New energy vehicle battery replacement scheduling method, device, electronic equipment and storage medium

Abstract

The embodiment of the present invention provides a battery replacement scheduling method for new energy vehicles. When the power of a target new energy vehicle drops to a preset value, a task node graph corresponding to the target new energy vehicle is obtained, the task node graph includes multiple task nodes, and the first connection edge between two task nodes corresponds to a first weight value; a battery swap station node graph between multiple battery swap stations in a target area is obtained, the battery swap station node graph includes multiple battery swap station nodes, each battery swap station node corresponds to a target battery swap station, and the second connection edge between two battery swap station nodes corresponds to a second weight value; the battery swap strategy of the target new energy vehicle is determined according to the battery swap station node graph and the task node graph. The battery swap strategy is determined by using the battery swap station nodes and the task nodes, and the battery swap station nodes are spatially coupled with the task nodes, fully considering the correlation between each task node and each battery swap station node when the new energy vehicle performs a task, thereby improving the efficiency of battery replacement scheduling deployed in the new energy vehicle.

Description

Technical Field

[0001] The present invention relates to the field of smart transportation technology, and in particular to a method, device, electronic equipment and storage medium for scheduling battery replacement for new energy vehicles. Background Art

[0002] With the popularity of new energy vehicles, more and more traditional gasoline-driven vehicles are being replaced by new energy vehicles. The largest of the existing new energy vehicles is electric vehicles, which use batteries to drive motors to drive the vehicle. Battery swap stations are facilities for replacing batteries for new energy vehicles. Compared with charging new energy vehicles, battery replacement for new energy vehicles through battery swap stations can avoid charging time occupying the driving time of new energy vehicles. The battery swap station will charge the replaced battery, but due to the limited number of batteries in the battery swap station, battery charging also takes a certain amount of time. There may be a situation where new energy vehicles need to wait for batteries, which reduces the transportation efficiency of new energy vehicles and affects the transportation plan of new energy vehicles. Summary of the invention

[0003] The embodiment of the present invention provides a battery replacement scheduling method for new energy vehicles, which aims to solve the problem that existing new energy vehicles may have to wait for batteries when replacing batteries in battery swap stations, reduce the transportation efficiency of new energy vehicles, and affect the transportation plan of new energy vehicles. The battery replacement strategy is determined by the battery swap station node and the task node, and the battery swap station node and the task node are coupled in space, which fully considers the correlation between each task node and each battery swap station node when the new energy vehicle performs the task, thereby improving the efficiency of battery replacement scheduling deployed in the new energy vehicle.

[0004] In a first aspect, an embodiment of the present invention provides a method for scheduling battery replacement for a new energy vehicle, the method comprising:

[0005] When the power of the target new energy vehicle drops to a preset value, a task node graph corresponding to the target new energy vehicle is obtained, wherein the task node graph includes a plurality of task nodes, and a first connecting edge between two task nodes corresponds to a first weight value;

[0006] Obtain a power station node graph between multiple power stations in a target area, wherein the power station node graph includes multiple power station nodes, each of the power station nodes corresponds to one of the target power station, and a second connection edge between two of the power station nodes corresponds to a second weight value;

[0007] The battery replacement strategy of the target new energy vehicle is determined according to the battery replacement station node diagram and the task node diagram.

[0008] Optionally, when the power of the target new energy vehicle drops to a preset value, obtaining a task node diagram corresponding to the target new energy vehicle includes:

[0009] Performing power detection on the target new energy vehicle in real time, and when it is detected that the power of the target new energy vehicle drops to a preset value, obtaining a task route corresponding to the target new energy vehicle;

[0010] Determine a task node diagram corresponding to the target new energy vehicle according to the task route.

[0011] Optionally, determining a task node graph corresponding to the target new energy vehicle according to the task route includes:

[0012] Determine the remaining mission route of the target new energy vehicle according to the mission route;

[0013] Determine a task node diagram corresponding to the target new energy vehicle according to the remaining task route.

[0014] Optionally, determining the task node graph corresponding to the target new energy vehicle according to the remaining task route includes:

[0015] Determine the remaining task nodes according to the remaining task route;

[0016] Based on the task amount between two adjacent remaining task nodes, determining a first weight value between the two adjacent remaining task nodes;

[0017] Determining a directed acyclic graph corresponding to the target new energy vehicle based on the remaining task nodes and the first weight value;

[0018] A task node graph corresponding to the target new energy vehicle is determined based on the directed acyclic graph.

[0019] Optionally, before obtaining a power station node graph between multiple target power stations in a target area, the method further includes:

[0020] Obtaining the mission route corresponding to the target new energy vehicle and obtaining a map of the battery swap station access;

[0021] Determine the mission area according to the mission route;

[0022] The target area is determined according to the task area and the battery swap station access map.

[0023] Optionally, the target battery swap station access map includes location information of each battery swap station and road information between each battery swap station, and the acquiring of a battery swap station node map between multiple battery swap stations in the target area includes:

[0024] Based on the location information of each battery swap station, determining a target battery swap station in the target area;

[0025] Determining a second weight value between each target battery swap station according to road information between each target battery swap station;

[0026] Based on the target battery swap station and the second weight value, a battery swap station node graph between multiple battery swap stations in the target area is determined.

