EUHT base station optimization method based on automatic driving vehicle network connection information

Abstract

The invention provides an EUHT base station optimization method based on automatic driving vehicle network connection information. The method comprises the following steps: acquiring network connection state data of an automatic driving vehicle; wherein the network connection state data comprises a network connection type; when the network connection types of the autonomous vehicle at two continuous time points are different, determining that a network switching event is generated, and recording network switching information of the network switching event; generating a network switching time sequence diagram in combination with the network switching information and the driving track data of the autonomous vehicle; generating a network switching thermodynamic diagram based on the network switching sequence diagram, and identifying a network coverage optimization area in the network switching thermodynamic diagram; the EUHT base station optimization deployment decision is generated by combining the driving frequency of the automatic driving vehicle in the network coverage optimization area, the network coverage problem can be dynamically identified, and the EUHT network signal weak area can be more accurately and quickly positioned.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving wireless network communication, and in particular to an EUHT base station optimization method based on network connection information of autonomous driving vehicles. Background Art

[0002] The communication transmission of autonomous driving vehicles mainly relies on two network connection methods, namely cellular networks and Enhanced Ultra High Throughput (EUHT) wireless communication technology, to achieve high-frequency and high-density data transmission. With its characteristics of high bandwidth and low latency, EUHT technology can effectively improve network transmission efficiency and data transmission stability, and reduce the traffic cost generated by cellular network data transmission. At present, EUHT technology has been officially put into use in the scenario of autonomous driving demonstration areas.

[0003] However, in the actual scenario of autonomous driving demonstration areas, there are still some defects in EUHT technology. Defect 1: Uneven network coverage leads to poor communication stability. The deployment of EUHT base stations is usually based on static models or preset rules (such as uniform interval layout), which cannot adapt to the data transmission scenarios of autonomous driving vehicles in dynamic scenarios, such as terrain occlusion and resource preemption in high-density areas of autonomous driving vehicles. When an autonomous driving vehicle enters an area without EUHT signal coverage, it needs to switch to the cellular network, which may lead to short-term communication interruption, instruction delay, or even control failure. Defect 2: Lack of means for optimizing deployment points. Traditional base station deployment and optimization schemes lack the analysis of the actual running trajectories and network switching behaviors of autonomous driving vehicles. Existing technologies mostly guide the deployment of EUHT base stations through simulated test signal strength or theoretical coverage models. For example, relying on roadside signal detector devices to collect data or locating signal blind spots through manual inspections. The above methods have the problems of too low efficiency and inability to respond in real time to the dynamic changes in the network connection status of autonomous driving vehicles. Summary of the Invention

[0004] The present invention provides an EUHT base station optimization method based on network connection information of autonomous driving vehicles to solve the technical problem in the prior art that it is impossible to accurately and quickly locate weak areas of EUHT network signals.

[0005] On the one hand, the present invention provides an EUHT base station optimization method based on network connection information of autonomous driving vehicles, including: Obtaining network connection status data of autonomous driving vehicles; wherein, the network connection status data includes network connection types; When the network connection types of the autonomous driving vehicle are different at two consecutive time points, determining that a network switching event occurs and recording the network switching information of the network switching event; Combine the network switching information with the driving trajectory data of the autonomous vehicle to generate a network switching timing diagram; Generate a network switching heat map based on the network switching timing diagram, and identify the network coverage optimization area in the network switching heat map; Combine the driving frequency of the autonomous vehicle in the network coverage optimization area to generate an EUHT base station optimization deployment decision.

[0006] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, the combining the network switching information with the driving trajectory data of the autonomous vehicle to generate a network switching timing diagram includes: Combine the network switching information and the driving trajectory data to extract the geographical location information of the vehicle when each network switching event occurs; Record the occurrence time, geographical location information and the corresponding network connection type of each network switching event in the network switching event list; Generate a network switching timing diagram based on the network switching event list in chronological order.

[0007] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, the generating a network switching heat map based on the network switching timing diagram includes: Evenly divide the geographical area covered by the driving trajectory of the autonomous vehicle into multiple polygon areas; According to the network switching timing diagram, count the occurrence times of network switching events in each polygon area; Calculate the network switching density of each polygon area according to the occurrence times; Generate a network switching heat map according to the network switching density; Overlay the network switching heat map on the map through a map visualization tool.

