Task scheduling method and system for server

Abstract

The invention provides a task scheduling method and system for a server, relates to the technical field of computers, and solves the problem of navigation errors of transportation hubs. The management server receives a map matching service request uploaded by the vehicle end, and determines a driving road section in the map matching service request by analyzing the position information; the management server determines a vehicle driving-in road set and driving-in roads in the vehicle driving-in road set according to the driving road section; the management server calculates a matched optimal edge server when the vehicle drives into the ramp according to the position and the driving route of the vehicle; the management server sends the local map generation request to an optimal edge server matched when the vehicle drives into the ramp; and the edge server generates a local map and sends the local map to the vehicle end.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a task scheduling method and system for a server. Background Art

[0002] The Internet of Vehicles (IoV) uses vehicle-to-vehicle communication technology, wireless communication, and remote sensing technology, etc., with the help of vehicles, roadside equipment, edge servers, base stations, and cloud servers, etc., to sense the vehicle's surrounding environment in real time, collect road and vehicle data, and obtain a series of traffic information such as real-time road conditions, road information, and pedestrian information; and combines with the Global Positioning System (GPS) navigation technology for system analysis and calculation, plans the vehicle's driving route, and makes decision analysis based on the real-time road conditions, so that the driver can timely detect driving deviations and perceive potential risks in advance, thereby greatly improving the driving comfort and safety.

[0003] Among them, the navigation system for assisted driving relies on multiple technologies to provide real-time navigation guidance for users, remind users to maintain the optimal driving route, and deviate from the planned driving route, etc. However, in hub areas, there are usually areas such as viaducts, dense ramps, or tunnels, and there are often problems with the navigation system misreporting that the vehicle has deviated from the route. When the road conditions are complex, misreporting that the vehicle has deviated from the route may lead to unknown driving safety. Summary of the Invention

[0004] In view of the above-mentioned shortcomings of the related technologies, this application provides a task scheduling method and system for a server to solve the above technical problems.

[0005] In a first aspect, a task scheduling method for a server provided by this application includes: The management server receives a map matching service request uploaded from the vehicle end, and determines the driving section in the map matching service request by parsing the location information; The management server determines the set of roads the vehicle enters and the entered roads therein according to the driving section; The management server calculates the best edge server to be matched when the vehicle enters the ramp according to the vehicle position and driving route; The management server sends a local map generation request to the best edge server to be matched when the vehicle enters the ramp; The edge server generates a local map and sends it to the vehicle end.

[0006] In an embodiment of this application, the method further includes: The user inputs driving requirement data such as the destination through the vehicle end, and the vehicle end generates a route request based on the driving requirement data and uploads it to the management server; The management server receives the route request from the vehicle end, generates multiple candidate routes, and sends them to the vehicle end; The vehicle end displays candidate routes, determines the candidate route selected by the user as the planned driving route in response to the user's selection instruction, and uploads the selection information to the management server; The management server generates the planned driving route locally and stores the planned driving route.

[0007] In an embodiment of the present application, the management server calculates the best edge server that matches when the vehicle enters the ramp according to the vehicle position and the driving route, including: Receiving the resource status periodically uploaded by the edge server and calculating the load of the edge server; Selecting the edge server with the minimum load as the best edge server that matches when the vehicle enters the ramp.

[0008] In an embodiment of the present application, the method further includes: The best edge server publishes a task offloading broadcast to multiple candidate edge servers in the network; Multiple candidate edge servers in the network respond to the offloading broadcast and report the estimated latency of locally calculating the local map generation task; The best edge server selects the candidate edge server with the minimum estimated latency and offloads the local map generation request.

[0009] In an embodiment of the present application, the edge server generates a local map and sends it to the vehicle end, including: Sensing the real-time road status through roadside devices and updating the topological connection relationship between the ramp and the main road according to the vehicle driving route; Generating a local map according to the updated topological relationship and real-time status.

[0010] In an embodiment of the present application, the real-time road status includes the real-time positioning points of the road; sensing the real-time road status through roadside devices includes: The best edge server sends the local map to the vehicle end and the management server; The management server calculates the time it takes for the vehicle to drive from the current lane to the entered road, and estimates the arrival time of the vehicle at each section according to the positions of the edge servers on the local map and the vehicle end speed; The management server sends a positioning point collection instruction to the corresponding edge server according to the arrival time; The edge server responds to the positioning point collection instruction and controls the roadside device to collect positioning points.

