A highway hard shoulder opening control method based on artificial intelligence

Abstract

The present invention relates to the field of highway control technology, and more specifically, to a highway hard shoulder opening control method based on artificial intelligence. The scheme includes real-time collection of traffic flow and vehicle speed; transmitting pre-processed data to a central control system through a high-speed communication network; testing and optimizing the intelligent decision-making algorithm using traffic simulation software, evaluating the performance of the algorithm by simulating different traffic scenarios, and adjusting parameters according to the test results; testing and optimizing the optimal strategy using traffic simulation software, adjusting parameters according to the test results; integrating the optimized intelligent decision-making algorithm into the control system of the highway; continuously monitoring the performance of the highway control system, the performance including traffic efficiency and accident rate, and online optimizing the optimal strategy for hard shoulder opening. The scheme achieves the safety and traffic efficiency of the highway system through roadside sensing combined with automatic shoulder development control dynamic adjustment.

Description

Technical Field

[0001] The present invention relates to the technical field of highway control, and more specifically, to an artificial intelligence-based highway hard shoulder opening control method. Background Art

[0002] In the field of highway control, it is crucial to study the methods, significance and importance of the open control of hard shoulders on highways. Optimizing the use of hard shoulders through intelligent means can not only improve road traffic efficiency and alleviate traffic congestion, but also significantly improve traffic safety. Dynamic open hard shoulders can flexibly respond to different traffic conditions, such as peak hours or emergencies, thereby effectively reducing the occurrence of traffic accidents. In addition, this control method can also help extend the service life of roads, reduce maintenance costs, and provide the public with a more convenient and safe travel environment. Therefore, in-depth research and application of efficient hard shoulder open control methods are of great significance to modern traffic management and smart city construction.

[0003] Prior to the technology of the present invention, existing methods for opening and controlling the hard shoulder of highways mainly relied on fixed-time strategies and manual judgment. These methods usually determine the opening and closing of the hard shoulder based on historical traffic data or a preset timetable, and lack a dynamic response to real-time traffic conditions. The technical difficulty lies in how to accurately predict and adapt to complex and changeable traffic flows, and how to optimize the use of road resources while ensuring traffic safety. Key points include the accuracy of real-time data collection, efficient and reliable data transmission, the development of intelligent decision-making algorithms, and the accuracy and reliability of the execution control system. In addition, the scalability and maintenance costs of the system must also be considered to adapt to different road sections and changing traffic needs. Summary of the invention

[0004] In view of the above problems, the present invention proposes an artificial intelligence-based highway hard shoulder opening management and control method, which achieves the safety and traffic efficiency of the highway system through roadside sensing, combined with automatic shoulder development control strategy and dynamic adjustment.

[0005] According to a first aspect of an embodiment of the present invention, a method for controlling the opening of a hard shoulder of a highway based on artificial intelligence is provided.

[0006] In one or more embodiments, preferably, the artificial intelligence-based highway hard shoulder opening management and control method includes:

[0007] Install roadside sensors to collect real-time traffic flow and vehicle speed;

[0008] The pre-processed data is transmitted to the central control system via a high-speed communication network;

[0009] Use traffic simulation software to test and optimize intelligent decision-making algorithms, evaluate the performance of the algorithms by simulating different traffic scenarios, and adjust parameters based on test results to improve the adaptability of the system;

[0010] Use traffic simulation software to test and optimize the best strategy and adjust parameters based on test results;

[0011] Integrate optimized intelligent decision-making algorithms into highway control systems;

[0012] Continuously monitor the performance of highway control systems, including traffic efficiency and accident rate, and perform online optimization of the best strategy for hard shoulder opening.

[0013] In one or more embodiments, preferably, the installation of roadside sensors to collect traffic flow and vehicle speed in real time specifically includes:

[0014] Set up key locations along the highway, including uphills, downhills, curves and accident-prone areas;

[0015] Install traffic flow detectors and vehicle speed monitoring equipment, and automatically start data collection on the installed traffic flow detectors and vehicle speed monitoring equipment.

[0016] In one or more embodiments, preferably, the transmitting the pre-processed data to the central control system via a high-speed communication network specifically includes:

[0017] Connect the installed traffic flow detectors and vehicle speed monitoring equipment to the central data acquisition system via wired or wireless means after completing data preprocessing;

[0018] After the central control system receives data from each sensor node, it first performs identity authentication and integrity checks, and only the verified data will be further processed;

[0019] The central data collection system receives data from traffic flow detectors and vehicle speed monitoring equipment in real time, and cleans, filters and fuses the raw data through preset algorithms.

[0020] In one or more embodiments, preferably, the intelligent decision-making algorithm is tested and optimized using traffic simulation software, the performance of the algorithm is evaluated by simulating different traffic scenarios, and parameters are adjusted according to the test results to improve the adaptability of the system, specifically including:

[0021] A highway network model built using traffic simulation software VISSIM, which includes road geometry, traffic signs and markings, signal light settings, and expected traffic flow distribution;

[0022] Real-time acquisition of environmental conditions and operating status at different time periods in the current highway network model, wherein the environmental conditions include rainy days, snowy days, foggy days and other weather conditions, and the operating status includes normal conditions, peak hours, non-peak hours and special events, wherein the special events include traffic accidents and construction and maintenance;

[0023] When it is determined that the environmental condition is not other weather conditions or the operating state is not a normal state, extracting the historical data of vehicle operation of each corresponding road section;

[0024] According to the historical data of vehicle operation on different road sections, the road traffic efficiency corresponding to the different road sections when the road shoulder is closed and opened is obtained by using the first calculation formula;

[0025] The second calculation formula is used to obtain the average delay time corresponding to different road sections when the shoulder is closed and opened;

[0026] The third calculation formula is used to obtain the corresponding accident escalation rates of different road sections when the road shoulder is closed and opened;

