtained by point cloud data reconstruction.

[0177] In the embodiment of the present application, the system processes the vehicle contour point cloud data collected by the laser radar and generates a three-dimensional model that accurately reflects the external shape of the vehicle through a surface reconstruction algorithm.

[0178] Step 602: Extract the motion trajectory of the parking trajectory image data to obtain a vehicle pose change sequence.

[0179] In step 602, the vehicle pose change sequence is a continuous record of the change of the vehicle position and posture over time extracted from the image data.

[0180] In the embodiment of the present application, the system analyzes the parking trajectory image sequence collected by the camera, extracts the pose change data of the vehicle in the parking process through a visual tracking algorithm to form a time sequence.

[0181] Step 603: input the vehicle surface three-dimensional model and the vehicle pose change sequence into a multi-modal fusion neural network for spatio-temporal correlation to generate a three-dimensional posture sequence in the vehicle motion process.

[0182] In step 603, the three-dimensional posture sequence is a continuous state record of the three-dimensional position and direction of the vehicle in the motion process.

[0183] In the embodiment of the present application, the system inputs the vehicle surface three-dimensional model and the vehicle pose change sequence into a multi-modal fusion neural network, and generates a vehicle motion posture sequence containing complete three-dimensional information through the spatio-temporal feature extraction capability of the network.

[0184] Step 604: identify the feature area of the charging interface in the vehicle surface three-dimensional model to determine the position of the vehicle charging interface.

[0185] In the embodiment of the present application, the system locates the feature area of the charging interface in the vehicle surface three-dimensional model through a feature recognition algorithm to determine its accurate position in the vehicle coordinate system.

[0186] Step 605: analyze the relative position relationship between the vehicle and the charging pile according to the three-dimensional posture sequence, and calculate the target docking posture of the charging interface corresponding to the charging pile socket based on the relative position relationship using a deep reinforcement learning model.

[0187] In step 605, the target docking posture is the ideal relative posture that the charging interface and the charging pile socket need to reach to achieve perfect docking.

[0188] In the embodiments of the present application, the system analyzes the relative position relationship between the vehicle and the charging pile according to the three-dimensional posture sequence, and calculates the optimal docking posture parameter by using a deep reinforcement learning model. The specific implementation process is: based on the vehicle position coordinates and heading angle data extracted from the three-dimensional posture sequence and the charging pile position coordinates, the relative distance and angle difference between the two are calculated, and these parameters and the vehicle charging interface position are jointly used as a state vector to input the deep reinforcement learning model. The model evaluates the long-term benefits of different docking postures through its value network, and outputs the optimal docking action sequence through the policy network, for example, when the system detects that the vehicle is located 2.5 meters southeast of the charging pile and the heading angle deviation is 15 degrees, the model calculates and outputs the target docking posture of "first turning right by 12 degrees and then straightening forward by 1.8 meters", so that the charging interface is finally accurately aligned with the charging pile socket.

[0189] Step 606: determining the optimal parking posture based on the vehicle charging interface position and the target docking posture.

[0190] In the embodiments of the present application, the system determines the optimal parking position and direction angle of the vehicle based on the vehicle charging interface position and the target docking posture through geometric relationship calculation.

[0191] In the embodiments of the present application, the multi-sensor data fusion processing scheme can accurately identify the characteristics and motion state of the vehicle, calculate the optimal docking scheme through intelligent algorithm, realize the accurate docking of the vehicle and the charging pile, and improve the convenience and success rate of the charging operation.

[0192] In order to further improve the accuracy and user experience of the charging parking guidance, in some embodiments, step 106: based on the vehicle charging interface position and the optimal parking posture, generate fine guidance instructions to assist the vehicle to park in the charging pile parking space, and send the fine guidance instructions to the user mobile terminal and the charging pile, including:

[0193] Step 701: calculate the horizontal angle deviation and vertical distance between the vehicle charging interface position and the charging pile socket interface, and generate a lateral correction instruction according to the horizontal angle deviation and the vertical distance.

[0194] In step 701, the horizontal angle deviation is the angle deviation of the vehicle charging interface and the charging pile socket interface in the horizontal direction, the vertical distance is the height difference between the two in the vertical direction, and the lateral correction instruction is an operation instruction for adjusting the horizontal deviation of the vehicle.

[0195] In the embodiments of the present application, the system calculates the horizontal angle deviation and vertical height difference between the vehicle charging interface and the charging pile socket interface through geometric relationship, and generates a lateral correction instruction containing the steering wheel rotation direction and angle based on these parameters.

[0196] Step 702: Based on the optimal parking posture, determine the forward direction and rotation angle that the vehicle needs to adjust, and generate longitudinal control commands according to the forward direction and rotation angle.