[0027] Optionally, determining the battery swap strategy of the target new energy vehicle according to the battery swap station node graph and the task node graph includes:

[0028] Performing a convolution operation on the battery swap station node graph through a first graph convolutional neural network to obtain a first node feature graph corresponding to the battery swap station node graph;

[0029] Performing a convolution operation on the task node graph through a second graph convolutional neural network to obtain a second node feature graph corresponding to the task node graph;

[0030] The first node feature map and the second node feature map are fused through a feature fusion network to obtain a fused node feature map;

[0031] The fusion node feature graph is subjected to linear regression processing through a linear regression network to obtain the battery replacement strategy of the target new energy vehicle.

[0032] In a second aspect, an embodiment of the present invention further provides a new energy vehicle battery replacement scheduling device, the new energy vehicle battery replacement scheduling device comprising:

[0033] A first acquisition module is used to acquire a task node graph corresponding to the target new energy vehicle when the power of the target new energy vehicle drops to a preset value, wherein the task node graph includes a plurality of task nodes, and a first connecting edge between two task nodes corresponds to a first weight value;

[0034] A second acquisition module is used to obtain a power station node graph between multiple power stations in the target area, wherein the power station node graph includes multiple power station nodes, each of which corresponds to one target power station, and a second connection edge between two power station nodes corresponds to a second weight value;

[0035] The first determination module is used to determine the battery replacement strategy of the target new energy vehicle based on the battery replacement station node diagram and the task node diagram.

[0036] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the new energy vehicle battery replacement scheduling method provided in an embodiment of the present invention are implemented.

[0037] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the new energy vehicle battery replacement scheduling method provided in the embodiment of the invention are implemented.

[0038] In an embodiment of the present invention, when the power of the target new energy vehicle drops to a preset value, a task node graph corresponding to the target new energy vehicle is obtained, the task node graph includes multiple task nodes, and the first connection edge between the two task nodes corresponds to a first weight value; a battery swap station node graph between multiple battery swap stations in the target area is obtained, the battery swap station node graph includes multiple battery swap station nodes, each of the battery swap station nodes corresponds to one of the target battery swap stations, and the second connection edge between the two battery swap station nodes corresponds to a second weight value; the battery swap strategy of the target new energy vehicle is determined according to the battery swap station node graph and the task node graph. The battery swap strategy is determined by the battery swap station nodes and the task nodes, and the battery swap station nodes and the task nodes are spatially coupled, fully considering the correlation between each task node and each battery swap station node when the new energy vehicle performs a task, thereby improving the efficiency of the replacement scheduling of the batteries deployed in the new energy vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 is a flow chart of a new energy vehicle battery replacement scheduling method provided by an embodiment of the present invention;

[0041] Figure 2 It is a structural schematic diagram of a new energy vehicle battery replacement scheduling device provided in an embodiment of the present invention;

[0042] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] like Figure 1As shown, Figure 1 This is a method flow chart of a method for scheduling battery replacement of new energy vehicles provided by an embodiment of the present invention. The method for scheduling battery replacement of new energy vehicles comprises the following steps:

[0045] 101. When the power of the target new energy vehicle drops to a preset value, a task node diagram corresponding to the target new energy vehicle is obtained.

[0046] In an embodiment of the present invention, the above-mentioned new energy battery replacement scheduling method can be deployed in a new energy vehicle scheduling platform. The above-mentioned new energy vehicle scheduling platform can be an electronic device with functions such as data processing, data analysis, image processing, and image generation. Specifically, the above-mentioned new energy vehicle scheduling platform can be a server or server cluster with functions such as data processing, data analysis, image processing, and image generation. The above-mentioned target new energy vehicle can be a vehicle that uses electricity as a driving energy source. The above-mentioned new energy vehicle battery replacement scheduling method can be used for battery replacement scheduling of new energy vehicles in industrial parks or commercial parks.

[0047] Specifically, the target new energy vehicle may be a new energy transport vehicle, which may be used to perform transport tasks within the park. The transport tasks may include personnel transport tasks or goods transport tasks. The target new energy vehicle may be equipped with batteries, battery state sensors (Battery State of Charge Sensors), drive motors and other components. The batteries store electricity, and the drive motors are driven by the electricity to drive the target new energy vehicle to travel. The battery state sensors may detect the amount of electricity stored in the batteries in real time. The target new energy vehicle may be a new energy vehicle that is performing transport tasks within the park.

[0048] Specifically, the battery status sensor may be a current measuring battery status sensor, a voltage measuring battery status sensor, an internal impedance measuring battery status sensor or the like; the preset value may be the battery power storage value; the target new energy vehicle may perform the corresponding task; the task driving route corresponding to the task is determined based on the task and the actual longitude and latitude coordinates of the target new energy vehicle; and the task node diagram is determined based on the task driving route.

[0049] The above-mentioned task nodes include multiple task nodes. In the above-mentioned task nodes, the first connecting edge between two task nodes corresponds to a first weight value. The above-mentioned first connecting edge can be a connecting road between the above-mentioned two task nodes. The above-mentioned first weight value can be determined according to the road conditions corresponding to the connecting road between the above-mentioned two task nodes and the driving distance corresponding to the connecting road between the above-mentioned two task nodes. The above-mentioned road conditions can be determined based on the number of vehicles traveling on the connecting road between the above-mentioned two task nodes, the number of lanes of the connecting road between the above-mentioned two task nodes, the road slope of the connecting road between the above-mentioned two task nodes, the road flatness of the connecting road between the above-mentioned two task nodes, the road damage condition of the connecting road between the above-mentioned two task nodes, the road load-bearing data of the connecting road between the above-mentioned two task nodes and other data.