[0027] Calculate the optimal road shoulder opening strategy using the fourth calculation formula;

[0028] When the environmental conditions and the operating state of a certain section change, re-evaluate and update all the optimal road shoulder opening strategies using the fourth calculation formula;

[0029] The first calculation formula is:

[0030] DLV=100%×czs÷pjc

[0031] Among them, DLV is the road traffic efficiency, czs is the total number of vehicles passing through the current section during this period, and pjc is the hourly average total number of vehicles passing through the current section;

[0032] The second calculation formula is:

[0033] PYW=100%×czs÷sc÷SCAV

[0034] Among them, PYW is the average delay time, czs is the total time of vehicles passing through the current section during this period, sc is the total number of vehicles, and SCAV is the average time of vehicles passing through the current section;

[0035] The third calculation formula is:

[0036] SGL=zhs÷zsc÷ysc

[0037] Wherein, SGL is the accident escalation rate, zhs is the total number of new accidents in the current section or adjacent sections under the same environmental conditions and operating status as the current time in the historical data, zsc is the total duration of the same environmental conditions and operating status as the current time in the historical data, and ysc is the total duration of the preset time period;

[0038] The fourth calculation formula is:

[0039] LJH=argminΣi=ni=1(k1×SGLj-k2×PYWj+DLVj)

[0040] Among them, LJH is the number of the optimal road shoulder, k1 is the first preset coefficient, SGLj is the accident escalation rate when the j-th road shoulder is opened, k2 is the second preset coefficient, PYWj is the average delay time when the j-th road shoulder is opened, DLVj is the road traffic efficiency when the j-th road shoulder is opened, and n is the total number of road sections.

[0041] In one or more embodiments, preferably, the using of traffic simulation software to test and optimize the best strategy and adjusting parameters according to the test results specifically includes:

[0042] Construct a highway network model that includes road geometry, traffic signs and markings, signal settings, and expected traffic flow distribution;

[0043] Embed the developed intelligent decision-making algorithm into the simulation environment, so that it can receive real-time traffic status data from the simulation model and output instructions for opening or closing the hard shoulder;

[0044] Based on the simulation results, the performance of the intelligent decision-making algorithm in different scenarios was evaluated. The main evaluation indicators included the percentage of road traffic efficiency improvement, the average delay time reduction, and the change in accident rate.

[0045] Update the optimal road shoulder number output according to the set efficiency improvement percentage, average delay time reduction and accident rate change constraints.

[0046] In one or more embodiments, preferably, the step of integrating the optimized intelligent decision-making algorithm into the control system of the highway specifically includes:

[0047] After adjusting the parameters according to the test results, they are implanted into the shoulder controller of the highway control system;

[0048] The output of the shoulder controller is judged online. If the shoulder controller output is activated, the efficiency improvement percentage, average delay time reduction and accident rate change are recorded.

[0049] In one or more embodiments, preferably, the continuous monitoring of the performance of the highway control system, the performance including the traffic efficiency and the accident rate, and the online optimization of the best strategy for the opening of the hard shoulder specifically include:

[0050] Adjust parameters based on test results to automatically determine whether the open state of the hard shoulder needs to be adjusted;

[0051] Establish an abnormal situation warning system to deal with sudden large-scale congestion or chain accidents;

[0052] Regularly review and analyze the long-term accumulated monitoring data, use machine learning technology to iteratively optimize the intelligent decision-making algorithm, and optimize the optimal k1 and k2 values ​​in the fourth calculation formula to maximize the comprehensive traffic efficiency of the fifth calculation formula while meeting the preset constraints;

[0053] The fifth calculation formula is:

[0054] ZHTG=(YL×YT+XL×XP+WL×WP+QL×QG)+PL×PG+gg×gl+FGG×FGL+TSG×TSL

[0055] Among them, ZHTG is the comprehensive traffic efficiency, YL is the probability of rainy days, YT is the average traffic efficiency of rainy days, XL is the probability of snowy days, XP is the average of snowy days, WL is the probability of foggy days, WP is the average of foggy days, QL is the probability of other weather conditions, QG is the average of other weather conditions, PL is the probability of normal conditions, PG is the average traffic efficiency of normal conditions, gg is the probability of peak hours, gl is the average traffic efficiency of peak hours, FGG is the probability of non-peak hours, FGL is the average traffic efficiency of non-peak hours, TSG is the probability of special events, and TSL is the average traffic efficiency of special events.

[0056] According to a second aspect of an embodiment of the present invention, there is provided a highway hard shoulder opening management and control system based on artificial intelligence.

[0057] In one or more embodiments, preferably, the artificial intelligence-based highway hard shoulder opening management and control system includes:

[0058] Real-time data collection module, used to install roadside sensors to collect traffic flow and vehicle speed in real time;

[0059] A data transmission module, used to transmit the pre-processed data to the central control system through a high-speed communication network;

[0060] Intelligent decision-making module, which is used to test and optimize the intelligent decision-making algorithm using traffic simulation software, evaluate the performance of the algorithm by simulating different traffic scenarios, and adjust parameters according to the test results to improve the adaptability of the system;

[0061] The simulation optimization module is used to test and optimize the best strategy using traffic simulation software and adjust parameters based on the test results;

[0062] System implementation module for integrating optimized intelligent decision-making algorithms into highway control systems;

[0063] The performance monitoring module is used to continuously monitor the performance of the highway control system, including traffic efficiency and accident rate, and to perform online optimization on the best strategy for opening the hard shoulder.

[0064] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method as described in any one of the first aspect of the embodiment of the present invention is implemented.

[0065] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement any one of the methods described in the first aspect of the embodiment of the present invention.

[0066] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0067] In the solution of the present invention, a reinforcement learning algorithm is used to dynamically optimize the hard shoulder opening strategy, taking multiple influencing factors into consideration to improve the traffic efficiency and safety of the road.