[0197] In step 702, the forward direction is the direction in which the vehicle needs to move, the rotation angle is the amount of steering wheel rotation that the vehicle needs to adjust, and the longitudinal control command is the operation guide used to control the vehicle's forward and backward movement and speed.

[0198] In this embodiment, the system determines the specific direction the vehicle needs to travel and the steering wheel rotation angle based on the optimal parking posture, and generates longitudinal control commands that include speed control and travel distance based on these parameters.

[0199] Step 703: Combine the lateral correction command and the longitudinal control command to form a fine guidance command.

[0200] In this embodiment, the system combines and arranges the lateral correction instructions and longitudinal control instructions in the order of execution to form a fine guidance instruction containing complete operation steps.

[0201] Step 704: Based on the fine-grained guidance instructions, generate visual prompts and device control signals, send the visual prompts to the user's mobile terminal for graphical display, and send the device control signals to the charging pile to control the charging pile to prepare for charging service.

[0202] In step 704, the visual prompts are converted into graphical interface display guidance content, and the device control signals are device control instructions sent to the charging pile. Controlling the charging pile to prepare for charging service refers to the system sending device control signals to the charging pile, triggering the charging pile to perform a series of preparatory tasks, including initiating a self-test program to check if the device status is normal, controlling the charging compartment door to open automatically, moving the charging gun to the pre-dock position, activating the payment QR code display screen, and updating the charging pile status to ready, so that it can immediately enter the charging process after the vehicle stops.

[0203] In this embodiment, the system converts the fine-grained guidance instructions into graphical prompts suitable for display on the mobile terminal, and generates control signals to control the charging pile's preparation status, which are then sent to the user's mobile terminal and the charging pile equipment, respectively.

[0204] In this embodiment of the application, the fine-grained guidance instruction generation scheme can provide clear and specific operation guidance, realize the precise docking of vehicles and charging piles, effectively reduce the difficulty of user operation, and improve the automation level of charging services and user experience.

[0205] Figure 3 A schematic diagram of a digital twin-based charging pile service guidance system provided in this application embodiment is shown below.Figure 3 The specific embodiments part describes as shown:

[0206] The acquisition module 31 is configured to acquire charging pile position topological data, real-time vehicle position data, and charging pile historical usage rate data in a target area.

[0207] The construction module 32 is configured to construct a charging pile parking vehicle dynamic matching graph based on the charging pile position topological data, the real-time vehicle position data, and the charging pile historical usage rate data, to evaluate charging pile availability in real time.

[0208] The generation module 33 is configured to generate a charging pile guidance strategy based on the charging pile parking vehicle dynamic matching graph and in combination with a digital twin model, the charging pile guidance strategy including a correspondence between available charging piles and vehicles, for allocating charging pile resources.

[0209] The calculation module 34 is configured to calculate an optimal guidance path from a current position of a vehicle to an available charging pile by using a path planning algorithm based on the real-time vehicle position data and the available charging pile, and to send the optimal guidance path information to the charging pile and a user mobile terminal respectively, to guide the vehicle to travel to the available charging pile.

[0210] The acquisition module 35 is configured to acquire vehicle contour point cloud data and parking trajectory image data when the vehicle travels to a preset range of the charging pile and prepares to park, and to perform multi-sensor data fusion processing on the vehicle contour point cloud data and the parking trajectory image data, to identify a vehicle charging interface position and an optimal parking posture.

[0211] The sending module 36 is configured to generate fine guidance instructions based on the vehicle charging interface position and the optimal parking posture, to assist the vehicle to park into a charging pile parking space, and to send the fine guidance instructions to the user mobile terminal and the charging pile, to realize service guidance.

[0212] The digital twin-based charging pile service guidance system according to the embodiments of the present application is used to realize the digital twin-based charging pile service guidance method described above, and therefore the specific embodiments of the digital twin-based charging pile service guidance system can refer to the embodiments of the digital twin-based charging pile service guidance method described above, and the specific embodiments can refer to the descriptions of the respective embodiments, which will not be repeated here.

[0213] The present application also provides an electronic device, including a memory for storing a computer program, and a processor for executing the computer program to realize the steps of the digital twin-based charging pile service guidance method described above.

[0214] The application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program.

[0215] In an example embodiment, the computer readable storage medium can include, but is not limited to, a U disk, a read-only memory, a random access memory, a mobile hard disk, a magnetic disk or an optical disk, and various media capable of storing a computer program.

[0216] The embodiments of the application further provide a computer program product, and the computer program product includes a computer program, and the computer program is executed by a processor to implement the steps in the embodiments of the method for guiding charging pile service based on digital twinning.

[0217] The skilled person can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in the above description in general terms. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0218] The above describes in detail the method, system, electronic device and storage medium provided by the application. The principles and implementation modes of the application are described by applying specific examples. The above description of the examples is only used to help understand the method of the application and its core idea. It should be pointed out that for ordinary skilled persons in the technical field, some improvements and modifications can be made to the application without departing from the principles of the application. These improvements and modifications also fall within the protection scope of the application.