[0011] In an embodiment of the present application, after generating the local map according to the updated topological relationship and real-time status, the method further includes: Adding the positioning point information of the roadside device on the local map and generating a driving route guidance on the local map.

[0012] In a second aspect, the task scheduling system for a server provided by the present application includes: A management server, an edge server, and roadside equipment; the management server, the edge server, and the roadside equipment are respectively communicatively connected to the vehicle terminal; The management server is configured to receive a map matching service request uploaded by the vehicle terminal, determine the driving section in the map matching service request by parsing the location information, calculate the best edge server to be matched when the vehicle enters the ramp, and send a local map generation request to the best edge server to be matched when the vehicle enters the ramp; The roadside equipment is configured to collect positioning points to the edge server; The edge server is configured to generate a local map and send it to the vehicle terminal, and add positioning point information to the local map to generate a driving route guidance on the local map.

[0013] As described above, a method and system for detecting malicious nodes in an autonomous driving network provided by the present application have the following beneficial effects: In the above process, the driving route added to the generated local map is formed by the positioning points collected by the roadside equipment, and the GNSS receiver of the roadside equipment also receives real-time positioning points (GPS or Beidou signals). Therefore, even if the positioning points "drift", the positioning point drift of the roadside equipment is the same as that of the vehicle. The driving route guidance generated according to the "drifted" positioning points can provide route guidance in the same state for the vehicle terminal, thereby eliminating the deviation of the route comparison result caused by the inaccurate real-time position of the vehicle terminal due to the "drift" of the positioning points.

[0014] At the same time, the local map integrates the obstacle information of the road, and the local route guidance is more accurate and can avoid the occlusion of obstacles.

[0015] When the vehicle terminal receives the local map, it compares the real-time position point with the route guidance of the local map. The comparison results are all based on the same perspective, time, and state, so the comparison results are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings: Figure 1 is a schematic diagram of an application scenario of a task scheduling method for a server; Figure 2 is a flowchart of the steps of a task scheduling method for a server proposed by the present invention. Detailed implementation manners

[0017] The following will describe the implementation manners of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for explaining the present application, rather than for limiting the protection scope of the present application.

[0018] It should be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present application. Therefore, only the components related to the present application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, number, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0019] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0020] High-speed road hub areas usually have viaducts, dense ramps or tunnels. GPS signals may be blocked or reflected (multipath effect), resulting in the positioning point "drifting" onto the main road or other roads. Even if the vehicle has actually entered the ramp, the GPS coordinates may be briefly displayed on the main road track, thus causing a deviation in the navigation comparison route. On the other hand, in some map data, the topological relationship (such as connection points, number of lanes) between the ramp and the main road may not be updated in time, or the lane-level accuracy is insufficient. The "driving path" preset by the navigation has a deviation from the actual road geometry, or some hubs are specially designed (such as continuous bifurcations, spiral ramps), which are inconsistent with the "simplified path" preset by the navigation, resulting in the problem that the navigation system falsely reports that the vehicle has deviated from the route.

[0021] To solve the above problems, a task scheduling method for a server is proposed. In this embodiment, taking the application scenario architecture of the task scheduling method for a server shown in the figure as an example, the operation process of the task scheduling method for a server is specifically explained. The task scheduling method for a server is applied to a vehicle networking device cluster set at a highway hub where multiple roads converge or a dense ramp intersection. The vehicle networking device cluster includes roadside devices, edge servers, and management servers; the management server is generally a cloud server within the region, and the edge servers form a server cluster, interacting with roadside devices, vehicle terminals, and management servers to process computing tasks; the vehicle terminal can interact with both the management server and the edge server to process corresponding computing tasks. The specific interaction lines are determined after selecting and matching servers according to the computing tasks.

[0022] The communication technologies adopted by vehicle networking roadside devices mainly include Cellular Vehicle-to-Everything (C-V2X), Wi-Fi, DSRC (Dedicated Short Range Communications), etc. The present invention does not limit the specific networking form.

[0023] Figure 2 It is the flowchart of the steps of the task scheduling method for a server proposed by the present invention. The processing request from the vehicle terminal is a computing task that needs to be scheduled by the management server in the application scenario architecture shown as Figure 1 shown. As shown in Figure 2 shown, the steps include: S1: The management server receives the map matching service request uploaded by the vehicle terminal and determines the driving section in the map matching service request by parsing the location information.