[0068] In the solution of the present invention, the system performance is continuously monitored, and feedback is collected to optimize the algorithm to ensure that the system operates effectively in the long term and adapts to changes in the traffic environment.

[0069] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0070] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0072] Figure 1 It is a flow chart of a method for controlling the opening of hard shoulders of highways based on artificial intelligence according to an embodiment of the present invention.

[0073] Figure 2 The present invention is a flowchart of installing roadside sensors in a method for controlling the opening of hard shoulders of highways based on artificial intelligence in one embodiment of the present invention to collect traffic flow and vehicle speed in real time.

[0074] Figure 3 It is a flowchart of transmitting pre-processed data to a central control system through a high-speed communication network in an artificial intelligence-based highway hard shoulder opening management and control method according to an embodiment of the present invention.

[0075] Figure 4 It is a flowchart of an embodiment of the present invention, in which a method for opening and controlling the hard shoulder of a highway based on artificial intelligence is used to test and optimize the intelligent decision-making algorithm using traffic simulation software, evaluate the performance of the algorithm by simulating different traffic scenarios, and adjust parameters according to the test results to improve the adaptability of the system.

[0076] Figure 5 It is a flowchart of testing and optimizing the best strategy using traffic simulation software in an artificial intelligence-based highway hard shoulder opening control method in one embodiment of the present invention, and adjusting parameters according to the test results.

[0077] Figure 6 It is a flow chart of an embodiment of the present invention, which integrates an optimized intelligent decision-making algorithm into a control system of a highway in an artificial intelligence-based highway hard shoulder opening management and control method.

[0078] Figure 7 It is a flowchart of an embodiment of the present invention, which continuously monitors the performance of a highway control system in an artificial intelligence-based highway hard shoulder opening management and control method, wherein the performance includes traffic efficiency and accident rate, and performs online optimization on the best strategy for hard shoulder opening.

[0079] Figure 8 It is a structural diagram of an artificial intelligence-based highway hard shoulder opening management and control system according to an embodiment of the present invention.

[0080] Fig. 9 It is a structural diagram of an electronic device in one embodiment of the present invention. DETAILED DESCRIPTION

[0081] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0082] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0083] In the field of highway control, it is crucial to study the methods, significance and importance of the open control of hard shoulders on highways. Optimizing the use of hard shoulders through intelligent means can not only improve road traffic efficiency and alleviate traffic congestion, but also significantly improve traffic safety. Dynamic open hard shoulders can flexibly respond to different traffic conditions, such as peak hours or emergencies, thereby effectively reducing the occurrence of traffic accidents. In addition, this control method can also help extend the service life of roads, reduce maintenance costs, and provide the public with a more convenient and safe travel environment. Therefore, in-depth research and application of efficient hard shoulder open control methods are of great significance to modern traffic management and smart city construction.

[0084] Prior to the technology of the present invention, existing methods for opening and controlling the hard shoulder of highways mainly relied on fixed-time strategies and manual judgment. These methods usually determine the opening and closing of the hard shoulder based on historical traffic data or a preset timetable, and lack a dynamic response to real-time traffic conditions. The technical difficulty lies in how to accurately predict and adapt to complex and changeable traffic flows, and how to optimize the use of road resources while ensuring traffic safety. Key points include the accuracy of real-time data collection, efficient and reliable data transmission, the development of intelligent decision-making algorithms, and the accuracy and reliability of the execution control system. In addition, the scalability and maintenance costs of the system must also be considered to adapt to different road sections and changing traffic needs.

[0085] In an embodiment of the present invention, a method for controlling the opening of hard shoulders on highways based on artificial intelligence is provided. The solution achieves the safety and traffic efficiency of the highway system through roadside sensing, combined with an automatic shoulder development control strategy and dynamic adjustment.

[0086] According to a first aspect of an embodiment of the present invention, a method for controlling the opening of a hard shoulder of a highway based on artificial intelligence is provided.

[0087] Figure 1 It is a flow chart of a method for controlling the opening of hard shoulders of highways based on artificial intelligence according to an embodiment of the present invention.

[0088] In one or more embodiments, preferably, the artificial intelligence-based highway hard shoulder opening management and control method includes:

[0089] S101. Install roadside sensors to collect real-time traffic flow and vehicle speed;

[0090] S102, transmitting the pre-processed data to a central control system via a high-speed communication network;

[0091] S103. Use traffic simulation software to test and optimize the intelligent decision-making algorithm, evaluate the performance of the algorithm by simulating different traffic scenarios, and adjust parameters according to the test results to improve the adaptability of the system;

[0092] S104, using traffic simulation software to test and optimize the best strategy, and adjusting parameters according to the test results;

[0093] S105, integrating the optimized intelligent decision-making algorithm into the control system of the highway;

[0094] S106. Continuously monitor the performance of the expressway control system, including traffic efficiency and accident rate, and perform online optimization on the best strategy for opening the hard shoulder.

[0095] In an embodiment of the present invention, high-precision sensors and cameras are deployed along the highway to collect key data such as traffic flow, vehicle speed, density, etc. in real time at a frequency of at least once per second. Then, the pre-processed data is transmitted to the central control system in real time. Finally, with maximizing road traffic efficiency and minimizing accident risks as the optimization goals, a hard shoulder opening strategy is dynamically generated based on real-time data. Finally, the system performance is continuously monitored, including calculating the actual percentage of traffic efficiency improvement, statistical changes in accident rates and other key indicators. A feedback mechanism is established to collect the opinions of drivers and managers, and combined with system logs and operation data, the intelligent decision-making algorithm is regularly retrained and optimized to ensure the long-term and effective operation of the system.