[0008] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, the identifying the network coverage optimization area in the network switching heat map includes: Analyze the vehicle trajectory areas where EUHT to cellular mobile network and cellular mobile network to EUHT network switching occur during the driving of the autonomous vehicle; Take the vehicle trajectory area passed through when switching back to the EUHT network after switching from the EUHT network to the cellular mobile network as the EUHT uncovered trajectory area; Generate a network coverage optimization area based on the superposition of the EUHT uncovered trajectory areas of multiple autonomous vehicles; Identify the position of the network coverage optimization area in the network handover heat map of each polygon area.

[0009] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, the generating of the EUHT base station optimization deployment decision in combination with the driving frequency of the autonomous vehicle in the network coverage optimization area includes: Count the driving frequency of the autonomous vehicle in each polygon in the network coverage optimization area; Rank the base station construction priorities of each polygon area according to the driving frequency; Select the target polygon area according to the priority ranking; Generate the optimization deployment decision of the EUHT base station in the target polygon area.

[0010] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, the generating of the network coverage optimization area based on the superposition of the EUHT uncovered trajectory areas of multiple autonomous vehicles includes: Extract the spatio-temporal features of the EUHT uncovered trajectory area of each autonomous vehicle; wherein, the spatio-temporal features include duration, trajectory length and trajectory density; Based on the spatio-temporal features, perform cluster analysis on each EUHT uncovered trajectory area to identify network coverage optimization areas with similar spatio-temporal features.

[0011] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, the performing of cluster analysis on each EUHT uncovered trajectory area based on the spatio-temporal features to identify network coverage optimization areas with similar spatio-temporal features includes: Divide the areas with similar spatio-temporal features in the spatio-temporal features of each EUHT uncovered trajectory area into the same cluster; For each cluster, calculate the average value of its spatio-temporal features; wherein, the average value includes the average uncovered trajectory duration, the average trajectory length and the average trajectory density; Evaluate the network coverage optimization priority of each cluster according to the average value of the spatio-temporal features; Select the area corresponding to the cluster with a priority higher than the preset level as the network coverage optimization area.

[0012] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, the identifying of the network coverage optimization area in the network handover heat map further includes: Identify the high-frequency handover area in the network handover heat map where the network handover density is higher than the preset density threshold; Take the high-frequency handover area as the network coverage optimization area.

[0013] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, after identifying the high-frequency handover area in the network handover heat map where the network handover density is higher than the preset density threshold, it further includes: Obtain the driving speed data of autonomous vehicles in the high-frequency handover area; Filter out the high-speed areas in the high-frequency handover area where the driving speed data is greater than the preset speed threshold; The step of taking the high-frequency handover area as the network coverage optimization area includes: Take the high-speed area as the network coverage optimization area.

[0014] According to an EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, the step of identifying the high-frequency handover area in the network handover heat map where the network handover density is higher than the preset density threshold includes: Based on the network handover heat map, determine the area set where the network handover density is higher than the preset density threshold; For each area in the area set, calculate the fluctuation coefficient of its network handover density; Filter out the areas where the fluctuation coefficient is less than the preset fluctuation coefficient threshold.

[0015] For the EUHT base station optimization method based on the network connection information of autonomous vehicles provided by the present invention, when the network connection types of autonomous vehicles are different at two consecutive time points, it is determined that a network handover event occurs, and the network handover information of the network handover event is recorded; combining the network handover information with the driving trajectory data of autonomous vehicles to generate a network handover time series diagram; based on the network handover time series diagram, generating a network handover heat map, and identifying the network coverage optimization area in the network handover heat map; combining the driving frequency of autonomous vehicles in the network coverage optimization area to generate an EUHT base station optimization deployment decision. This embodiment is based on the actual vehicle network connection status, is more in line with the actual road operation situation, can dynamically identify network coverage problems, can more accurately and quickly locate the weak areas of the EUHT network signal, and can save a large amount of manual test costs and optimization deployment costs. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a schematic flowchart of the EUHT base station optimization method based on the network connection information of autonomous driving vehicles provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of the EUHT base station optimization device based on the network connection information of autonomous driving vehicles provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0018] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Figure 1 It is a schematic flowchart of the EUHT base station optimization method based on the network connection information of autonomous driving vehicles provided by an embodiment of the present invention.