[0050] For example, when the target new energy vehicle performs the corresponding personnel transportation task, the target new energy vehicle can travel according to the operating route set by the business rules of the personnel transportation task. When the battery status sensor detects that the battery power of the target new energy vehicle is lower than the preset value, the vehicle dispatching platform determines the preset driving route according to the operating route, and determines the driving route node according to the preset driving route. The driving route node can be the starting point of the driving route and the end point of the driving route. The driving route node can also be an intermediate node established in the driving route. The intermediate node can be a stopover point for people to get on and off the vehicle when the target new energy vehicle performs the transportation task. The task node graph is determined based on the driving route nodes. The connecting edges corresponding to the task nodes are determined based on the task node graph, and the first weight value is determined based on the connecting edges.

[0051] When the target new energy vehicle performs a task of transporting goods, the target new energy vehicle may travel according to the transport route set by the business rules of the task of transporting goods; when the battery status sensor detects that the battery power of the new energy transport vehicle is lower than the preset value, the vehicle dispatching platform determines a preset travel route according to the transport route, and determines the travel route nodes according to the preset travel route; the travel route nodes may be the starting point and the end point of the travel route; the travel route nodes may also be intermediate travel route nodes established in the travel route; the intermediate nodes may be stopovers where the target new energy vehicle needs to unload or load part of the goods when traveling from the starting point to the end point of the travel route; the task node diagram is determined based on the travel route nodes.

[0052] 102. Obtain a node diagram of a battery swap station between multiple battery swap stations in a target area.

[0053] In an embodiment of the present invention, the target area may be a designated area within the park, for example, an area corresponding to a transportation task to be performed by the target new energy vehicle.

[0054] The above-mentioned battery swap station node graph includes multiple battery swap station nodes, each battery swap station node corresponds to a target battery swap station, and the second connection edge between the two battery swap station nodes corresponds to the second weight value. The above-mentioned target area can be determined based on the mission driving route corresponding to the above-mentioned target new energy vehicle and the current longitude and latitude coordinate position of the above-mentioned target new energy vehicle. The above-mentioned target area can also be determined based on the mileage of the target new energy vehicle driven by the remaining power of the battery deployed in the above-mentioned target new energy vehicle. The above-mentioned battery swap station can be a place for replacing the battery deployed in the above-mentioned target new energy vehicle. The above-mentioned battery swap station can store batteries, and the above-mentioned batteries can be fully charged batteries or partially charged batteries. The above-mentioned second connection edge can be The connecting road between the two battery swap station nodes may be a connecting road between the two battery swap station nodes. The second weight value may be determined according to the road condition corresponding to the connecting road between the two battery swap station nodes and the driving distance corresponding to the connecting road between the two battery swap station nodes. The road condition may be determined according to the number of vehicles traveling on the connecting road between the two battery swap station nodes, the number of lanes on the connecting road between the two battery swap station nodes, the road slope of the connecting road between the two battery swap station nodes, the road flatness of the connecting road between the two battery swap station nodes, the road damage condition of the connecting road between the two battery swap station nodes, the road load-bearing data of the connecting road between the two battery swap station nodes and other data.

[0055] In a possible embodiment, when the battery status sensor detects that the target new energy vehicle drops to the preset value and obtains the task node diagram corresponding to the target new energy vehicle, the target area is determined based on the current longitude and latitude coordinates of the target new energy vehicle and the task driving route corresponding to the new energy vehicle, and the target area range is determined based on the mileage that the target new energy vehicle can be driven by the remaining power of the battery deployed in the target new energy vehicle.

[0056] For example, if the remaining battery power can drive the target new energy vehicle to travel 20 kilometers, the target area can be determined to be 20 kilometers in radius according to the mileage. In order to avoid the target new energy vehicle being unable to travel 20 kilometers due to errors in the battery status sensor, the target area can also be 15 kilometers. If the remaining battery power can drive the target new energy vehicle to travel 50 kilometers, the target area can be determined to be 50 kilometers in radius according to the mileage. In order to avoid the target new energy vehicle being unable to travel 50 kilometers due to errors in the battery status sensor, the target area can also be 45 kilometers. According to the target area, the longitude and latitude positions of the battery swap station in the target area are determined. Based on the longitude and latitude positions of the battery swap station, the battery swap station node corresponding to the longitude and latitude positions of the battery swap station is determined. Based on the battery swap station node and the target area, the battery swap station node map is determined.

[0057] 103. Determine the battery replacement strategy for the target new energy vehicle based on the battery replacement station node diagram and the task node diagram.

[0058] In an embodiment of the present invention, the battery swap strategy can be based on the battery swap station node diagram and the task node diagram to determine the optimal battery swap station location that the target new energy vehicle can go to and the optimal route required for the optimal battery swap station that the target new energy vehicle can go to. The optimal battery swap station can be determined based on the battery swap station node diagram and the task node diagram to be the optimal battery swap station for the target new energy vehicle to go to for battery swap. The optimal route can be the route from the target new energy vehicle to the optimal battery swap station, the time required is the shortest, the distance required is the shortest, or the driving environment is the most comfortable. Specifically, the battery swap strategy can be to scale the battery swap station node diagram and the task node diagram in equal proportions and combine them to obtain a battery swap strategy diagram, and calculate the battery swap strategy diagram through a trained graph convolutional neural network model to determine the battery swap strategy of the target new energy vehicle. The above calculation can also be performed through Dijkstra algorithm, Bellman-Ford algorithm, Floyd-Warshall algorithm and other algorithms to determine the battery swap strategy of the target new energy vehicle.