[0096] Figure 2The present invention is a flowchart of installing roadside sensors in a method for controlling the opening of hard shoulders of highways based on artificial intelligence in one embodiment of the present invention to collect traffic flow and vehicle speed in real time.

[0097] like Figure 2 As shown, in one or more embodiments, preferably, the installation of roadside sensors to collect traffic flow and vehicle speed in real time specifically includes:

[0098] S201. Set up key locations along the expressway, including uphills, downhills, curves and accident-prone areas;

[0099] S202: Install a traffic flow detector and a vehicle speed monitoring device, and automatically start data collection on the installed traffic flow detector and the vehicle speed monitoring device.

[0100] In an embodiment of the present invention, reliable data support is provided for intelligent traffic management through a high-precision sensor network and an efficient data transmission mechanism. The core steps include: first, select key locations along the highway for sensor installation. These locations include but are not limited to uphill, downhill, curves and accident-prone areas. For example, on a six-lane two-way highway, we select an installation point at the uphill starting point, end point and middle curve in each direction, for a total of six installation points. The selection of these locations is based on historical traffic accident data and traffic flow analysis to ensure that the selected locations can represent the average traffic conditions of the section. Secondly, traffic flow detectors and vehicle speed monitoring devices are installed at the selected locations. The traffic flow detector uses high-precision radar or video monitoring equipment to accurately identify the number and type of passing vehicles. The vehicle speed monitoring device measures the speed of the vehicle in real time through Doppler radar or video image processing technology. For example, at the starting point of a certain uphill, we installed a high-precision radar traffic flow detector and a Doppler radar vehicle speed monitoring device. These devices are installed on a gantry about 6 meters above the road surface to ensure a wide and unobstructed view.

[0101] Figure 3 It is a flowchart of transmitting pre-processed data to a central control system through a high-speed communication network in an artificial intelligence-based highway hard shoulder opening management and control method according to an embodiment of the present invention.

[0102] like Figure 3 As shown, in one or more embodiments, preferably, the pre-processed data is transmitted to the central control system via a high-speed communication network, specifically including:

[0103] S301, connecting the installed traffic flow detectors and vehicle speed monitoring equipment to the central data acquisition system via wired or wireless means after completing data preprocessing;

[0104] S302, after receiving the data from each sensor node, the central control system first performs identity authentication and integrity check, and only the authenticated data will be further processed;

[0105] S303, the central data acquisition system receives data from traffic flow detectors and vehicle speed monitoring equipment in real time, and cleans, filters and fuses the raw data through a preset algorithm.

[0106] In an embodiment of the present invention, the installed traffic flow detector and vehicle speed monitoring device are connected to the central data acquisition system by wired or wireless means. In this embodiment, we adopt wireless transmission to avoid complicated cable laying work. Each sensor node is equipped with a wireless communication module to transmit data to the central data acquisition system in real time through the 4G / 5G network. At the same time, a data encryption and identity authentication mechanism is established to ensure the security of data transmission. For example, each sensor node will encrypt the data before sending it, and decrypt and verify it at the receiving end to prevent the data from being tampered with or stolen. Then, the central data acquisition system receives data from each sensor in real time, and cleans, filters and fuses the raw data through a preset algorithm. The data cleaning process includes noise removal, outlier detection, etc.; data filtering filters out useful information according to preset rules (such as vehicle speed threshold, vehicle model classification, etc.); data fusion integrates data from multiple sensors to form a unified description of traffic conditions. For example, the system averages the vehicle speed data at different locations in the same time period to obtain the average vehicle speed of the road section; at the same time, combined with traffic flow data, it determines whether there is congestion. The processed data is used to update the real-time traffic status display board, mobile applications or other information release platforms to provide drivers with accurate road conditions information. Through the above steps, the goal of installing roadside sensors at key locations along the highway and collecting traffic flow and vehicle speed data in real time is achieved. The system not only improves road traffic efficiency, but also enhances traffic safety, providing strong technical support for intelligent traffic management.

[0107] Figure 4 It is a flowchart of an embodiment of the present invention, in which a method for opening and controlling the hard shoulder of a highway based on artificial intelligence is used to test and optimize the intelligent decision-making algorithm using traffic simulation software, evaluate the performance of the algorithm by simulating different traffic scenarios, and adjust parameters according to the test results to improve the adaptability of the system.

[0108] like Figure 4As shown, in one or more embodiments, preferably, the intelligent decision-making algorithm is tested and optimized using traffic simulation software, the performance of the algorithm is evaluated by simulating different traffic scenarios, and the parameters are adjusted according to the test results to improve the adaptability of the system, specifically including:

[0109] S401, a highway network model constructed using traffic simulation software VISSIM, the model including road geometry, traffic signs and markings, signal light settings, and expected traffic flow distribution;

[0110] S402, real-time acquisition of environmental conditions and operating status at different time periods in the current highway network model, wherein the environmental conditions include rainy days, snowy days, foggy days and other weather conditions, and the operating status includes normal conditions, peak hours, non-peak hours and special events, wherein the special events include traffic accidents and construction and maintenance;

[0111] S403, when it is determined that the environmental condition is not other weather conditions or the operating state is not a normal state, extracting the historical data of vehicle operation of each corresponding road section;

[0112] S404, according to the historical data of vehicle operation on different road sections, using the first calculation formula to obtain the road traffic efficiency of different road sections when the road shoulder is closed and opened;

[0113] S405, using a second calculation formula to obtain the average delay time corresponding to different road sections when the shoulder is closed and opened;

[0114] S406, using a third calculation formula to obtain the accident escalation rates corresponding to different road sections when the road shoulder is closed and opened;

[0115] S407, calculating the optimal road shoulder opening strategy using the fourth calculation formula;

[0116] S408, when the environmental condition and the operating state of a certain section change, re-evaluate and update the calculation of all optimal road shoulder opening strategies using the fourth calculation formula;