Claims

1. A charging pile service guidance method based on digital twin, characterized in that, include: Collect topology data of charging pile locations, real-time vehicle location data, and historical usage data of charging piles within the target area; Based on the charging pile location topology data, the vehicle real-time location data, and the charging pile historical usage rate data, a dynamic matching map of charging pile parking spaces and vehicles is constructed to assess the availability of charging piles in real time. Based on the dynamic matching map of charging pile parking spaces and vehicles, combined with the digital twin model, a charging pile guidance strategy is generated. The charging pile guidance strategy includes the correspondence between available charging piles and vehicles, which is used to allocate charging pile resources. Based on the vehicle's real-time location data and the available charging piles, a path planning algorithm is used to calculate the optimal guidance path from the vehicle's current location to the available charging piles. The optimal guidance path information is then sent to the charging piles and the user's mobile terminal to guide the vehicle to the available charging piles. When the vehicle drives to the preset range of the charging pile and prepares to park, the vehicle contour point cloud data and parking trajectory image data are acquired, and the vehicle contour point cloud data and the parking trajectory image data are subjected to multi-sensor data fusion processing to identify the vehicle charging interface position and the optimal parking posture. Based on the location of the vehicle's charging port and the optimal parking posture, a precise guidance instruction is generated to assist the vehicle in parking the charging station. The precise guidance instruction is then sent to the user's mobile terminal and the charging station to provide service guidance.

2. The method according to claim 1, characterized in that, The step of calculating the optimal guidance path from the vehicle's current location to an available charging station using a path planning algorithm, based on the vehicle's real-time location data and the available charging stations, includes: Obtain the current coordinates of the vehicle's real-time location data and the coordinates of the target parking space corresponding to the available charging pile; Establish a path search area with the current coordinate point as the starting point and the target berth coordinate point as the ending point, and extract channel network data and obstacle distribution data from the path search area; Based on the channel network data, a path topology graph containing path nodes and connecting edges is constructed. In the path topology graph, based on the obstacle distribution data, a path planning algorithm is used to calculate multiple candidate paths from the starting point to the ending point. For each candidate path, perform path characteristic analysis to generate path length and turning complexity values. Based on the path length and turning complexity values, and combined with the deep Q-network model, calculate the comprehensive cost of each candidate path. Candidate paths whose overall cost is less than a preset cost threshold are selected as the optimal guiding path.

3. The method according to claim 2, characterized in that, The process involves analyzing the path characteristics of each candidate path to generate a path length value and a turning complexity value. Based on these values ​​and the turning complexity value, and using a deep Q-network model, the comprehensive cost of each candidate path is calculated, including: For each candidate path, perform path geometric feature analysis to extract the path node sequence and connecting edge attributes. Based on the path node sequence and connecting edge attributes, calculate the actual travel distance of each connecting edge. By accumulating the actual travel distances of each connecting edge, generate the path length value. For each candidate path, perform turning feature analysis, count the number of turns in the candidate path, and calculate the angle change for each turn. Then, perform a weighted calculation on the number of turns and the angle change to obtain the turning complexity value. The path length value and the turning complexity value are normalized respectively, and the normalized path length value and the normalized turning complexity value are combined into a standardized path feature vector. The standardized path feature vector is input into a deep Q-network model, and path space features are extracted through the multi-layer convolutional network of the deep Q-network model. The path space features are evaluated using the fully connected layers of the deep Q-network model, and the comprehensive cost value of each candidate path is output.

4. The method according to claim 1, characterized in that, The charging pile guidance strategy is generated based on the dynamic vehicle matching map of the charging pile parking space and combined with the digital twin model, including: The dynamic matching map of the charging pile parking space vehicles is input into the digital twin model. The graph data processing module of the digital twin model processes the dynamic matching map of the charging pile parking space vehicles to obtain charging pile nodes with real-time load coefficients and temporary connection edges with connection weights. The load assessment module of the digital twin model is used to screen charging pile nodes whose real-time load coefficient is less than a preset coefficient threshold to form a candidate charging pile set. The digital twin model's weight filtering module selects charging pile nodes with connection weights greater than a preset weight threshold from the candidate charging pile set, and determines them as target charging piles. The spatial analysis module of the digital twin model extracts the spatial coordinates of the parking space node and the position coordinates of the dynamic vehicle node corresponding to the target charging pile, and calculates the path reachability parameters between the position coordinates of the dynamic vehicle node and the spatial coordinates of the parking space node. The decision generation module of the digital twin model generates a dynamic ranking result of the matching priority from the vehicle node to the target charging pile based on the path reachability parameters. The optimal charging pile allocation scheme is determined by the strategy output module of the digital twin model based on the matching priority ranking result, and a charging pile guidance strategy is formed based on the optimal charging pile allocation scheme.