[0059] The above-mentioned graph convolutional neural network model can be obtained by obtaining a first data set and a model to be trained, wherein the first data set includes a sample battery swap strategy map and label data corresponding to the sample battery swap strategy map, inputting the sample battery swap strategy map into the model to be trained for processing, performing convolution processing through the convolution layer in the model to be trained to obtain intermediate features, performing linear regression processing on the intermediate features through the output layer of the model to be trained, obtaining the processing result corresponding to the sample battery swap strategy map, calculating the error loss function between the processing result corresponding to the sample battery swap strategy map and the label data corresponding to the sample battery swap strategy map, taking minimizing the error loss function as the optimization goal, adjusting the parameters of the model to be trained through the back propagation algorithm, iterating the parameter adjustment process until the error loss function converges at the minimum, or the number of iterations reaches a preset value, stopping training, and obtaining a trained model. The battery swap strategy map to be processed is input into the trained model for processing to obtain the processing result of the battery swap strategy map to be processed.

[0060] In a possible embodiment, after obtaining the above-mentioned battery swap station node map and the above-mentioned task node map, the above-mentioned vehicle dispatching platform performs proportional scaling and combination processing based on the above-mentioned battery swap station node map and the above-mentioned task node map to obtain the above-mentioned battery swap strategy map, and calculates the above-mentioned battery swap strategy map through the above-mentioned trained convolutional neural network to obtain the processing result of the above-mentioned battery swap strategy map, and determines the battery swap strategy of the above-mentioned target new energy vehicle based on the processing result of the above-mentioned battery swap strategy map.

[0061] In an embodiment of the present invention, when the power of the target new energy vehicle drops to a preset value, a task node graph corresponding to the target new energy vehicle is obtained, the task node graph includes multiple task nodes, the first connection edge between two task nodes corresponds to a first weight value, and a power swap station node graph between multiple power swap stations in the target area is obtained. The power swap station node graph includes multiple power swap station nodes, each power swap station node corresponds to a target power swap station, and the second connection edge between two power swap station nodes corresponds to a second weight value. The power swap strategy of the target new energy vehicle is determined according to the power swap station node graph and the task node graph. The power swap strategy is obtained by performing an implicit relationship between the power swap station node and the task node, and the power swap station node and the task node are spatially coupled, fully considering the correlation between each task node and each power swap station node when the new energy vehicle performs a task, thereby improving the efficiency of the replacement scheduling of the battery deployed in the new energy vehicle.

[0062] Optionally, in the step of obtaining the task node diagram corresponding to the target new energy vehicle when the power of the target new energy vehicle drops to a preset value, the power of the target new energy vehicle can be detected in real time. When it is detected that the power of the target new energy vehicle drops to a preset value, the task route corresponding to the target new energy vehicle is obtained; and the task node diagram corresponding to the target new energy vehicle is determined according to the task route.

[0063] In an embodiment of the present invention, the above-mentioned power detection can perform real-time power detection on the battery deployed in the above-mentioned target new energy vehicle through the above-mentioned battery status sensor. The mission route corresponding to the above-mentioned target new energy vehicle can be an operating route set according to the mission requirements corresponding to the above-mentioned target new energy vehicle. The above-mentioned preset value can be 20% of the power storage percentage of the battery deployed in the above-mentioned target new energy vehicle. When the above-mentioned battery status sensor detects that the power of the battery deployed in the above-mentioned target new energy vehicle is lower than 20%, the above-mentioned power information is uploaded to the above-mentioned vehicle dispatching platform. The above-mentioned vehicle dispatching platform obtains the mission route corresponding to the above-mentioned target new energy vehicle, and determines the task node map of the above-mentioned target new energy vehicle according to the task node corresponding to the mission route of the above-mentioned target new energy vehicle and the task node of the above-mentioned target new energy vehicle.

[0064] Optionally, in the step of determining the task node graph corresponding to the target new energy vehicle according to the task route, the remaining task route of the target new energy vehicle can be determined according to the task route; and the task node graph corresponding to the target new energy vehicle can be determined according to the remaining task route.

[0065] In an embodiment of the present invention, the above-mentioned remaining task route can be determined based on the latitude and longitude coordinate positions corresponding to the above-mentioned task route and the above-mentioned target new energy vehicle. Specifically, when the above-mentioned target new energy vehicle is in a task state, the route that the above-mentioned target new energy vehicle has traveled is determined based on the above-mentioned task route and the latitude and longitude coordinate positions corresponding to the above-mentioned target new energy vehicle. The remaining task route of the above-mentioned target new energy vehicle is subtracted from the task route of the above-mentioned target new energy vehicle to obtain the remaining task route of the above-mentioned target new energy vehicle. The remaining task nodes corresponding to the remaining task route of the above-mentioned target new energy vehicle are determined based on the remaining task route of the above-mentioned target new energy vehicle, and the task node graph corresponding to the above-mentioned target new energy vehicle is determined based on the above-mentioned remaining task nodes.

