Highway multi-scenario comprehensive application platform based on digital twin

Abstract

The present invention discloses a highway multi-scenario comprehensive application platform based on digital twins, which relates to the field of intelligent transportation technology. The application platform includes a scenario calibration module, an application prompt module and a feedback statistics module. The technical key points are: according to real-time traffic data and analysis results, it automatically sends intelligent instructions such as lane change, deceleration, safety prompts, etc. to the driver, enhances the initiative of traffic management, obtains the traffic conditions and safety parameters in the corresponding scenarios ahead in advance, and reserves sufficient reaction time for the driver. By obtaining the feedback data of the driver in different prompt scenarios, and then performing comprehensive calculations to obtain the feedback index, the driver's satisfaction can be accurately and effectively reflected according to the comparison between the feedback index and the feedback threshold. By using digital twin technology and machine learning algorithms, the traffic flow data in different scenarios are analyzed and processed in real time, the prompt instructions are dynamically optimized, and the overall intelligence level and adaptive ability are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and specifically to a multi-scenario comprehensive application platform for highways based on digital twins. Background Art

[0002] Intelligent transportation refers to the use of modern electronic information technology, communication technology, control technology and computer technology to intelligently manage and control the transportation system in order to improve the safety, efficiency and sustainability of transportation. The intelligent transportation system covers all aspects from road infrastructure, transportation tools to traffic management, and through information and automation, it optimizes traffic flow, reduces traffic congestion, reduces traffic accident rates, and improves travel experience.

[0003] The technical solution pointed out in the document with the existing authorization announcement number CN115035715B and the name of which is a method for predicting highway traffic based on decision trees and multivariate auxiliary information, includes: establishing a multivariate auxiliary information time series with a multi-scale time span, using a multivariate information-aware LSTM model to learn the feature representation of information such as traffic and weather, and then constructing a time series with multivariate information, using a gradient boosting decision tree to train the model, and improving the accuracy of traffic prediction in highway scenarios; the present invention uses real highway microwave vehicle inspection and meteorological detector data sets to construct a multivariate information data set, uses a sliding window to comprehensively consider a variety of characteristic factors affecting traffic flow, and uses a model based on a gradient boosting decision tree to predict traffic in highway scenarios, which has a higher accuracy rate, but it cannot be comprehensively operated for multiple scenarios on highways.

[0004] In combination with the above documents and existing technologies, the road conditions when drivers are driving on highways are not always the same. For example, there will be highway entrances and exits, mountain tunnels, and toll stations during driving. At this time, it is necessary to consider how to effectively prompt the driver in different scenarios. The existing platform also has corresponding safety prompts, but they do not or rarely take into account the driver's satisfaction with the prompt information. If the prompt has a large error, the driver's satisfaction will be greatly reduced. When the driver makes driving adjustments based on erroneous or large-error prompts, the risk of accidents will increase to a certain extent, which is not conducive to the vehicle's travel efficiency on the highway. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the shortcomings of the prior art, the present invention provides a multi-scenario comprehensive application platform for highways based on digital twins. According to real-time traffic data and analysis results, it automatically issues intelligent instructions such as lane change, deceleration, and safety prompts to the driver, thereby enhancing the initiative of traffic management, obtaining the traffic conditions and safety parameters in the corresponding scenarios ahead in advance, and reserving sufficient reaction time for the driver. By obtaining the feedback data of the driver in different prompt scenarios, and then performing comprehensive calculations to obtain the feedback index, the driver's satisfaction can be accurately and effectively reflected based on the comparison between the feedback index and the feedback threshold. By using digital twin technology and machine learning algorithms, the traffic flow data in different scenarios are analyzed and processed in real time, the prompt instructions are dynamically optimized, the overall intelligence level and adaptability are improved, and the problems raised in the background technology are solved.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] The highway multi-scenario comprehensive application platform based on digital twin includes:

[0010] The scene calibration module obtains the navigation data of any driver and combines it with digital twin technology to identify and mark the prompt scenes on the corresponding navigation route. The prompt scenes include highway intersection scenes, highway tunnel scenes, and highway toll station scenes.