[0024] The vehicle terminal can be an On-Board Unit (OBU) installed in the vehicle or a mobile terminal of a passenger in the vehicle. The vehicle terminal can transmit real-time data (such as location, speed, vehicle status) to the management server and the edge server and receive roadside information (such as traffic signal status, traffic warning, etc.) sent by the edge server.

[0025] During the vehicle's driving process, satellite broadcast signals (including satellite position, timestamp, etc.) are sent. The vehicle terminal calls the GPS module or Beidou module to receive position points, compares the planned driving route generated by the system with the position points to determine whether the vehicle is driving along the planned driving route and the corresponding relationship between the current position and the planned driving route; when the vehicle terminal calculates that the current driving position is close to the target ramp or hub position in the planned driving route, it sends a map matching service request to the management server.

[0026] There may be multiple ramp or hub positions in the planned driving route. The target ramp or the target hub position refers to the ramp that the vehicle needs to change lanes to enter or a certain lane in the hub that the vehicle needs to enter, and the driving road is changed through this lane.

[0027] The roadside communication device (RoadSide Unit, RSU) adopted by the present invention integrates LTE-V2X communication technology, supports protocol conversion of data, provides an all-round and low-latency connection ability between the road and vehicles, the road and people, and the road and the cloud platform, and realizes real-time communication between the edge server and the vehicle end through the RSU; and the RSU supports roadside traffic infrastructure data (for example, traditional intelligent transportation facilities, new intelligent roadside perception devices, roadside edge computing units, etc. are all traffic infrastructure); and the RSU is docked with various traditional intelligent transportation facilities (such as traffic lights, cameras, microwave detectors, variable message signs, etc.) to enable traditional intelligent transportation facilities to access the vehicle network, and can access new traffic information sources such as ground differential and meteorological services based on the edge computing architecture, and provide all-round roadside intelligent network connection services covering driving safety, efficiency, information services, etc.

[0028] Before executing S1, the system will also execute the following steps: S01: The user inputs driving demand data such as the destination through the vehicle end, and the vehicle end generates a route request based on the driving demand data and uploads it to the management server.

[0029] S02: The management server receives the route request from the vehicle end, generates multiple candidate routes, and sends them to the vehicle end.

[0030] S03: The vehicle end displays the candidate routes, determines the candidate route selected by the user as the planned driving route in response to the user's selection instruction, and uploads the selection information to the management server.

[0031] S04: The management server generates a planned driving route locally and stores the planned driving route.

[0032] The management server can also store the code of the vehicle end corresponding to the planned driving route.

[0033] During driving, when the vehicle end detects that the distance between the driving position and the target ramp is within the preset range, it uploads a map matching service request to the management server. The map matching service request includes the vehicle code and the vehicle position. Therefore, the management server can compare the position information and find the corresponding transportation hub or ramp that the vehicle should enter based on the current driving section, that is, the set of roads to enter.

[0034] Since there may be multiple lanes or ramps in the transportation hub, and there is only one lane that the vehicle needs to enter in the planned driving route, the set of roads to enter is used to represent the transportation hub or ramp that the vehicle is about to enter.

[0035] S2: The management server determines the set of roads for the vehicle to enter and the roads to enter therein according to the driving section.

[0036] The incoming road is the designated road that conforms to the driving route in the transportation hub where the vehicle is about to enter.

[0037] S3: The management server calculates the optimal edge server to be matched when the vehicle enters the ramp based on the vehicle position and driving route.

[0038] Since the management server stores the planned driving route, based on the positioning points uploaded by the vehicle terminal, the positional relationship between the current vehicle position and the transportation hub or ramp can be estimated, that is, the time when the vehicle is about to enter the transportation hub or ramp can be predicted.

[0039] Based on the vehicle position and driving route, it can be estimated that the vehicle takes time T to drive from the currently driving lane to the incoming road after operations such as lane change and deceleration. Select the idle edge server among the edge servers on the incoming road side and send the local map generation request to the idle edge server.

[0040] For example, if there are three lanes on the current road and the vehicle is driving in the leftmost lane, the cloud server estimates the time T for the vehicle to change lanes to the rightmost lane and then enter the ramp, and then based on the current computing tasks of the edge server, estimates the edge server that will be idle after time T.