[0066] Optionally, in the step of determining the task node graph corresponding to the target new energy vehicle according to the remaining task route, the remaining task nodes can be determined according to the remaining task route; based on the task amount between two adjacent remaining task nodes, a first weight value between two adjacent remaining task nodes can be determined; based on the remaining task nodes and the first weight value, a directed acyclic graph corresponding to the target new energy vehicle can be determined; based on the directed acyclic graph, the task node graph corresponding to the target new energy vehicle can be determined.

[0067] In an embodiment of the present invention, the above-mentioned task volume can be determined based on the mileage of the required driving route of the above-mentioned target new energy vehicle, the driving time corresponding to the mileage of the required driving route, and the road conditions of the required driving route of the above-mentioned target new energy vehicle. The above-mentioned directed acyclic graph can be a graph without loops (rings). Based on the upper vertex in the above-mentioned directed acyclic graph corresponding to the starting point of the remaining tasks in the above-mentioned remaining task nodes, the lower vertex in the above-mentioned directed acyclic graph corresponds to the end point of the remaining tasks in the above-mentioned remaining task nodes, and the directed edges in the above-mentioned directed acyclic graph correspond to the above-mentioned first connecting edges and the second connecting edges. The above-mentioned directed acyclic graph is also called AOV network (Activity On Vertex Network).

[0068] Specifically, after the vehicle dispatching platform obtains the task node graph and the battery swap station node graph, the remaining task nodes can be determined according to the remaining task route corresponding to the target new energy vehicle, and the task volume between the two adjacent remaining task nodes can be determined based on the road condition, mileage, and driving time corresponding to the mileage of the route between the two adjacent remaining task nodes; the first weight value between the two adjacent remaining task nodes can be determined based on the task volume between the two remaining task nodes; the upper vertex, lower vertex and directed edge of the directed acyclic graph can be determined based on the remaining task nodes and the first weight value; the directed acyclic graph can be determined based on the upper vertex, lower vertex and directed edge of the directed acyclic graph; and the task node graph corresponding to the target new energy vehicle can be determined based on the directed acyclic graph.

[0069] Optionally, before obtaining the battery swap station node map between multiple target battery swap stations in the target area, you can also obtain the task route corresponding to the target new energy vehicle and the battery swap station access map; determine the task area based on the task route; determine the target area based on the task area and the battery swap station access map.

[0070] In an embodiment of the present invention, the mission route corresponding to the above-mentioned target new energy vehicle can be determined according to the type of the above-mentioned target new energy vehicle, the mission type of the above-mentioned target new energy vehicle can be determined based on the mission type of the above-mentioned target new energy vehicle, and the mission requirement of the above-mentioned target new energy vehicle can be determined based on the mission requirement of the above-mentioned target new energy vehicle. The access map of the above-mentioned battery swap station can be a map of all routes that the above-mentioned target new energy transport vehicle can lead to the above-mentioned battery swap station, and the access map of the above-mentioned battery swap station is determined based on the route map of the above-mentioned battery swap station.

[0071] Specifically, before the step of obtaining the battery swap station node diagram between multiple target battery swap stations in the target area, if the target new energy vehicle is a new energy transport vehicle, the route that the target new energy transport vehicle needs to operate can be determined according to the target new energy transport vehicle, and the task route corresponding to the route that the target new energy transport vehicle needs to operate is determined based on the target new energy transport vehicle. For example, the center point of the task area is determined based on the center point of the task route corresponding to the target new energy transport vehicle in the actual longitude and latitude coordinates, the left boundary of the task area and the right boundary of the task area are determined based on the left vertex and the right vertex of the task route in the actual longitude and latitude coordinates, the area range of the task area is determined based on the left boundary of the task area and the right boundary of the task area, the task area is determined based on the area range and the center point of the task area, and the target area is determined according to the task area and the path diagram through which the target new energy transport vehicle can lead to the battery swap station.

[0072] Optionally, in the step of obtaining a battery swap station node map between multiple battery swap stations in a target area, in which the target battery swap station access map includes the location information of each battery swap station and the road information between each battery swap station, the target battery swap station can be determined in the target area based on the location information of each battery swap station; the second weight value between each target battery swap station can be determined based on the road information between each target battery swap station; and the battery swap station node map between multiple battery swap stations in the target area can be determined based on the target battery swap station and the second weight value.

[0073] In an embodiment of the present invention, the above-mentioned target battery swap station route map may include location information of each battery swap station and road information between the above-mentioned battery swap stations. The above-mentioned location information may be coordinate location information of the above-mentioned battery swap station in actual longitude and latitude coordinates. The above-mentioned road information may be road conditions between the above-mentioned battery swap stations. The above-mentioned road conditions may be the degree of road damage between the above-mentioned battery swap stations, the flatness of the roads between the above-mentioned battery swap stations, the number of lanes information between the above-mentioned battery swap stations, and the driving vehicle data on the roads between the above-mentioned battery swap stations. The above-mentioned road conditions may be obtained according to the above-mentioned vehicle dispatching platform.

[0074] The above-mentioned vehicle dispatching platform can connect to satellites to take high-altitude images to obtain the road conditions between the above-mentioned battery swap stations, and determine the road information between the above-mentioned target battery swap stations based on the road conditions between the above-mentioned battery swap stations, determine the second weight value between the above-mentioned target battery swap stations based on the road information between the above-mentioned target battery swap stations, and determine the battery swap station node map between multiple battery swap stations in the above-mentioned target area based on the above-mentioned target battery swap stations and the above-mentioned second weight value.