[0011] The application prompt module is used to, when the driver is driving normally on the highway, it is estimated that the marked point on the navigation route will pass by S meters ahead. If the marked point is a highway intersection scene, the traffic density is obtained, the traffic density is compared with the standard density value, and the corresponding first prompt instruction is executed according to the comparison result;

[0012] If the marked point is a highway tunnel scene, a safety data set is obtained, and a safety index I under the marked point is generated based on the preprocessed safety data set. The safety index I is compared with the safety threshold, and the corresponding second prompt instruction is executed according to the comparison result;

[0013] If the marked point is a highway toll station scene, the pre-station data is obtained, and the pre-station data includes the number of vehicles piled up in front of the station and the toll speed of each toll gate. When the number of vehicles piled up in front of the station reaches the preset saturation value, the toll speed of each toll gate is compared to extract the top three toll gates in terms of toll speed as the calibration toll gates, and trigger the guidance prompt instruction;

[0014] The feedback statistics module obtains and calculates the feedback index P for each prompt scenario based on the feedback data of the corresponding driver in each prompt scenario among the preset M drivers. q , and each feedback index Pq Compare with the preset feedback threshold and execute the corresponding strategy according to the comparison result.

[0015] Furthermore, a corresponding scene at S meters ahead is marked on the navigation route, and the corresponding scene is the marking point, and the value of S in the S meters ahead is at least 100.

[0016] Furthermore, traffic density refers to the number of vehicles per unit length of highway, and the calculation formula of traffic density is as follows:

[0017] Vk=sc / lr;

[0018] Where Vk represents the traffic density, sc represents the number of vehicles passing through per unit time, and lr represents the length of the highway intersection section.

[0019] Furthermore, the process of executing the corresponding first prompt instruction according to the comparison result is as follows:

[0020] When the traffic density exceeds the standard density value, the triggered lane change prompt instruction is: the corresponding driver is prompted by voice to change lanes to the side away from the intersection; when the traffic density does not exceed the standard density value, the triggered deceleration prompt instruction is: the corresponding driver is prompted by voice that there is an intersection ahead and needs to slow down.

[0021] Furthermore, the safety data set includes traffic density values, interior lighting values, and interior ventilation values, and the traffic density values ​​are the same as those in a highway intersection scenario.

[0022] Furthermore, the internal lighting value represents the lighting value in the highway tunnel, and the process of obtaining the lighting value is: installing brightness sensors at equal intervals in the highway tunnel, extracting the minimum value of each brightness data, and combining it with the standard brightness to calculate the lighting value. The formula based on it is as follows:

[0023] Zm=|dz min -Bd|;

[0024] Where Zm represents the lighting value, dz min It indicates the minimum brightness in the highway tunnel, and Bd indicates the preset standard brightness;

[0025] The internal ventilation value represents the ventilation value in the highway tunnel, and the process of obtaining the ventilation value is: wind speed sensors are installed at equal intervals in the highway tunnel, the minimum value of each wind speed data is extracted, and the wind speed value is calculated in combination with the standard wind speed. The formula is as follows:

[0026] Fs=|df min -Bf|;

[0027] Where Fs represents the wind speed value, df min It indicates the minimum wind speed in the highway tunnel, and Bf indicates the preset standard wind speed.

[0028] Furthermore, the formula for calculating the safety index I is as follows:

[0029] I = 1 / (αVt+βZm+γFs);

[0030] Where Vt represents the traffic density value, α, β, γ are all weight coefficients, and 0<α≤1, 0<β≤1, 0<γ≤1;

[0031] The process of executing the corresponding second prompt instruction according to the comparison result is as follows:

[0032] When the safety index I exceeds the preset safety threshold, no response action is taken; when the safety index I does not exceed the preset safety threshold, a safety prompt instruction is triggered, and the corresponding driver is prompted by voice that there is an abnormal situation in the tunnel ahead and needs to reduce the speed and pay attention to the road conditions.