[0020] See Figure 1 , the EUHT base station optimization method based on the network connection information of autonomous driving vehicles may include the following steps 101 to 105.

[0021] Step 101: Obtain the network connection status data of the autonomous driving vehicle; wherein, the network connection status data includes the network connection type.

[0022] In this step, the network connection status data of the autonomous driving vehicle can be obtained through an on-vehicle communication module (OBU), a vehicle monitoring system or a network infrastructure. The network connection type generally may include a cellular network and an ultra-high-speed wireless communication. In addition to the network connection type, the network connection status data may further include data transmission rate, network latency, connection duration, geographical location information, timestamp, network handover frequency, vehicle driving speed, and vehicle identification information, etc.

[0023] Step 102: When the network connection types of the autonomous driving vehicle at two consecutive time points are different, determine that a network handover event occurs, and record the network handover information of the network handover event.

[0024] In this step, the network connection type of the autonomous vehicle can be detected once every preset time period. For example, if the network connection type detected at the first time point is ultra-high-speed wireless communication and the network connection type detected at the second time point is cellular network, it is determined that a network switching event has occurred. The network switching information generally includes the occurrence time, the occurrence location (latitude and longitude of the autonomous vehicle), the network switching type (such as switching from EUHT to cellular network, or from cellular network to EUHT), etc.

[0025] Step 103: Combine the network switching information with the driving trajectory data of the autonomous vehicle to generate a network switching time series diagram.

[0026] Step 103 specifically may include: Combine the network switching information and the driving trajectory data to extract the geographical location information of the vehicle when each network switching event occurs; Record the occurrence time, geographical location information, and the corresponding network connection type (such as switching from EUHT to cellular network, or from cellular network to EUHT) of each network switching event into the network switching event list; Based on the network switching event list, generate a network switching time series diagram in chronological order.

[0027] In step 103, the driving trajectory data can be understood as the position of the autonomous vehicle at each time point. The network switching information (such as the occurrence time and the network switching type) can be associated with the driving trajectory data of the vehicle, and the latitude and longitude coordinates of the vehicle when each network switching event occurs can be extracted as the geographical location information. For example, the occurrence time can be matched with the time points in the driving trajectory data to obtain the geographical location information. The network switching event list can be created in advance.

[0028] Step 104: Based on the network switching time series diagram, generate a network switching heat map and identify the network coverage optimization area in the network switching heat map.

[0029] Specifically, generating a network switching heat map based on the network switching time series diagram may include: Step 1: Uniformly divide the geographical area covered by the driving trajectory of the autonomous vehicle into multiple polygon areas; In this step, the geographical area is divided into multiple small areas to more finely count and analyze the distribution of network switching events. A polygon can generally be understood as a regular polygon or a centrally symmetric figure, such as a square, an equilateral triangle, and a regular hexagon, etc. Generally, a regular hexagon can be preferably selected because a regular hexagon has a high space utilization rate and a low boundary error when covering the geographical area. It can be default that the side length of the regular hexagon is 10 meters, but it can be adjusted according to actual needs; Step 2: According to the network switching timing diagram, count the occurrence times of network switching events in each polygon area; In this step, each network switching event in the network switching timing diagram can be traversed to determine its geographical location where it occurs. Each network switching event is classified into the corresponding polygon area, and the number of network switching events in each polygon area is counted to obtain the occurrence times. Step 3: Calculate the network switching density of each polygon area according to the occurrence times; In this step, the number of network switching events in each polygon area can be divided by the area of the area to obtain the network switching density. The network switching density can reflect the network coverage stability in this area; Step 4: Generate a network switching heat map according to the network switching density; In this step, the network switching density can be visualized in the form of a heat map to intuitively display the weak areas of network coverage. Usually, color gradients are used to represent the network switching density. For example, red represents high density and green represents low density. Through the heat map, the weak areas of network coverage can be intuitively seen, providing intuitive visual support for the optimized deployment of base stations; Step 5: Overlay the network switching heat map on the map through a map visualization tool; In this step, a map visualization tool (such as a GIS system) can be used to overlay the network switching heat map on the actual geographical map; Step 105: Combine the driving frequencies of autonomous vehicles in the network coverage optimization area to generate an optimized deployment decision for EUHT base stations.