[0117] The first calculation formula is:

[0118] DLV=100%×czs÷pjc

[0119] Among them, DLV is the road traffic efficiency, czs is the total number of vehicles passing through the current section during this period, and pjc is the hourly average total number of vehicles passing through the current section;

[0120] The second calculation formula is:

[0121] PYW=100%×czs÷sc÷SCAV

[0122] Among them, PYW is the average delay time, czs is the total time of vehicles passing through the current section during this period, sc is the total number of vehicles, and SCAV is the average time of vehicles passing through the current section;

[0123] The third calculation formula is:

[0124] SGL=zhs÷zsc÷ysc

[0125] Wherein, SGL is the accident escalation rate, zhs is the total number of new accidents in the current section or adjacent sections under the same environmental conditions and operating status as the current time in the historical data, zsc is the total duration of the same environmental conditions and operating status as the current time in the historical data, and ysc is the total duration of the preset time period;

[0126] The fourth calculation formula is:

[0127] LJH=argminΣi=ni=1(k1×SGLj-k2×PYWj+DLVj)

[0128] Among them, LJH is the number of the optimal road shoulder, k1 is the first preset coefficient, SGLj is the accident escalation rate when the j-th road shoulder is opened, k2 is the second preset coefficient, PYWj is the average delay time when the j-th road shoulder is opened, DLVj is the road traffic efficiency when the j-th road shoulder is opened, and n is the total number of road sections.

[0129] In an embodiment of the present invention, a highway network model is constructed: VISSIM is used to create a highway network model that includes road geometry, traffic signs and markings, signal light settings, and expected traffic flow distribution. This model is used to simulate the traffic environment in the real world. Real-time data acquisition: Environmental conditions and operating status data of different time periods are obtained from the highway network model. These data include weather conditions (such as rainy days, snowy days, foggy days, etc.) and traffic conditions (such as normal conditions, peak hours, non-peak hours, special events such as traffic accidents and construction and maintenance). Historical data extraction: When it is detected that the environmental conditions are not "other weather" or the operating status is not "normal state", the system will extract the vehicle operation history data of the corresponding section. These data will be used for subsequent calculations and analysis. Calculate road traffic efficiency: Use the first calculation formula DLV=100%×czs÷pjc to calculate the road traffic efficiency of different sections when the shoulder is closed and opened. Among them, DLV represents road traffic efficiency, czs is the total number of vehicles passing through the current section during this period, and pjc is the hourly average number of vehicles passing through the current section. This formula calculates efficiency by comparing the actual number of vehicles passing through with the average number of vehicles passing through. Calculate the average delay time: Use the second calculation formula PYW=100%×czs÷sc÷SCAV to calculate the average delay time of different sections when the shoulder is closed and opened. Among them, PYW represents the average delay time, czs is the total time of vehicles passing through the current section during this period, sc is the total number of vehicles, and SCAV is the average time of vehicles passing through the current section. This formula calculates the average delay by considering the passing time and number of all vehicles. Calculate the accident escalation rate: Use the third calculation formula SGL=zhs÷zsc÷ysc to calculate the accident escalation rate of different sections when the shoulder is closed and opened. Among them, SGL represents the accident escalation rate, zhs is the total number of new accidents generated in the current section or adjacent sections under the same environmental conditions and operating status as the current moment in the historical data, zsc is the total time of the same environmental conditions and operating status as the current moment in the historical data, and ysc is the total time of the preset time period. This formula calculates the frequency of accidents by analyzing historical accident data. Calculate the optimal shoulder opening strategy for a road section: Use the fourth calculation formula LJH=argminΣi=ni=1(k1×SGLj-k2×PYWj+DLVj) to calculate the optimal shoulder opening strategy for a road section. Among them, LJH represents the optimal shoulder number of the road section, k1 and k2 are preset coefficients used to adjust the weights of the accident escalation rate and the average delay time, SGLj, PYWj and DLVj represent the accident escalation rate, average delay time and road traffic efficiency when the shoulder of the j-th road section is opened, respectively, and n is the total number of road sections. This formula determines the optimal strategy by minimizing the weighted accident escalation rate and average delay time while maximizing the road traffic efficiency.Strategy update: When the environmental conditions or operating status change, the system will re-evaluate and update all the optimal road shoulder opening strategies to ensure that the algorithm can adapt to the changing traffic conditions. Through the above steps and formulas, the intelligent decision-making algorithm can be effectively tested and optimized to improve the adaptability and efficiency of the system.

[0130] Figure 5 It is a flowchart of testing and optimizing the best strategy using traffic simulation software in an artificial intelligence-based highway hard shoulder opening control method in one embodiment of the present invention, and adjusting parameters according to the test results.

[0131] like Figure 5 As shown, in one or more embodiments, preferably, the optimal strategy is tested and optimized using traffic simulation software, and parameters are adjusted according to the test results, specifically including:

[0132] S501, constructing a highway network model including road geometry, traffic signs and markings, signal light settings, and expected traffic flow distribution;

[0133] S502, embedding the developed intelligent decision-making algorithm into the simulation environment, so that it can receive real-time traffic status data from the simulation model and output instructions for opening or closing the hard shoulder;

[0134] S503. Based on the simulation results, the performance of the intelligent decision-making algorithm in different scenarios is evaluated. The main evaluation indicators include the percentage of improvement in road traffic efficiency, the reduction in average delay time, and the change in accident rate.

[0135] S504: Update the output of the optimal road shoulder number according to the set efficiency improvement percentage, average delay time reduction and accident rate change constraints.