[0041] During the process of processing tasks, the edge server maintains a task queue and synchronizes the task queue to the management server regularly. The task queue includes tasks to be processed, tasks in progress, and completed tasks; and regularly sends task metadata to the management server. The task metadata can include: task ID, task type (e.g., video analysis, data sensor processing, local map generation, etc.), task submission time, priority, and other data. The management server estimates whether the edge server will be idle after time T based on the task submission time, so as to determine the idle edge server.

[0042] S4: The management server sends the local map generation request to the optimal edge server to be matched when the vehicle enters the ramp.

[0043] In the case of heavy traffic, it is possible that all edge servers are processing tasks and there is no idle edge server. Therefore, the management server can perform the specific operations of S3 below to select a more appropriate one among the edge servers.

[0044] S3 includes the following sub-steps: S31: Receive the resource status periodically uploaded by the edge server. The resource status includes CPU utilization rate, RAM memory occupancy, and GPU utilization rate.

[0045] For example, the edge server sends JSON data {"cpu": 65%, "ram": "8GB / 16GB"} through HTTP POST.

[0046] S32: Calculate the load P of the edge server; P = CPU1 + RAM1 + GPU1, , , are the resource ratios of CPU, RAM, and GPU respectively called when executing the task of generating the local map. This coefficient is obtained through experiments. CPU1, RAM1, and GPU1 respectively correspond to the utilization rates of CPU, RAM, and GPU in sequence.

[0047] S33: Select the edge server with the minimum load as the best edge server matched when the vehicle enters the ramp.

[0048] During the specific execution process, the edge server may receive other tasks sent from the vehicle end or the server at any time. Therefore, the further solution of the present invention: After the management server selects the best edge server, perform task offloading according to the actual situation; if the best edge server receives other tasks, for example, the sensors of a moving vehicle detect an obstacle ahead and request the edge server to generate an obstacle avoidance path, or the vehicle airbag is triggered and decelerates suddenly, and requests the edge server to report the vehicle position, vehicle status, etc., the best edge server needs to give priority to executing the urgent other tasks. At this time, through the following method, the best edge server schedules the task of generating the local map to other edge servers.

[0049] The edge servers on the road that the vehicle enters are connected to form a network, and the edge servers in the network can migrate tasks to other edge servers.

[0050] S001: The best edge server broadcasts a task offloading message to multiple candidate edge servers in the network.

[0051] Task offloading includes the calculation requirements and maximum delay corresponding to generating the local path; the maximum delay is obtained according to the time T and the time t consumed after the best edge server receives the management server.

[0052] S002: Multiple candidate edge servers in the network respond to the offloading broadcast and report the estimated delay of calculating the local map generation task locally.

[0053] The estimated delay is determined by the existing tasks and computing resources of the candidate edge servers. For example, the existing tasks of the candidate edge server , , , and the task of generating the local map is used as , and according to the task priority for , , , Arrange and calculate cumulatively The calculation time of previous tasks and the time taken to execute according to local computing resources is only related to . Assume sorting by priority > > > , = Calculation time + Calculation + Calculation time, and report to the optimal edge server.

[0054] S003: The optimal edge server selects the candidate edge server with the minimum estimated latency and offloads the local map generation request.

[0055] The optimal edge server offloads the local map generation request to the candidate edge server with the minimum estimated latency.

[0056] S5: The edge server generates a local map and sends it to the vehicle terminal.

[0057] According to the technical solution described in this embodiment, the local map can be generated by the optimal edge server, or by the candidate edge server selected by the optimal edge server according to the estimated latency.

[0058] During the process of the edge server generating the local map, the following operations are performed: K11: Sense the real-time road status through roadside devices.

[0059] The real-time road status includes whether there are obstacles occupying the lane and the real-time position of the lane.

[0060] The real-time road status also includes the real-time positioning points of the road, the position information of the roadside devices, and the position information of the edge server. The roadside devices are installed with GNSS receivers, which are devices for receiving, tracking, processing, and measuring Global Navigation Satellite System (GNSS) signals. The GNSS receivers receive satellite broadcast signals, which are the positioning points of the roadside devices.

[0061] The set of positioning points collected by the roadside devices installed on the road side can form the real-time positioning information of the road.

[0062] The edge server sends instructions for collecting positioning points to each roadside device, and the roadside devices periodically collect positioning points and transmit them to the edge server.