[0030] In this embodiment, when the network connection types of autonomous vehicles are different at two consecutive time points, it is determined that a network switching event occurs, and the network switching information of the network switching event is recorded; combining the network switching information with the driving trajectory data of the autonomous vehicle to generate a network switching timing diagram; based on the network switching timing diagram, generating a network switching heat map and identifying the network coverage optimization area in the network switching heat map; combining the driving frequencies of autonomous vehicles in the network coverage optimization area to generate an optimized deployment decision for EUHT base stations. This embodiment is based on the actual vehicle network connection status, more in line with the actual road operation situation, can dynamically identify network coverage problems, can more accurately and quickly locate the weak areas of EUHT network signals, and can save a large amount of manual testing costs and optimized deployment costs.

[0031] In an embodiment of this specification, identifying the network coverage optimization area in the network switching heat map may include: Analyze the vehicle trajectory areas where EUHT to cellular mobile network and cellular mobile network to EUHT network switching occur during the driving process of autonomous vehicles; After switching the EUHT network to the cellular mobile network, the vehicle trajectory area passed through when switching back to the EUHT network again is used as the EUHT uncovered trajectory area; Based on the superposition of the EUHT uncovered trajectory areas of multiple autonomous vehicles, a network coverage optimization area is generated; Identify the position of the network coverage optimization area in the network switching heat map of each polygon area.

[0032] In this embodiment, by analyzing the network switching trajectories of autonomous vehicles, identifying the weak areas of EUHT network signals, and generating a network coverage optimization area, it is possible to accurately identify the weak areas of network coverage, provide intuitive visual support, improve the reliability of optimization decisions, and improve the efficiency of network coverage optimization.

[0033] In an embodiment of this specification, in combination with the driving frequency of autonomous vehicles in the network coverage optimization area, an EUHT base station optimization deployment decision is generated, including: Count the driving frequencies of autonomous vehicles in each polygon in the network coverage optimization area; According to the driving frequencies, sort the polygon areas in terms of the priority of base station construction; According to the priority sorting, select the target polygon areas; Generate an optimization deployment decision for EUHT base stations within the target polygon areas.

[0034] In this embodiment, by counting the driving frequencies of vehicles, it is possible to identify which areas are "hot" areas where vehicles frequently pass, and these areas have a higher demand for network coverage. Areas with high frequencies have a higher priority, indicating that these areas have a more urgent demand for network coverage. Multiple target areas can be selected for optimization according to actual needs and resource conditions. For example, select the top 10% of the polygon areas as the target polygon areas in the order of arrangement. The optimization deployment decision can include parameters such as the specific locations, quantities, and powers of the base stations. This embodiment can improve the scientificity and rationality of base station deployment, enhance the efficiency of network coverage optimization, strengthen the stability and reliability of network coverage, and save resources and costs.

[0035] In an embodiment of this specification, the generating of the network coverage optimization area based on the superposition of the EUHT uncovered trajectory areas of multiple autonomous vehicles includes: Extract the spatio-temporal features of the EUHT uncovered trajectory area of each autonomous vehicle; wherein, the spatio-temporal features include duration, trajectory length, and trajectory density; Based on the spatio-temporal features, perform cluster analysis on each EUHT uncovered trajectory area to identify network coverage optimization areas with similar spatio-temporal features.

[0036] In this embodiment, "similar spatio-temporal characteristics" refer to the comprehensive performance of the time and space characteristics of vehicles in areas not covered by EUHT. Through cluster analysis, areas with similar spatio-temporal characteristics can be grouped into one category, thereby identifying network coverage areas that need to be optimized. Specifically, the similar spatio-temporal characteristics include: similar duration: the residence times of multiple vehicles in a certain area are similar; similar trajectory length: the driving distances of multiple vehicles in a certain area are similar; similar trajectory density: the activity frequencies of multiple vehicles in a certain area are similar; similar trajectory distribution: the trajectory distribution patterns of multiple vehicles in a certain area are similar. This embodiment can more accurately locate the areas that need to be optimized.