[0136] In an embodiment of the present invention, first, a highway network model including road geometry, traffic signs and markings, signal light settings, and expected traffic flow distribution is constructed using VISSIM software. The model should reflect the physical characteristics and operating environment of a real highway in detail. Secondly, the developed intelligent decision-making algorithm is embedded in the simulation environment. The algorithm can receive traffic status data from the simulation model in real time and identify the current traffic mode and potential congestion points by analyzing these data. Based on this information, the algorithm will generate instructions for opening or closing the hard shoulder to optimize traffic flow and reduce congestion. Then, during the simulation process, the algorithm will dynamically adjust its parameters according to the real-time feedback of traffic status data. For example, when it is detected that the average speed of a certain section of road is continuously lower than a preset threshold, the algorithm may automatically increase the frequency or duration of opening the hard shoulder of the section; conversely, if the traffic is smooth, it may reduce unnecessary hard shoulder opening to balance road resource utilization and traffic safety. Finally, based on the simulation results, key indicators such as the percentage of road traffic efficiency improvement, the average delay time reduction, and the change in accident rate under different strategies are evaluated. Based on these evaluation results, the optimal section number output strategy under the current road network conditions and specific traffic demand scenarios is determined. At the same time, these strategies are updated into intelligent decision-making algorithms to achieve more efficient traffic management and control in future practical applications.

[0137] Figure 6 It is a flow chart of an embodiment of the present invention, which integrates an optimized intelligent decision-making algorithm into a control system of a highway in an artificial intelligence-based highway hard shoulder opening management and control method.

[0138] like Figure 6 As shown, in one or more embodiments, preferably, the integration of the optimized intelligent decision-making algorithm into the control system of the highway specifically includes:

[0139] S601, after adjusting the parameters according to the test results, implanting them into the shoulder controller of the control system of the expressway;

[0140] S602, online judging the output of the shoulder controller, if the shoulder controller output is activated, recording the efficiency improvement percentage, average delay time reduction and accident rate change.

[0141] In the embodiment of the present invention, first, the existing intelligent decision-making algorithm is optimized to improve its application effect in the highway control system. The optimized algorithm is verified by simulation experiments and actual road tests to verify its performance indicators, such as efficiency improvement percentage, average delay time reduction, and accident rate change. After the algorithm optimization is completed, it is implanted into the control system of the highway, and the specific implementation method is to embed the algorithm into the software of the shoulder controller. The shoulder controller is an important part of the highway control system, responsible for monitoring and managing road conditions and communicating with vehicles. By integrating the optimized intelligent decision-making algorithm into the shoulder controller, real-time monitoring and intelligent scheduling of highway traffic flow can be achieved. During the operation of the system, the output of the shoulder controller needs to be judged online. When the shoulder controller outputs a start signal, the system automatically records the current efficiency improvement percentage, average delay time reduction, accident rate change and other key indicators. These data will be used to evaluate the performance of the intelligent decision-making algorithm in the actual road environment and provide a basis for subsequent algorithm optimization. For example, it is assumed that the intelligent decision-making algorithm integration scheme described in the present invention is implemented on a certain highway. In the algorithm optimization stage, simulation experiments showed that compared with the original algorithm, the optimized algorithm can improve efficiency by 10%, reduce average delay time by 20%, and reduce accident rate by 5%. In actual application, when the shoulder controller outputs the start signal, the system records that the current efficiency has increased by 12%, the average delay time has decreased by 25%, and the accident rate has decreased by 8%. These data show that the intelligent decision-making algorithm integration solution described in the present invention has achieved good results in actual road environments.

[0142] Figure 7 It is a flowchart of an embodiment of the present invention, which continuously monitors the performance of a highway control system in an artificial intelligence-based highway hard shoulder opening management and control method, wherein the performance includes traffic efficiency and accident rate, and performs online optimization on the best strategy for hard shoulder opening.

[0143] like Figure 7 As shown, in one or more embodiments, preferably, the continuous monitoring of the performance of the highway control system, the performance including the traffic efficiency and the accident rate, and the online optimization of the best strategy for the opening of the hard shoulder specifically include:

[0144] S701, adjusting parameters according to the test results to automatically determine whether the opening state of the hard shoulder needs to be adjusted;

[0145] S702. Establish an abnormal situation warning system to deal with sudden large-scale congestion or chain accidents;

[0146] S703. Regularly review and analyze the long-term accumulated monitoring data, use machine learning technology to iteratively optimize the intelligent decision-making algorithm, and optimize the optimal k1 and k2 values ​​in the fourth calculation formula to maximize the comprehensive traffic efficiency of the fifth calculation formula while satisfying the preset constraints;

[0147] The fifth calculation formula is:

[0148] ZHTG=(YL×YT+XL×XP+WL×WP+QL×QG)+PL×PG+gg×gl+FGG×FGL+TSG×TSL

[0149] Among them, ZHTG is the comprehensive traffic efficiency, YL is the probability of rainy days, YT is the average traffic efficiency of rainy days, XL is the probability of snowy days, XP is the average of snowy days, WL is the probability of foggy days, WP is the average of foggy days, QL is the probability of other weather conditions, QG is the average of other weather conditions, PL is the probability of normal conditions, PG is the average traffic efficiency of normal conditions, gg is the probability of peak hours, gl is the average traffic efficiency of peak hours, FGG is the probability of non-peak hours, FGL is the average traffic efficiency of non-peak hours, TSG is the probability of special events, and TSL is the average traffic efficiency of special events.

[0150] In an embodiment of the present invention, long-term data analysis and machine learning optimization: the system regularly reviews and analyzes the long-term accumulated monitoring data, and uses machine learning technology to iteratively optimize the intelligent decision-making algorithm. By continuously learning and adapting to new traffic patterns and environmental changes, the system can optimize the optimal k1 and k2 values ​​in the fourth calculation formula while meeting the preset constraints, so that the comprehensive traffic efficiency of the fifth calculation formula is maximized; Calculation of comprehensive traffic efficiency: The comprehensive traffic efficiency is calculated by a complex formula that takes into account a variety of factors, including traffic efficiency under different weather conditions, average traffic efficiency in normal conditions and peak hours, average traffic efficiency during non-peak hours, and the probability and average traffic efficiency of special events. By optimizing the parameters in this formula, the system can find the best hard shoulder opening strategy to improve overall traffic efficiency.