[0033] Furthermore, the toll collection speed of each toll gate is obtained by obtaining the number of vehicles passing through the corresponding toll gate every half hour, and dividing the number of vehicles by thirty minutes to obtain the number of vehicles passing through the corresponding toll gate per minute, which is the toll collection speed of the corresponding toll gate; the triggered guidance prompt instruction is: prompting the corresponding driver to go to the calibrated toll gate through voice.

[0034] Furthermore, the process of obtaining driver feedback data is as follows:

[0035] After the driver passes the marked point of the corresponding prompt scene, the voice of the corresponding instruction before entering the marked point is sent to the driver to ask whether he is satisfied. If there is no response or recognition, it will not be counted in the feedback data. If the driver is dissatisfied with the voice of the corresponding instruction, it will be counted as feedback data of the corresponding scene. Feedback index P q The calculation method is as follows:

[0036]

[0037] Where P q The q in represents the number of the corresponding prompt scene, and q = 1, 2, 3, P1 represents the feedback index in the highway intersection scene, P2 represents the feedback index in the highway tunnel scene, P3 represents the feedback index in the highway toll station scene, T i，q represents the feedback data of the i-th driver in the corresponding prompt scenario, where i = 1, 2, ..., M, T avg，q It represents the mean of the corresponding feedback data of M drivers in the corresponding prompt scenario.

[0038] Furthermore, the process of executing the corresponding strategy according to the comparison results is as follows:

[0039] Each feedback index P q Compared with the preset feedback threshold, when the feedback index P q If the feedback index P is lower than the feedback threshold, no response action will be taken; q If it is not lower than the feedback threshold, a warning signal is triggered and an optimization adjustment strategy is executed;

[0040] The process of executing the optimization adjustment strategy is as follows:

[0041] The digital twin technology is used to analyze and process the traffic flow data obtained in the corresponding prompt scene in real time, and the machine learning algorithm is used to optimize the traffic flow data. q and traffic flow data to generate the optimized frequency under the corresponding prompt scenario q , and follow the optimized frequency Of q Carry out optimization processing;

[0042] Among them, the traffic flow data in the highway intersection scenario is: traffic density Vk;

[0043] The traffic flow data in the highway tunnel scenario are: safety index I;

[0044] The traffic flow data in the highway toll station scenario are: the maximum value of the toll speed;

[0045] Calculate the optimization frequencyOf q The formula is as follows:

[0046] Of q =G1(w1P q +w2S q );

[0047] In the formula, G1 is the constant correction coefficient, Sj is q It represents the traffic flow data under the corresponding prompt scenario, w1 and w2 are the preset proportional coefficients of the feedback index and the traffic flow data respectively, and w1>w2>0.

[0048] (III) Beneficial effects

[0049] The present invention provides a highway multi-scenario comprehensive application platform based on digital twins, which has the following beneficial effects:

[0050] 1. Based on real-time traffic data and analysis results, the present invention automatically issues intelligent instructions such as lane change, deceleration, and safety prompts to the driver, thereby enhancing the initiative of traffic management, obtaining the traffic conditions and safety parameters of the corresponding scene ahead in advance, reserving sufficient reaction time for the driver, and guiding the driver to adopt appropriate driving strategies to reduce the risk of accidents. At the same time, it can effectively guide traffic flow and improve overall traffic efficiency;

[0051] 2. The present invention obtains the feedback data of the driver in different prompting scenarios, and then obtains the feedback index after comprehensive calculation. The comparison between the feedback index and the feedback threshold can accurately and effectively reflect the driver's satisfaction. The digital twin technology and machine learning algorithm are used to analyze and process the traffic flow data in different scenarios in real time, dynamically optimize the prompt instructions, and improve the overall intelligence level and adaptive ability. According to the feedback index and traffic flow data, the optimization frequency is generated, which can ensure the effectiveness of the prompt instructions to a certain extent and improve the driver's satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a schematic diagram of the modular structure of the highway multi-scenario comprehensive application platform based on digital twins in the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Example 1: Please refer to Figure 1 This embodiment provides a highway multi-scenario comprehensive application platform based on digital twins. The application platform includes a scenario calibration module, an application prompt module, and a feedback statistics module. The entire application platform uses data twin technology to simulate corresponding scenarios for various scenarios of highways, and can perform subsequent analysis or prediction based on the simulated simulation scenarios. It can provide powerful decision-making assistance for both managers and drivers, realizing the development of an intelligent platform;