[0063] In order to further ensure that the positioning points collected by the roadside devices and the positioning points collected by the vehicle terminal are collected under the same conditions, the present invention also proposes the following method for collecting positioning points: Based on the vehicle's location and driving route, the management server can estimate the time T it takes for the vehicle to travel from the current driving lane to the incoming road after operations such as lane change and deceleration, select an idle edge server among the edge servers on the incoming road side, send a local map generation request to the idle edge server, and further estimate the time for the vehicle to pass through different road sections based on the speed of the vehicle after entering the ramp, and notify the roadside devices corresponding to different road sections to collect positioning points according to this time.

[0064] K11 includes the process: K111: The optimal edge server sends the local map to the vehicle terminal and the management server.

[0065] K112: The management server calculates the time T it takes for the vehicle to travel from the current driving lane to the incoming road, and estimates the arrival time of the vehicle at each road section based on the positions of the edge servers on the local map and the vehicle terminal speed.

[0066] Assume that edge server 1 is responsible for information processing of road section 1, edge server 2 is responsible for information processing of road section 2, and edge server 3 is responsible for information processing of road section 3. Road sections 1, 2, and 3 are connected end to end to form the entire road for the vehicle to enter main road 2 from main road 1 through the ramp. The management server calculates T + t1 for the vehicle to pass through road section 1, T + t2 for the vehicle to pass through road section 1, and T + t3 for the vehicle to pass through road section 1; a scheduler is established to trigger step S113 in sequence according to the timestamps of T + t1, T + t2, and T + t3.

[0067] K113: The management server sends a positioning point collection instruction to the corresponding edge server according to the arrival time.

[0068] K114: The edge server responds to the positioning point collection instruction and controls the roadside device to collect positioning points.

[0069] Continuing with the above example, the management server sends a positioning point collection instruction to edge server 1 at T + t1, and edge server 1 responds to the instruction to notify the roadside device set on road section 1 and connected locally to collect positioning points; the management server sends a positioning point collection instruction to edge server 2 at T + t2, and edge server 1 responds to the instruction to notify the roadside device set on road section 2 and connected locally to collect positioning points, and so on.

[0070] K12: Update the lane topology connection relationship. Since the vehicle's driving route is determined, the topology relationship of the ramp and the main road can be updated according to the vehicle's driving route. The main road includes the road where the vehicle exits, the road where the vehicle enters, and other ramps that the vehicle passes through from the exit road to the incoming road.

[0071] Based on the updated lane topology connection relationship, the edge server obtains the accurate turning angles, offsets, etc. of the local road, eliminating the deviation of the line comparison result caused by the deviation between the "driving route" preset by the navigation and the actual road geometry.

[0072] K13: Generate a local map based on the updated topology relationship and real-time status; Furthermore, local route guidance can also be added to the local map.

[0073] In one example, the edge server can, based on the static high-precision map, determine the accurate angle of road turning according to the updated topology relationship, generate a local map, add the positioning point information of roadside devices above the local map, and generate a driving route guidance on the local map.

[0074] Adding positioning point information above the local map can be completed by the optimal edge server that generates the local map or the candidate edge server with the minimum estimated delay; in another case, after the optimal edge server generates the local map, edge servers at different locations call roadside devices to collect positioning points according to the timestamp triggered by the management server, add them to the local map, and then send the driving route guidance to the vehicle terminal in real time, and the vehicle terminal updates during driving.

[0075] Since the GNSS receiver of the roadside device also receives real-time positioning points (GPS or Beidou signals), even if there is "drift" of the positioning points, the drift of the positioning points of the roadside device and the "drift" of the positioning points of the vehicle are also consistent. The driving route guidance generated according to the "drifted" positioning points can provide route guidance in the same state for the vehicle terminal, thus eliminating the deviation of the line comparison result caused by the inaccurate real-time position of the vehicle terminal due to the "drift" of the positioning points.

[0076] At the same time, the local map integrates the obstacle information of the road, and the local route guidance is more accurate and can avoid the occlusion of obstacles.

[0077] The vehicle terminal receives the local map and compares the real-time position point with the route guidance of the local map. The comparison results are all based on the same perspective, time, and status, so the comparison results are more accurate.