[0151] According to a second aspect of an embodiment of the present invention, there is provided a highway hard shoulder opening management and control system based on artificial intelligence.

[0152] Figure 8 It is a structural diagram of an artificial intelligence-based highway hard shoulder opening management and control system according to an embodiment of the present invention.

[0153] In one or more embodiments, preferably, the artificial intelligence-based highway hard shoulder opening management and control system includes:

[0154] The real-time acquisition module 801 is used to install roadside sensors to collect traffic flow and vehicle speed in real time;

[0155] Data transmission module 802, used to transmit the pre-processed data to the central control system via a high-speed communication network;

[0156] Intelligent decision module 803, used to test and optimize the intelligent decision algorithm using traffic simulation software, evaluate the performance of the algorithm by simulating different traffic scenarios, and adjust parameters according to the test results to improve the adaptability of the system;

[0157] A simulation optimization module 804 is used to test and optimize the best strategy using traffic simulation software and adjust parameters according to the test results;

[0158] A system implementation module 805 for integrating the optimized intelligent decision-making algorithm into the control system of the highway;

[0159] The performance monitoring module 806 is used to continuously monitor the performance of the highway control system, including the traffic efficiency and accident rate, and to perform online optimization on the best strategy for opening the hard shoulder.

[0160] In the embodiment of the present invention, a system suitable for different structures is realized through a series of modular designs. The system can achieve closed-loop, reliable and efficient execution through collection, analysis and control.

[0161] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method as described in any one of the first aspect of the embodiment of the present invention is implemented.

[0162] According to a fourth aspect of an embodiment of the present invention, an electronic device is provided. Fig. 9 It is a structural diagram of an electronic device in one embodiment of the present invention. Fig. 9 The electronic device shown is a general-purpose artificial intelligence-based highway hard shoulder opening control device. Fig. 9 , the electronic device includes a plurality of acquisition devices 901 and a processing device 902; wherein different acquisition devices 901 monitor different areas of a target scene, and the monitoring areas of the plurality of acquisition devices cover the target scene;

[0163] Each acquisition device 901 is used to acquire an image of a target scene and identify the position information of a moving target in the acquired image;

[0164] The processing device 902 includes a processor 903, a communication interface 904, a memory 905 and a communication bus 906, wherein the processor 903, the communication interface 904 and the memory 905 communicate with each other via the communication bus 906.

[0165] Memory 905, used for storing computer programs;

[0166] The processor 903 is used to implement any of the above method steps provided by the embodiments of the present invention when executing the computer program stored in the memory 905.

[0167] The communication bus 906 mentioned in the above processing device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 906 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0168] The communication interface 904 is used for communication between the above processing device and other devices.

[0169] The memory 905 may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory 905 may also be at least one storage device located away from the processor 903.

[0170] The above-mentioned processor 903 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0171] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0172] In the solution of the present invention, a reinforcement learning algorithm is used to dynamically optimize the hard shoulder opening strategy, taking multiple influencing factors into consideration to improve the traffic efficiency and safety of the road.

[0173] In the solution of the present invention, the system performance is continuously monitored, and feedback is collected to optimize the algorithm to ensure that the system operates effectively in the long term and adapts to changes in the traffic environment.

[0174] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0175] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0178] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A highway hard shoulder opening control method based on artificial intelligence, characterized in that: The method includes: Install roadside sensors to collect real-time traffic flow and vehicle speed; The pre-processed data is transmitted to the central control system via a high-speed communication network; Use traffic simulation software to test and optimize intelligent decision-making algorithms, evaluate the performance of the algorithms by simulating different traffic scenarios, and adjust parameters based on test results to improve the adaptability of the system; Use traffic simulation software to test and optimize the best strategy and adjust parameters based on test results; Integrate optimized intelligent decision-making algorithms into highway control systems; Continuously monitor the performance of highway control systems, including traffic efficiency and accident rate, and optimize the best strategy for hard shoulder opening online; The intelligent decision-making algorithm is tested and optimized using traffic simulation software, and the performance of the algorithm is evaluated by simulating different traffic scenarios, and parameters are adjusted according to the test results to improve the adaptability of the system, including: A highway network model built using traffic simulation software VISSIM, which includes road geometry, traffic signs and markings, signal light settings, and expected traffic flow distribution; Real-time acquisition of environmental conditions and operating status at different time periods in the current highway network model, wherein the environmental conditions include rainy days, snowy days, foggy days and other weather conditions, and the operating status includes normal conditions, peak hours, non-peak hours and special events, wherein the special events include traffic accidents and construction and maintenance; When it is determined that the environmental condition is not other weather conditions or the operating state is not a normal state, extracting the historical data of vehicle operation of each corresponding road section; According to the historical data of vehicle operation on different road sections, the road traffic efficiency corresponding to the different road sections when the road shoulder is closed and opened is obtained by using the first calculation formula; The second calculation formula is used to obtain the average delay time corresponding to different road sections when the shoulder is closed and opened; The third calculation formula is used to obtain the corresponding accident escalation rates of different road sections when the road shoulder is closed and opened; Calculate the optimal road shoulder opening strategy using the fourth calculation formula; When the environmental conditions and the operating state of a certain section change, re-evaluate and update all the optimal road shoulder opening strategies using the fourth calculation formula; The first calculation formula is: DLV=100%×czs÷pjc Among them, DLV is the road traffic efficiency, czs is the total number of vehicles passing through the current section during this period, and pjc is the hourly average total number of vehicles passing through the current section; The second calculation formula is: PYW=100%×czs÷sc÷SCAV Among them, PYW is the average delay time, czs is the total time of vehicles passing through the current section during this period, sc is the total number of vehicles, and SCAV is the average time of vehicles passing through the current section; The third calculation formula is: SGL=zhs÷zsc÷ysc Wherein, SGL is the accident escalation rate, zhs is the total number of new accidents in the current section or adjacent sections under the same environmental conditions and operating status as the current time in the historical data, zsc is the total duration of the same environmental conditions and operating status as the current time in the historical data, and ysc is the total duration of the preset time period; The fourth calculation formula is: LJH=argminΣi=ni=1(k1×SGLj-k2×PYWj+DLVj) Among them, LJH is the number of the optimal road shoulder, k1 is the first preset coefficient, SGLj is the accident escalation rate when the j-th road shoulder is opened, k2 is the second preset coefficient, PYWj is the average delay time when the j-th road shoulder is opened, DLVj is the road traffic efficiency when the j-th road shoulder is opened, and n is the total number of road sections.