[0075] Optionally, in the step of determining the battery swap strategy of the target new energy vehicle based on the battery swap station node graph and the task node graph, the battery swap station node graph can also be convolved through a first graph convolutional neural network to obtain a first node feature graph corresponding to the battery swap station node graph; the task node graph can be convolved through a second graph convolutional neural network to obtain a second node feature graph corresponding to the task node graph; the first node feature graph and the second node feature graph can be fused through a feature fusion network to obtain a fused node feature graph; the fused node feature graph can be linearly regressed through a linear regression network to obtain the battery swap strategy of the target new energy vehicle.

[0076] In an embodiment of the present invention, the battery swap strategy of the target new energy vehicle is obtained by performing graph convolution processing and linear regression on the node graph of the battery swap station and the task node graph through the trained battery swap strategy model. Specifically, the battery swap strategy model includes a first graph convolutional neural network, a second graph convolutional neural network, a feature fusion network, and a linear regression network, wherein the first graph convolutional neural network and the second graph convolutional neural network are in a parallel relationship, and the outputs of the first graph convolutional neural network and the second graph convolutional neural network are respectively connected to the input of the feature fusion network, and the output of the feature fusion network is connected to the output of the linear regression network.

[0077] The battery swap station node graph is input into the first graph convolutional neural network in the battery swap strategy model for convolution operation to obtain a first node feature graph; at the same time, the task node graph is input into the second graph convolutional neural network in the battery swap strategy model for convolution operation to obtain a second node feature graph; the first node feature graph and the second node feature graph are simultaneously input into the feature fusion network in the battery swap strategy model for fusion processing to obtain a fused node feature graph; the fused node feature graph is input into the linear regression network in the battery swap strategy model for linear regression processing to obtain the battery swap strategy for new energy vehicles.

[0078] The above-mentioned first graph convolutional neural network can be obtained by obtaining a first data set, a second data set and a model to be trained, wherein the first data set includes a sample task node graph and label data corresponding to the sample task node graph, and the above-mentioned label data is a manually annotated battery swap strategy, and the second data set includes a sample battery swap station node graph and label data corresponding to the sample battery swap station node graph, and the sample task node graph and the sample battery swap station node graph are input into the model to be trained for processing, and the above-mentioned first node feature graph and the above-mentioned second node feature graph are obtained by convolution processing through the convolution layer in the model to be trained, and the above-mentioned first node feature graph and the above-mentioned second node feature graph are fused through the output layer of the model to be trained to obtain the above-mentioned fused node feature graph, and the above-mentioned fused node feature graph is linearly regressed to obtain the processing result corresponding to the fused node feature graph, and the error loss function between the processing result corresponding to the fused node feature graph and the label data corresponding to the fused node feature graph is calculated, and the error loss function is minimized as the optimization goal, and the parameters of the model to be trained are adjusted by the back propagation algorithm, and the parameter adjustment process is iterated until the error loss function converges at the minimum, or the number of iterations reaches a preset value, and the training is stopped to obtain a trained model.

[0079] The node graph of the battery swap station to be processed and the task node graph are input into the trained model for processing to obtain the processing results of the node graph of the battery swap station to be processed and the task node graph, and the battery swap strategy of the target new energy vehicle is determined based on the above processing results.

[0080] It should be noted that the new energy vehicle battery replacement scheduling method provided in the embodiment of the present invention can be applied to photographing equipment, smart phones, computers, servers and other devices that can perform new energy vehicle battery replacement scheduling.

[0081] like Figure 2 As shown, an embodiment of the present invention provides a battery replacement scheduling device for a new energy vehicle, and the battery replacement scheduling device for a new energy vehicle includes:

[0082] A first acquisition module 201 is used to acquire a task node graph corresponding to the target new energy vehicle when the power of the target new energy vehicle drops to a preset value, wherein the task node graph includes a plurality of task nodes, and a first connection edge between two task nodes corresponds to a first weight value;

[0083] The second acquisition module 202 is used to obtain a power station node graph between multiple power stations in the target area, wherein the power station node graph includes multiple power station nodes, each of which corresponds to one target power station, and the second connection edge between two power station nodes corresponds to a second weight value;

[0084] The first determination module 203 is used to determine the battery replacement strategy of the target new energy vehicle according to the battery replacement station node diagram and the task node diagram.

[0085] Optionally, the first acquisition module 201 includes:

[0086] A real-time detection module is used to detect the power level of the target new energy vehicle in real time, and when it is detected that the power level of the target new energy vehicle drops to a preset value, obtain the task route corresponding to the target new energy vehicle;

[0087] The second determination module is used to determine the task node diagram corresponding to the target new energy vehicle according to the task route.

[0088] Optionally, the second determining module includes:

[0089] A third determination submodule is used to determine the remaining mission route of the target new energy vehicle according to the mission route;

[0090] The fourth determination submodule is used to determine the task node diagram corresponding to the target new energy vehicle according to the remaining task route.