5. The method according to claim 1, characterized in that, The step of constructing a dynamic matching map of charging pile parking spaces based on the charging pile location topology data, the vehicle real-time location data, and the charging pile historical usage rate data includes: Establish charging pile nodes containing the location coordinates of charging piles and berth nodes containing the spatial coordinates of berths; Based on the charging pile location topology data, a fixed connection edge is established between the charging pile node and the berth node; The real-time vehicle location data is converted into dynamic vehicle nodes with timestamps, and the location coordinates of the dynamic vehicle nodes are updated in real time. Based on the historical usage data of the charging piles, the real-time load factor of each charging pile node is calculated; Based on the spatial proximity relationship between the updated position coordinates of the dynamic vehicle node and the spatial coordinates of the berth node, a temporary connection edge is established between the dynamic vehicle node and the berth node. Using the real-time load coefficient of the charging pile node, the temporary connection edge is weighted to obtain a temporary connection edge with connection weight. A dynamic matching graph for charging piles, parking spaces, and vehicles is constructed by integrating charging pile nodes with real-time load coefficients, parking space nodes, dynamic vehicle nodes, fixed connection edges, and temporary connection edges with connection weights.

6. The method according to claim 1, characterized in that, The step of performing multi-sensor data fusion processing on the vehicle contour point cloud data and the parking trajectory image data to identify the vehicle charging port location and optimal parking posture includes: The vehicle contour point cloud data is used to perform three-dimensional structure reconstruction to generate a three-dimensional model of the vehicle surface. Motion trajectory extraction is performed on the parking trajectory image data to obtain a vehicle pose change sequence; The three-dimensional model of the vehicle surface and the vehicle pose change sequence are input into a multimodal fusion neural network for spatiotemporal correlation to generate a three-dimensional pose sequence during vehicle motion. In the three-dimensional model of the vehicle surface, the characteristic areas of the charging interface are identified to determine the location of the vehicle charging interface; Based on the three-dimensional posture sequence, the relative positional relationship between the vehicle and the charging pile is analyzed. Based on the relative positional relationship, the target docking posture of the charging interface corresponding to the charging pile socket is calculated using a deep reinforcement learning model. The optimal parking posture is determined based on the location of the vehicle charging port and the target docking posture.

7. The method according to claim 1, characterized in that, Based on the vehicle's charging port location and optimal parking posture, a refined guidance instruction is generated to assist the vehicle in parking the charging station space. This refined guidance instruction is then sent to the user's mobile terminal and the charging station, including: Calculate the horizontal angle and vertical distance between the vehicle charging interface and the charging pile interface, and generate a lateral correction command based on the horizontal angle and the vertical distance; Based on the optimal parking posture, the vehicle's forward direction and rotation angle that need to be adjusted are determined, and longitudinal control commands are generated according to the forward direction and rotation angle. By combining the lateral correction command and the longitudinal control command, a fine guidance command is formed; Based on the precise guidance instructions, visual prompts and device control signals are generated. The visual prompts are sent to the user's mobile terminal for graphical display, and the device control signals are sent to the charging pile to control the charging pile to prepare for charging service.

8. A charging pile service guidance system based on digital twins, characterized in that, include: The data acquisition module is used to collect topology data of charging pile locations, real-time vehicle location data, and historical usage data of charging piles within the target area. The module is used to construct a dynamic matching map of charging pile parking spaces and vehicles based on the charging pile location topology data, the vehicle real-time location data, and the charging pile historical usage rate data, so as to evaluate the availability of charging piles in real time. The generation module is used to generate a charging pile guidance strategy based on the vehicle dynamic matching map of the charging pile parking space and combined with the digital twin model. The charging pile guidance strategy includes the correspondence between available charging piles and vehicles, which is used to allocate charging pile resources. The calculation module is used to calculate the optimal guidance path from the vehicle's current location to the available charging pile based on the vehicle's real-time location data and the available charging pile using a path planning algorithm, and send the optimal guidance path information to the charging pile and the user's mobile terminal respectively to guide the vehicle to the available charging pile. The acquisition module is used to acquire vehicle contour point cloud data and parking trajectory image data when the vehicle drives to the preset range of the charging pile and prepares to park, and to perform multi-sensor data fusion processing on the vehicle contour point cloud data and the parking trajectory image data to identify the vehicle charging interface position and the optimal parking posture. The sending module is used to generate fine guidance instructions based on the location of the vehicle's charging interface and the optimal parking posture to assist the vehicle in parking in the charging pile space, and send the fine guidance instructions to the user's mobile terminal and the charging pile to realize service guidance.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the digital twin-based charging pile service guidance method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, enables the implementation of the digital twin-based charging pile service guidance method as described in any one of claims 1 to 7.

Images