2. The method for controlling the opening of a highway hard shoulder based on artificial intelligence according to claim 1, characterized in that: The installation of roadside sensors to collect traffic flow and vehicle speed in real time specifically includes: Set up key locations along the highway, including uphills, downhills, curves and accident-prone areas; Install traffic flow detectors and vehicle speed monitoring equipment, and automatically start data collection on the installed traffic flow detectors and vehicle speed monitoring equipment.

3. The method for controlling the opening of hard shoulders of highways based on artificial intelligence according to claim 1, characterized in that: The pre-processed data is transmitted to the central control system via a high-speed communication network, specifically including: Connect the installed traffic flow detectors and vehicle speed monitoring equipment to the central data acquisition system via wired or wireless means after completing data preprocessing; After the central control system receives data from each sensor node, it first performs identity authentication and integrity checks, and only the verified data will be further processed; The central data collection system receives data from traffic flow detectors and vehicle speed monitoring equipment in real time, and cleans, filters and fuses the raw data through preset algorithms.

4. The method for controlling the opening of a highway hard shoulder based on artificial intelligence according to claim 1, characterized in that: The use of traffic simulation software to test and optimize the best strategy and adjust parameters according to the test results specifically includes: Construct a highway network model that includes road geometry, traffic signs and markings, signal settings, and expected traffic flow distribution; Embed the developed intelligent decision-making algorithm into the simulation environment, so that it can receive real-time traffic status data from the simulation model and output instructions for opening or closing the hard shoulder; Based on the simulation results, the performance of the intelligent decision-making algorithm in different scenarios was evaluated. The main evaluation indicators included the percentage of road traffic efficiency improvement, the average delay time reduction, and the change in accident rate. Update the optimal road shoulder number output according to the set efficiency improvement percentage, average delay time reduction and accident rate change constraints.

5. The method for controlling the opening of a highway hard shoulder based on artificial intelligence according to claim 1, characterized in that: The integration of the optimized intelligent decision-making algorithm into the control system of the highway specifically includes: After adjusting the parameters according to the test results, they are implanted into the shoulder controller of the highway control system; The output of the shoulder controller is judged online. If the shoulder controller output is activated, the efficiency improvement percentage, average delay time reduction and accident rate change are recorded.

6. The method for controlling the opening of a highway hard shoulder based on artificial intelligence according to claim 1, characterized in that: The continuous monitoring of the performance of the highway control system, including the traffic efficiency and accident rate, and online optimization of the best strategy for opening the hard shoulder specifically include: Adjust parameters based on test results to automatically determine whether the open state of the hard shoulder needs to be adjusted; Establish an abnormal situation warning system to deal with sudden large-scale congestion or chain accidents; Regularly review and analyze the long-term accumulated monitoring data, use machine learning technology to iteratively optimize the intelligent decision-making algorithm, and optimize the optimal k1 and k2 values ​​in the fourth calculation formula to maximize the comprehensive traffic efficiency of the fifth calculation formula while meeting the preset constraints; The fifth calculation formula is: ZHTG=(YL×YT+XL×XP+WL×WP+QL×QG)+PL×PG+gg×gl+FGG×FGL+TSG×TSL Among them, ZHTG is the comprehensive traffic efficiency, YL is the probability of rainy days, YT is the average traffic efficiency of rainy days, XL is the probability of snowy days, XP is the average of snowy days, WL is the probability of foggy days, WP is the average of foggy days, QL is the probability of other weather conditions, QG is the average of other weather conditions, PL is the probability of normal conditions, PG is the average traffic efficiency of normal conditions, gg is the probability of peak hours, gl is the average traffic efficiency of peak hours, FGG is the probability of non-peak hours, FGL is the average traffic efficiency of non-peak hours, TSG is the probability of special events, and TSL is the average traffic efficiency of special events.

7. An artificial intelligence-based highway hard shoulder opening control system, characterized in that: The system is used to implement the method according to any one of claims 1 to 6, and the system comprises: Real-time data collection module, used to install roadside sensors to collect traffic flow and vehicle speed in real time; A data transmission module, used to transmit the pre-processed data to the central control system through a high-speed communication network; Intelligent decision-making module, which is used to test and optimize the intelligent decision-making algorithm using traffic simulation software, evaluate the performance of the algorithm by simulating different traffic scenarios, and adjust parameters according to the test results to improve the adaptability of the system; The simulation optimization module is used to test and optimize the best strategy using traffic simulation software and adjust parameters based on the test results; System implementation module for integrating optimized intelligent decision-making algorithms into highway control systems; The performance monitoring module is used to continuously monitor the performance of the highway control system, including traffic efficiency and accident rate, and to perform online optimization on the best strategy for opening the hard shoulder.

8. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method according to any one of claims 1 to 6 when executed by a processor.

9. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-6.

Images