[0091] Optionally, the fourth determining submodule includes:

[0092] A first determining subunit, configured to determine remaining task nodes according to the remaining task route;

[0093] A second determining subunit, configured to determine a first weight value between two adjacent remaining task nodes based on the amount of tasks between the two adjacent remaining task nodes;

[0094] A third determining subunit, based on the remaining task nodes and the first weight value, determines a directed acyclic graph corresponding to the target new energy vehicle;

[0095] The fourth determination subunit determines a task node graph corresponding to the target new energy vehicle based on the directed acyclic graph.

[0096] Optionally, the second acquisition module 202 further includes:

[0097] The first acquisition submodule is used to acquire the mission route corresponding to the target new energy vehicle and acquire the access map of the battery swap station;

[0098] A fifth determination submodule, used to determine the task area according to the task route;

[0099] The sixth determination submodule is used to determine the target area according to the task area and the battery swap station access map.

[0100] Optionally, the sixth determining submodule includes:

[0101] A fifth determining subunit, configured to determine a target battery swap station in the target area based on the location information of each battery swap station;

[0102] A sixth determining subunit, determining a second weight value between each target battery swap station according to road information between each target battery swap station;

[0103] A seventh determination subunit determines a battery swap station node graph between multiple battery swap stations in the target area based on the target battery swap station and the second weight value.

[0104] Optionally, the first determining module 203 includes:

[0105] A first convolution submodule, configured to perform a convolution operation on the battery swap station node graph through a first graph convolutional neural network to obtain a first node feature graph corresponding to the battery swap station node graph;

[0106] A second convolution submodule, used to perform a convolution operation on the task node graph through a second graph convolutional neural network to obtain a second node feature graph corresponding to the task node graph;

[0107] A first fusion submodule, configured to fuse the first node feature map with the second node feature map through a feature fusion network to obtain a fused node feature map;

[0108] The first linear regression processing submodule is used to perform linear regression processing on the fusion node feature map through a linear regression network to obtain the battery replacement strategy of the target new energy vehicle.

[0109] It should be noted that the new energy vehicle battery replacement scheduling device provided in the embodiment of the present invention can be applied to photographing equipment, smart phones, computers, servers and other equipment that can perform new energy vehicle battery replacement scheduling.

[0110] The new energy vehicle battery replacement scheduling device provided in the embodiment of the present invention can implement each process implemented by the new energy vehicle battery replacement scheduling method in the above method embodiment, and can achieve the same beneficial effects. To avoid repetition, it will not be repeated here.

[0111] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program of a new energy vehicle battery replacement scheduling method stored in the memory 302 and executable on the processor 301, wherein:

[0112] The processor 301 is used to call the computer program stored in the memory 302 and execute the following steps:

[0113] When the power of the target new energy vehicle drops to a preset value, a task node graph corresponding to the target new energy vehicle is obtained, wherein the task node graph includes a plurality of task nodes, and a first connecting edge between two task nodes corresponds to a first weight value;

[0114] Obtain a power station node graph between multiple power stations in a target area, wherein the power station node graph includes multiple power station nodes, each of the power station nodes corresponds to one of the target power station, and a second connection edge between two of the power station nodes corresponds to a second weight value;

[0115] The battery replacement strategy of the target new energy vehicle is determined according to the battery replacement station node diagram and the task node diagram.

[0116] Optionally, when the power of the target new energy vehicle drops to a preset value, the processor 301 executes the step of obtaining a task node diagram corresponding to the target new energy vehicle, including:

[0117] Performing power detection on the target new energy vehicle in real time, and when it is detected that the power of the target new energy vehicle drops to a preset value, obtaining a task route corresponding to the target new energy vehicle;

[0118] Determine a task node diagram corresponding to the target new energy vehicle according to the task route.

[0119] Optionally, the determining of the task node graph corresponding to the target new energy vehicle according to the task route performed by the processor 301 includes:

[0120] Determine the remaining mission route of the target new energy vehicle according to the mission route;

[0121] Determine a task node diagram corresponding to the target new energy vehicle according to the remaining task route.

[0122] Optionally, the determining of the task node graph corresponding to the target new energy vehicle according to the remaining task route performed by the processor 301 includes:

[0123] Determine the remaining task nodes according to the remaining task route;

[0124] Based on the task amount between two adjacent remaining task nodes, determining a first weight value between the two adjacent remaining task nodes;

[0125] Determining a directed acyclic graph corresponding to the target new energy vehicle based on the remaining task nodes and the first weight value;

[0126] A task node graph corresponding to the target new energy vehicle is determined based on the directed acyclic graph.

[0127] Optionally, before acquiring the power station node graph between multiple target power station in the target area, the method executed by the processor 301 further includes:

[0128] Obtaining the mission route corresponding to the target new energy vehicle and obtaining a map of the battery swap station access;

[0129] Determine the mission area according to the mission route;

[0130] The target area is determined according to the task area and the battery swap station access map.

[0131] Optionally, the target battery swap station access map executed by the processor 301 includes location information of each battery swap station and road information between each battery swap station, and the acquiring of a battery swap station node map between multiple battery swap stations in the target area includes:

[0132] Based on the location information of each battery swap station, determining a target battery swap station in the target area;

[0133] Determining a second weight value between each target battery swap station according to road information between each target battery swap station;

[0134] Based on the target battery swap station and the second weight value, a battery swap station node graph between multiple battery swap stations in the target area is determined.