[0055] The scene calibration module obtains the navigation data of any driver and combines it with digital twin technology to identify and mark the prompt scenes on the corresponding navigation route. The prompt scenes include highway intersection scenes, highway tunnel scenes, and highway toll station scenes.

[0056] Among them, the navigation data adopts GNSS+inertial navigation fusion positioning;

[0057] NSS+INS fusion positioning is a positioning technology that uses the fusion of the global navigation satellite system (GNSS) and the inertial navigation system (INS). It combines two different positioning methods to improve the accuracy and reliability of position information in a complementary way; the fusion process usually uses filters or optimization algorithms, such as extended Kalman filters (EKF) or particle filters. These algorithms perform weighted fusion of the measurement results of GNSS and inertial navigation systems to obtain more accurate and stable position estimates;

[0058] Based on the navigation data, the locations of all kinds of intersections on the navigation route can be monitored. Combined with the digital twin, a 3D model of the intersection can be established to simulate the real-time driving trajectories of various vehicles, and then the highway intersection scene can be obtained;

[0059] Based on the navigation data, the location and length information of each tunnel on the navigation route can be monitored. Combined with the digital twin, a 3D model of the interior of the tunnel can be established to simulate the real-time driving trajectory of various vehicles, and then the highway tunnel scene can be obtained;

[0060] Based on navigation data, the location of each toll station on the navigation route can be monitored. Combined with digital twins, a 3D model of the toll station can be established to simulate the real-time driving trajectory of various vehicles, and then the highway toll station scene can be obtained;

[0061] In short, by using digital twin technology combined with high-precision navigation data, corresponding problems in various highway scenarios can be discovered in advance through real-time simulation. This is suitable for newly built highways and can also be used to optimize and upgrade existing highways.

[0062] The application prompt module is used. When the driver is driving normally on the highway, it is estimated that the marked point on the navigation route will pass by S meters ahead. If the marked point is a highway intersection scene, the traffic density of the highway intersection scene is remotely obtained from the remote control center through wireless networking technology. When the traffic density exceeds the standard density value, the lane change prompt instruction is triggered. When the traffic density does not exceed the standard density value, the deceleration prompt instruction is triggered;

[0063] The normal driving process of the driver on the expressway means that the driver drives at a speed between 80 kilometers per hour and 120 kilometers per hour on the expressway, and the maximum speed limit on the expressway is 120 kilometers per hour;

[0064] Mark the corresponding scene S meters ahead on the navigation route, and the corresponding scene is the marked point;

[0065] The value of S in the S meters ahead is at least 100 meters, and the purpose of providing the relevant information of the marked point in advance is to make corresponding prompt operations in advance and reserve time for the driver to respond, thereby ensuring the safety of the driving process;

[0066] The remote control center is the road monitoring center, which is similar to a workstation and command center. It is also equipped with various sensors or cameras in the corresponding scenes to complete the monitoring of the required parameters or real-time data in the scene.

[0067] Wireless networking technology refers to the technology that uses wireless communication to achieve data transmission and network connection between devices. For moderate distances, cellular networks can be used, and for long distances, satellite communications can be used.

[0068] Cellular network is a technology that provides wide-area wireless communication services through cellular base stations, including different generations of mobile communication technologies, such as: 2G: provides basic voice and text messaging services; 3G: supports higher-speed data transmission and enables mobile Internet; 4G: provides higher-speed data transmission and better network coverage, widely used in smartphones, tablets, etc.; 5G: the latest generation of mobile communication technology, with higher speed, lower latency and wider connectivity, supporting applications such as the Internet of Things and smart city transportation; Satellite communication uses satellites in Earth orbit to achieve wide-area wireless communication. Its main features include: Wide coverage: can cover most areas of the earth, including oceans and remote areas; Applications: Internet access in remote areas, Global Positioning System (GPS), urban transportation, etc.