[0037] Suppose in a certain autonomous driving demonstration area, the EUHT uncovered trajectory areas of multiple vehicles are as follows: Vehicle A, duration: 10 minutes; trajectory length: 10 kilometers; trajectory density: 10 trajectory points per minute; Vehicle B, duration: 12 minutes; trajectory length: 12 kilometers; trajectory density: 11 trajectory points per minute; Vehicle C, duration: 2 minutes; trajectory length: 2 kilometers; trajectory density: 2 trajectory points per minute.

[0038] Through cluster analysis, the trajectory areas of Vehicle A and Vehicle B have similar spatio-temporal characteristics (long duration, long trajectory length, high trajectory density) and can be grouped into the same cluster. The trajectory area of Vehicle C has different spatio-temporal characteristics and can be grouped into another cluster. Therefore, the trajectory areas of Vehicle A and Vehicle B can be identified as network coverage areas that need to be optimized preferentially.

[0039] In an embodiment of this specification, based on spatio-temporal characteristics, cluster analysis is performed on each EUHT uncovered trajectory area to identify network coverage optimization areas with similar spatio-temporal characteristics, including: Step 1: Divide areas with similar spatio-temporal characteristics in the spatio-temporal characteristics of each EUHT uncovered trajectory area into the same cluster; In this step, a clustering algorithm (such as K-means, DBSCAN, etc.) can be used to analyze the extracted spatio-temporal characteristics and divide areas with similar spatio-temporal characteristics into the same cluster; Step 2: For each cluster, calculate the average value of its spatio-temporal characteristics; among them, the average value includes the average uncovered trajectory duration, average trajectory length, and average trajectory density; Step 3: Evaluate the network coverage optimization priority of each cluster according to the average value of the spatio-temporal characteristics; For example, clusters with long duration, long trajectory length, and high trajectory density have higher priority, indicating that the need for network coverage in these areas is more urgent; Step 4: Select the area corresponding to the clustering cluster with a priority higher than the preset level as the network coverage optimization area.

[0040] In this embodiment, it is assumed that in a certain autonomous driving demonstration area, two clustering clusters are obtained through clustering analysis, and each clustering cluster contains multiple EUHT uncovered trajectory areas. The calculated representative spatio-temporal features are as follows: Clustering cluster 1: Average uncovered trajectory duration: 10 minutes; average trajectory length: 10 kilometers; average trajectory density: 10 trajectory points / minute; Clustering cluster 2: Average uncovered trajectory duration: 2 minutes; average trajectory length: 2 kilometers; average trajectory density: 2 trajectory points / minute; The average value of the spatio-temporal features of clustering cluster 1 indicates that the vehicles in this area have a long stay time, a long driving distance, and frequent activities, so the priority is higher and the base station optimization needs to be carried out first.

[0041] In an embodiment of this specification, identifying the network coverage optimization area in the network handover heat map further includes: Identifying the high-frequency handover area in the network handover heat map where the network handover density is higher than the preset density threshold; Taking the high-frequency handover area as the network coverage optimization area.

[0042] In this embodiment, by identifying the high-frequency handover area and concentrating resources to optimize these areas, the overall efficiency of network coverage optimization is improved and resource waste is reduced.

[0043] In an embodiment of this specification, after identifying the high-frequency handover area in the network handover heat map where the network handover density is higher than the preset density threshold, it further includes: Obtaining the driving speed data of autonomous vehicles in the high-frequency handover area; Screening the high-speed areas in the high-frequency handover area where the driving speed data is greater than the preset speed threshold; Taking the high-frequency handover area as the network coverage optimization area includes: Taking the high-speed area as the network coverage optimization area.

[0044] In this embodiment, not only can the network coverage weak areas be accurately identified, but also the selection of the optimization area can be ensured to be more in line with the actual traffic operation situation, especially for the network coverage requirements in the high-speed driving scenario.