[0135] Optionally, the processor 301 determines the battery swap strategy of the target new energy vehicle according to the battery swap station node diagram and the task node diagram, including:

[0136] Performing a convolution operation on the battery swap station node graph through a first graph convolutional neural network to obtain a first node feature graph corresponding to the battery swap station node graph;

[0137] Performing a convolution operation on the task node graph through a second graph convolutional neural network to obtain a second node feature graph corresponding to the task node graph;

[0138] The first node feature map and the second node feature map are fused through a feature fusion network to obtain a fused node feature map;

[0139] The fusion node feature graph is subjected to linear regression processing through a linear regression network to obtain the battery replacement strategy of the target new energy vehicle.

[0140] It should be noted that the electronic device provided in the embodiment of the present invention can be applied to smart phones, computers, servers and other devices that can perform the new energy vehicle battery replacement scheduling method.

[0141] The electronic device provided in the embodiment of the present invention can implement each process implemented by the new energy vehicle battery replacement scheduling method in the above method embodiment, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0142] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the new energy vehicle battery replacement scheduling method or the application-side new energy vehicle battery replacement scheduling method provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0143] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0144] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for scheduling battery replacement for new energy vehicles, characterized in that: The method comprises the following steps: When the power of the target new energy vehicle drops to a preset value, a task node graph corresponding to the target new energy vehicle is obtained, wherein the task node graph includes a plurality of task nodes, and a first connecting edge between two of the task nodes corresponds to a first weight value; Obtaining a mission route corresponding to the target new energy vehicle and obtaining a map of the power swap station access; determining a mission area according to the mission route; and determining a target area according to the mission area and the power swap station access map; Obtain a power station node graph between multiple power stations in a target area, wherein the power station node graph includes multiple power station nodes, each of the power station nodes corresponds to one power station, and a second connection edge between two of the power station nodes corresponds to a second weight value; A convolution operation is performed on the battery swap station node graph through a first graph convolutional neural network to obtain a first node feature graph corresponding to the battery swap station node graph; a convolution operation is performed on the task node graph through a second graph convolutional neural network to obtain a second node feature graph corresponding to the task node graph; the first node feature graph and the second node feature graph are fused through a feature fusion network to obtain a fused node feature graph; a linear regression network is used to perform linear regression on the fused node feature graph to obtain the battery swap strategy of the target new energy vehicle.

2. The new energy vehicle battery replacement scheduling method according to claim 1, characterized in that: When the power of the target new energy vehicle drops to a preset value, obtaining a task node diagram corresponding to the target new energy vehicle includes: Performing power detection on the target new energy vehicle in real time, and when it is detected that the power of the target new energy vehicle drops to a preset value, obtaining a task route corresponding to the target new energy vehicle; Determine a task node diagram corresponding to the target new energy vehicle according to the task route.

3. The new energy vehicle battery replacement scheduling method according to claim 2, characterized in that: The step of determining the task node graph corresponding to the target new energy vehicle according to the task route includes: Determine the remaining mission route of the target new energy vehicle according to the mission route; Determine a task node diagram corresponding to the target new energy vehicle according to the remaining task route.

4. The new energy vehicle battery replacement scheduling method according to claim 3, characterized in that: The step of determining the task node graph corresponding to the target new energy vehicle according to the remaining task route includes: Determine the remaining task nodes according to the remaining task route; Based on the task amount between two adjacent remaining task nodes, determining a first weight value between the two adjacent remaining task nodes; Determining a directed acyclic graph corresponding to the target new energy vehicle based on the remaining task nodes and the first weight value; A task node graph corresponding to the target new energy vehicle is determined based on the directed acyclic graph.

5. The new energy vehicle battery replacement scheduling method according to claim 1, characterized in that: The battery swap station access map includes the location information of each battery swap station and the road information between each battery swap station. The acquiring of the battery swap station node map between multiple battery swap stations in the target area includes: Based on the location information of each battery swap station, determining a target battery swap station in the target area; Determining a second weight value between each target battery swap station according to road information between each target battery swap station; Based on the target battery swap station and the second weight value, a battery swap station node graph between multiple battery swap stations in the target area is determined.

6. A battery replacement scheduling device for new energy vehicles, characterized in that: The new energy vehicle battery replacement scheduling device comprises: A first acquisition module is used to acquire a task node graph corresponding to the target new energy vehicle when the power of the target new energy vehicle drops to a preset value, wherein the task node graph includes a plurality of task nodes, and a first connecting edge between two of the task nodes corresponds to a first weight value; The second acquisition module is used to obtain the task route corresponding to the target new energy vehicle and the access map of the power swap station; determine the task area according to the task route; determine the target area according to the task area and the access map of the power swap station; obtain the power swap station node map between multiple power swap stations in the target area, the power swap station node map includes multiple power swap station nodes, each of the power swap station nodes corresponds to one power swap station, and the second connection edge between the two power swap station nodes corresponds to the second weight value; The first determination module is used to perform a convolution operation on the battery swap station node graph through a first graph convolutional neural network to obtain a first node feature graph corresponding to the battery swap station node graph; perform a convolution operation on the task node graph through a second graph convolutional neural network to obtain a second node feature graph corresponding to the task node graph; fuse the first node feature graph with the second node feature graph through a feature fusion network to obtain a fused node feature graph; perform linear regression processing on the fused node feature graph through a linear regression network to obtain the battery swap strategy of the target new energy vehicle.

7. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the new energy vehicle battery replacement scheduling method as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the new energy vehicle battery replacement scheduling method as described in any one of claims 1 to 5 are implemented.

Images