[0078] The present invention also provides a task scheduling system for a server, which is constructed based on the vehicle network architecture and includes: a management server, an edge server, and roadside devices; the management server, the edge server, and the roadside devices are respectively communicatively connected to the vehicle terminal; The management server is used to receive the map matching service request uploaded by the vehicle terminal, determine the driving section in the map matching service request by parsing the location information, calculate the best edge server to be matched when the vehicle enters the ramp, and send the local map generation request to the best edge server to be matched when the vehicle enters the ramp; The roadside device is used to collect the positioning points to the edge server; The edge server is used to generate the local map and send it to the vehicle terminal, and add the positioning point information to the local map to generate the driving route guidance in the local map.

[0079] Another aspect of the present application also provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the task scheduling method for the server provided in each of the above embodiments.

[0080] In the embodiments of the present application, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. The terms "comprising" and "including" mentioned throughout the specification and claims are open-ended terms and should be interpreted as "including but not limited to".

[0081] The above embodiments only exemplarily illustrate the principles and effects of the present application and are not used to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present application should still be covered by the claims of the present application.

Claims

1. A task scheduling method for a server, characterized in that, A task scheduling system applied to the construction of vehicle networking, including: The management server receives the map matching service request uploaded by the vehicle terminal, and determines the driving section in the map matching service request by parsing the location information; The management server determines the set of roads that the vehicle enters, and the entered roads therein, according to the driving section; The management server calculates the best edge server matched when the vehicle enters the ramp, according to the vehicle position and driving route; The management server sends the local map generation request to the best edge server matched when the vehicle enters the ramp; The edge server generates a local map and sends it to the vehicle terminal.

2. The method according to claim 1, wherein The method further includes: The user inputs driving requirement data such as the destination through the vehicle terminal, and the vehicle terminal generates a route request based on the driving requirement data and uploads it to the management server; The management server receives the route request from the vehicle terminal, generates multiple candidate routes and sends them to the vehicle terminal; The vehicle terminal displays the candidate routes, determines the candidate route selected by the user as the planned driving route in response to the user's selection instruction, and uploads the selection information to the management server; The management server generates a planned driving route locally and stores the planned driving route.

3. The method according to claim 1, wherein The management server calculates the best edge server matched when the vehicle enters the ramp, according to the vehicle position and driving route, including: Receiving the resource status periodically uploaded by the edge server, and calculating the load of the edge server; Selecting the edge server with the minimum load as the best edge server matched when the vehicle enters the ramp.

4. The method according to claim 3, characterized in that The method further includes: The best edge server publishes a task offloading broadcast to multiple candidate edge servers in the network; Multiple candidate edge servers in the network respond to the offloading broadcast and report the estimated delay of locally calculating the local map generation task; The best edge server selects the candidate edge server with the minimum estimated delay and offloads the local map generation request.

5. The method according to claim 1, characterized in that, The edge server generates a local map and sends it to the vehicle terminal, including: Sensing the real-time status of the road through roadside equipment, and updating the topological connection relationship between the ramp and the main road according to the vehicle driving route; Generating a local map according to the updated topological relationship and real-time status.

6. The method according to claim 5, wherein The real-time road status includes the real-time positioning points of the road; Sensing the real-time status of the road through roadside equipment, including: The best edge server sends the local map to the vehicle terminal and the management server; The management server calculates the time it takes for the vehicle to drive from the currently driving lane to the entered road, and estimates the arrival time of the vehicle at each section according to the positions of each edge server on the local map and the vehicle terminal speed; The management server sends the positioning point collection instruction to the corresponding edge server according to the arrival time; The edge server responds to the positioning point collection instruction and controls the roadside equipment to collect positioning points.

7. The method according to claim 5, characterized in that, After generating the local map according to the updated topological relationship and real-time status, the method further includes: Adding the positioning point information of the roadside equipment on the local map, and generating a driving route guide on the local map.

8. A task scheduling system for a server, characterized in that, A task scheduling system for a server includes: A management server, an edge server, and roadside equipment; the management server, the edge server, and the roadside equipment are respectively communicatively connected to the vehicle terminal; The management server is used to receive the map matching service request uploaded by the vehicle terminal, determine the driving section in the map matching service request by parsing the location information, calculate the best edge server to be matched when the vehicle enters the ramp, and send the local map generation request to the best edge server to be matched when the vehicle enters the ramp; The roadside device is used to collect the positioning points to the edge server; The edge server is used to generate a local map and send it to the vehicle terminal, and add positioning point information to the local map to generate a driving route guide in the local map.

Images