[0045] In an embodiment of this specification, identifying the high-frequency handover area in the network handover heat map where the network handover density is higher than the preset density threshold includes: Based on the network handover heat map, determining the area set where the network handover density is higher than the preset density threshold; For each area in the area set, calculate the fluctuation coefficient of its network handover density; Filter out the areas where the fluctuation coefficient is less than the preset fluctuation coefficient threshold.

[0046] In this embodiment, by introducing the index of the fluctuation coefficient, the areas with relatively small fluctuations in network handover density are filtered out as the key points for optimization. This can not only accurately identify the weak areas of network coverage, but also ensure that the selection of the optimized areas is more stable and reliable, avoiding misjudgment caused by short-term fluctuations. The preset density threshold can be set, and no specific limitation is made here. The preset fluctuation coefficient threshold can be set, and no specific limitation is made here.

[0047] The coefficient of variation (CV) is a statistic used to measure the dispersion or variability of data. The average value of the network handover density and the standard deviation of the network handover density can be calculated. The coefficient of variation is the ratio of the standard deviation to the average value, usually expressed as a percentage.

[0048] Based on the same general inventive concept, the present invention also protects an EUHT base station optimization device based on the network connection information of autonomous driving vehicles, as Figure 2 shown Figure 2 FIG. is a schematic structural diagram of an EUHT base station optimization device based on the network connection information of autonomous driving vehicles provided by an embodiment of the present invention. The EUHT base station optimization device based on the network connection information of autonomous driving vehicles provided by the present invention will be described below. The EUHT base station optimization device based on the network connection information of autonomous driving vehicles described below can be correspondingly referred to the EUHT base station optimization method based on the network connection information of autonomous driving vehicles described above.

[0049] The EUHT base station optimization device based on the network connection information of autonomous driving vehicles includes an acquisition module 201, a network handover event module 202, a handover timing diagram module 203, a handover heat map module 204, and a base station optimization module 205.

[0050] The acquisition module 201 is used to acquire the network connection status data of the autonomous driving vehicle; wherein, the network connection status data includes the network connection type; The network handover event module 202 is used to determine that a network handover event occurs when the network connection types of the autonomous driving vehicle at two consecutive time points are different, and record the network handover information of the network handover event; The handover timing diagram module 203 is used to generate a network handover timing diagram by combining the network handover information with the driving trajectory data of the autonomous driving vehicle; The switching heat map module 204 is configured to generate a network switching heat map based on the network switching timing diagram and identify network coverage optimization areas in the network switching heat map; The base station optimization module 205 is configured to generate an EUHT base station optimization deployment decision in combination with the driving frequency of the autonomous vehicle in the network coverage optimization area.

[0051] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0052] As Figure 3 shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute the EUHT base station optimization method based on the network connection information of the autonomous vehicle.

[0053] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0054] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the EUHT base station optimization method provided by the above-mentioned various methods based on the network connection information of the autonomous vehicle.

[0055] On yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the EUHT base station optimization method provided by the above-mentioned various methods based on the network connection information of the autonomous vehicle.

[0056] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0057] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An EUHT base station optimization method based on the network connection information of autonomous vehicles, characterized in that Including: Obtain the network connection status data of the autonomous vehicle; wherein, the network connection status data includes the network connection type; When the network connection types of the autonomous vehicle are different at two consecutive time points, determine that a network switching event occurs, and record the network switching information of the network switching event; Combine the network switching information with the driving trajectory data of the autonomous vehicle to generate a network switching timing diagram; Based on the network switching timing diagram, generate a network switching heat map, and identify the network coverage optimization area in the network switching heat map; Combine the driving frequency of the autonomous vehicle in the network coverage optimization area to generate an EUHT base station optimization deployment decision.

2. The EUHT base station optimization method based on the network connection information of the autonomous vehicle according to claim 1, wherein The combining the network switching information with the driving trajectory data of the autonomous vehicle to generate a network switching timing diagram includes: Combine the network switching information and the driving trajectory data to extract the geographical location information of the vehicle when each network switching event occurs; Record the occurrence time, geographical location information and the corresponding network connection type of each network switching event into the network switching event list; Based on the network switching event list, generate a network switching timing diagram in chronological order.