[0069] Traffic density refers to the number of vehicles on a highway per unit length, usually expressed in vehicles per kilometer. In order to improve the monitoring accuracy of traffic density, the data from traffic monitoring cameras and wireless sensor networks are combined, where the data obtained from the wireless sensor network is used for verification, and the calculation formula for traffic density is as follows:

[0070] Vk=sc / lr;

[0071] In the formula, Vk represents the traffic density, sc represents the number of vehicles passing through per unit time, and lr represents the length of the highway intersection section; the traffic monitoring cameras installed at the intersection and the road are used to collect video data, and the specific steps are: deploy cameras to cover the intersection section; use video processing software to detect and count vehicles; regularly analyze video data, extract vehicle quantity and speed information to calculate traffic density; the wireless sensor network used in the verification is as follows: use wireless sensor networks (such as radars, infrared sensors) to monitor traffic; deploy wireless sensor nodes to cover the intersection section; the sensors collect vehicle data in real time, such as the number of passes and speed; transmit the data to the central processing system for analysis, and verify the calculated traffic density with the aforementioned traffic density;

[0072] When the traffic density exceeds the standard density value, the triggered lane change prompt instruction is: the corresponding driver is prompted by voice to change lanes to the side away from the intersection, and the driver can make actual adjustments according to the situation; when the traffic density does not exceed the standard density value, the triggered deceleration prompt instruction is: the corresponding driver is prompted by voice that there is an intersection ahead and needs to slow down, and the driver can make actual adjustments according to the situation;

[0073] If the marked point is a highway tunnel scene, the safety data set of the highway tunnel scene is remotely obtained from the remote control center through wireless networking technology, and the safety data set includes the traffic density value, the internal lighting value and the ventilation value. Based on the pre-processed safety data set, the safety index I of the marked point is generated. When the safety index I exceeds the preset safety threshold, no response action is taken; when the safety index I does not exceed the preset safety threshold, the safety prompt instruction is triggered, and the corresponding driver is prompted by voice that there is an abnormality in the tunnel ahead and needs to reduce the speed and pay attention to the road conditions;

[0074] Among them, the traffic density value in the safety data set is the same as the traffic density in the highway intersection scene, and the acquisition principle is the same, so I will not elaborate on it here;

[0075] The internal lighting value represents the lighting value in the highway tunnel, and the process of obtaining the lighting value is: install brightness sensors at equal intervals in the highway tunnel, extract the minimum value of each brightness data, and calculate the lighting value in combination with the standard brightness. The formula is as follows:

[0076] Zm=|dz min -Bd|;

[0077] Where Zm represents the lighting value, dz min It represents the minimum brightness in the highway tunnel, and Bd represents the preset standard brightness, that is, the brightness required for normal lighting;

[0078] The internal ventilation value represents the ventilation value in the highway tunnel, and the process of obtaining the ventilation value is: wind speed sensors are installed at equal intervals in the highway tunnel, the minimum value of each wind speed data is extracted, and the wind speed value is calculated in combination with the standard wind speed. The formula is as follows:

[0079] Fs=|df min -Bf|;

[0080] Where Fs represents the wind speed value, df min It indicates the minimum wind speed in the highway tunnel, and Bf indicates the preset standard wind speed, i.e. the wind speed required for normal ventilation operation;

[0081] The formula for calculating the safety index I is as follows:

[0082] I = 1 / (αVt+βZm+γFs);

[0083] Wherein, Vt represents the traffic density value, α, β, γ are all weight coefficients, and 0<α≤1, 0<β≤1, 0<γ≤1, α+β+γ=1; each data in the safety data set is inversely proportional to the safety index I; the process of processing each parameter before calculating the safety index I is: normalization processing;

[0084] It should be noted that in the case of insufficient ventilation in the tunnel, necessary measures include reducing the speed of the vehicle: slowing down can reduce vehicle exhaust emissions and reduce the concentration of air pollutants.