3. The EUHT base station optimization method based on the network connection information of an autonomous vehicle according to claim 1, wherein The generating a network switching heat map based on the network switching timing diagram includes: Evenly divide the geographical area covered by the driving trajectory of the autonomous vehicle into multiple polygon areas; According to the network switching timing diagram, count the occurrence times of network switching events in each polygon area; According to the occurrence times, calculate the network switching density of each polygon area; Generate a network switching heat map according to the network switching density; Through a map visualization tool, overlay the network switching heat map on the map.

4. The EUHT base station optimization method based on the network connection information of an autonomous vehicle according to claim 3, wherein, The identifying the network coverage optimization area in the network switching heat map includes: Analyze the vehicle trajectory areas where EUHT to cellular mobile network and cellular mobile network to EUHT network switching occur during the driving process of the autonomous vehicle; After switching from the EUHT network to the cellular mobile network, the vehicle trajectory area passed through when switching back to the EUHT network again is used as the EUHT uncovered trajectory area; Based on the overlay of the EUHT uncovered trajectory areas of multiple autonomous vehicles, generate a network coverage optimization area; Identify the position of the network coverage optimization area in the network switching heat map of each polygon area.

5. The EUHT base station optimization method based on the network connection information of an autonomous vehicle according to claim 4, wherein The combining the driving frequency of the autonomous vehicle in the network coverage optimization area to generate an EUHT base station optimization deployment decision includes: Count the driving frequencies of the autonomous vehicle in each polygon in the network coverage optimization area; According to the driving frequencies, sort the base station construction priorities of each polygon area; According to the priority sorting, select the target polygon area; Generate an optimization deployment decision for the EUHT base station in the target polygon area.

6. The EUHT base station optimization method based on the network connection information of an autonomous vehicle according to claim 4, wherein The generating a network coverage optimization area based on the overlay of the EUHT uncovered trajectory areas of multiple autonomous vehicles includes: Extract the spatio-temporal features of the EUHT uncovered trajectory area of each autonomous vehicle; wherein, the spatio-temporal features include duration, trajectory length and trajectory density; Based on the spatio-temporal characteristics, perform clustering analysis on each EUHT uncovered trajectory area to identify network coverage optimization areas with similar spatio-temporal characteristics.

7. The EUHT base station optimization method based on the network connection information of autonomous vehicles according to claim 6, wherein The performing clustering analysis on each EUHT uncovered trajectory area based on the spatio-temporal characteristics to identify network coverage optimization areas with similar spatio-temporal characteristics includes: Divide the areas with similar spatio-temporal characteristics in the spatio-temporal characteristics of each EUHT uncovered trajectory area into the same clustering cluster; For each clustering cluster, calculate the average value of its spatio-temporal characteristics; wherein, the average value includes the average uncovered trajectory duration, average trajectory length, and average trajectory density; Evaluate the network coverage optimization priority of each clustering cluster according to the average value of the spatio-temporal characteristics; Select the areas corresponding to the clustering clusters with a priority higher than the preset level as network coverage optimization areas.

8. The EUHT base station optimization method based on the network connection information of an autonomous vehicle according to claim 4, wherein The identifying the network coverage optimization areas in the network handover heat map further includes: Identify the high-frequency handover areas in the network handover heat map where the network handover density is higher than the preset density threshold; Use the high-frequency handover areas as network coverage optimization areas.

9. The EUHT base station optimization method based on the network connection information of an autonomous vehicle according to claim 8, wherein After the identifying the high-frequency handover areas in the network handover heat map where the network handover density is higher than the preset density threshold, it further includes: Obtain the driving speed data of the autonomous vehicles in the high-frequency handover areas; Screen the high-speed areas in the high-frequency handover areas where the driving speed data is greater than the preset speed threshold; The using the high-frequency handover areas as network coverage optimization areas includes: Use the high-speed areas as network coverage optimization areas.

10. The EUHT base station optimization method based on the network connection information of autonomous vehicles according to claim 8, characterized in that The identifying the high-frequency handover areas in the network handover heat map where the network handover density is higher than the preset density threshold includes: Based on the network handover heat map, determine the area set where the network handover density is higher than the preset density threshold; For each area in the area set, calculate the fluctuation coefficient of its network handover density; Screen out the areas with a fluctuation coefficient less than the preset fluctuation coefficient threshold.

Images