[0085] If the marked point is a highway toll station scene, the pre-station data in the highway tunnel scene is remotely obtained from the remote control center through wireless networking technology, and the pre-station data includes the number of vehicles piled up in front of the station and the toll speed of each toll gate. Under the condition that the number of vehicles piled up in front of the station reaches the preset saturation value, the toll speed of each toll gate is compared to extract the top three toll gates with the highest toll speed as the calibrated toll gates, and trigger the guidance prompt instruction to prompt the corresponding driver to go to the calibrated toll gate through voice; for example: the toll speeds corresponding to toll gates 2, 3, and 5 in the toll station are ranked in the top three, so the voice prompts the driver to go to toll gates 2, 3, and 5;

[0086] The number of vehicles piled up in front of the station is obtained through high-definition cameras in front of the toll station. If the number of vehicles piled up in front of the station reaches the preset saturation value, it means that there is congestion in front of the station, so subsequent strategies need to be implemented. If the number of vehicles piled up in front of the station does not reach the preset saturation value, the system will not respond.

[0087] The method for obtaining the toll speed of each toll gate is as follows: obtain the number of vehicles passing through the corresponding toll gate every half hour, and divide the number of vehicles by thirty minutes to obtain the number of vehicles passing through the corresponding toll gate per minute, which is the toll speed of the corresponding toll gate; the toll gates with the top three toll speeds are the toll gates corresponding to the top three toll speeds in the corresponding toll station, after sorting the toll speeds from large to small.

[0088] Specifically, based on real-time traffic data and analysis results, it automatically sends intelligent instructions such as lane changing, deceleration, and safety reminders to the driver, enhancing the initiative of traffic management, obtaining traffic conditions and safety parameters for the corresponding scenarios ahead in advance, reserving sufficient reaction time for the driver, and guiding the driver to adopt appropriate driving strategies to reduce the risk of accidents. At the same time, it can effectively guide traffic flow and improve overall traffic efficiency.

[0089] The feedback statistics module obtains and calculates the feedback index P for each prompt scenario based on the feedback data of the corresponding driver in each prompt scenario among the preset M drivers. q , and each feedback index P q Compared with the preset feedback threshold, when the feedback index P q If the feedback index P is lower than the feedback threshold, it means that the feedback accuracy of the corresponding prompt scene meets the requirements and the system does not respond. q If it is not lower than the feedback threshold, it means that the feedback accuracy of the corresponding prompt scene does not meet or satisfy the requirements, triggering a warning signal and executing an optimization adjustment strategy;

[0090] The process of obtaining driver feedback data is as follows:

[0091] After the driver passes the marked point of the corresponding scene, the voice of the corresponding instruction before entering the marked point is sent to the driver to ask whether he is satisfied. If the driver does not respond or agree, it will not be counted in the feedback data. If the driver responds that he is not satisfied with the voice of the corresponding instruction, it will be counted in the feedback data of the corresponding scene.

[0092]

[0093] Where P q The q in represents the number of the corresponding prompt scene, and q = 1, 2, 3, P1 represents the feedback index in the highway intersection scene, P2 represents the feedback index in the highway tunnel scene, P3 represents the feedback index in the highway toll station scene, T i，q represents the feedback data of the i-th driver in the corresponding prompt scenario, and T i，q The value is 1 or 0, where i = 1, 2, ..., M, T avg，q represents the mean of the corresponding feedback data of M drivers in the corresponding prompt scenario, where M is a positive integer;

[0094] Feedback Index P q The larger the value, the worse the prompt instructions given to the driver by the corresponding prompt scene;

[0095] The process of executing the optimization adjustment strategy is as follows:

[0096] The digital twin technology is used to analyze and process the traffic flow data obtained in the corresponding prompt scene in real time, and the machine learning algorithm is used to optimize the traffic flow data. q and traffic flow data to generate the optimized frequency under the corresponding prompt scenario q ;According to the optimized frequencyOf q Carry out optimization processing;

[0097] Among them, the traffic flow data in the highway intersection scenario is: traffic density Vk;

[0098] The traffic flow data in the highway tunnel scenario are: safety index I;

[0099] The traffic flow data in the highway toll station scenario are: the maximum value of the toll speed;

[0100] Calculate the optimization frequencyOf q The formula is as follows:

[0101] Of q =G19w1P q +w2S q );

[0102] Where G1 is a constant correction coefficient, and its specific value can be adjusted and set by the user, or generated by analytical function fitting, Sj q represents the traffic flow data under the corresponding prompt scenario, w1 and w2 are the preset proportional coefficients of the feedback index and the traffic flow data, and w1>w2>0; it should be noted that the calculation optimization frequency Of q Before that, each parameter needs to be normalized;

[0103] Specifically, by obtaining the feedback data of the driver in different prompt scenarios and then performing comprehensive calculations to obtain the feedback index, the comparison between the feedback index and the feedback threshold can accurately and effectively reflect the driver's satisfaction. By using digital twin technology and machine learning algorithms, the traffic flow data in different scenarios can be analyzed and processed in real time, and the prompt instructions can be dynamically optimized to improve the overall intelligence level and adaptability. According to the feedback index and traffic flow data, the optimization frequency is generated, which can ensure the effectiveness of the prompt instructions to a certain extent and improve the driver's satisfaction.

[0104] Example 2: Based on Example 1, this example also provides a highway multi-scenario comprehensive application method based on digital twins, including the following specific steps:

[0105] S1. Obtain navigation data of any driver and combine it with digital twin technology to identify and mark prompt scenes on the corresponding navigation route, and the prompt scenes include highway intersection scenes, highway tunnel scenes and highway toll station scenes;

[0106] S2. When the driver is driving normally on the highway, it is estimated that the driver will pass a marked point on the navigation route S meters ahead. If the marked point is a highway intersection scene, the traffic density is obtained, the traffic density is compared with the standard density value, and the corresponding first prompt instruction is executed according to the comparison result;

[0107] If the marked point is a highway tunnel scene, a safety data set is obtained, and a safety index I under the marked point is generated based on the preprocessed safety data set. The safety index I is compared with the safety threshold, and the corresponding second prompt instruction is executed according to the comparison result;

[0108] If the marked point is a highway toll station scene, the pre-station data is obtained, and the pre-station data includes the number of vehicles piled up in front of the station and the toll speed of each toll gate. When the number of vehicles piled up in front of the station reaches the preset saturation value, the toll speed of each toll gate is compared to extract the top three toll gates in terms of toll speed as the calibration toll gates, and trigger the guidance prompt instruction;

[0109] S3. Obtain and calculate the feedback index P for each prompting scenario based on the feedback data of the corresponding driver in each prompting scenario from among the preset M drivers. q , and each feedback index P q Compare with the preset feedback threshold and execute the corresponding strategy according to the comparison result.

[0110] In the application, the several formulas involved are all calculated by removing the dimensions and taking their numerical values. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The formula is set by technical personnel in this field according to actual conditions.

[0111] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A multi-scenario integrated application platform for highways based on digital twins, characterized by: The platform includes: The scene calibration module obtains the navigation data of any driver and combines it with digital twin technology to identify and mark the prompt scenes on the corresponding navigation route. The prompt scenes include highway intersection scenes, highway tunnel scenes, and highway toll station scenes. The application prompt module is used to, when the driver is driving normally on the highway, it is estimated that the marked point on the navigation route will pass by S meters ahead. If the marked point is a highway intersection scene, the traffic density is obtained, the traffic density is compared with the standard density value, and the corresponding first prompt instruction is executed according to the comparison result; If the marked point is a highway tunnel scene, a safety data set is obtained, and a safety index I under the marked point is generated based on the preprocessed safety data set. The safety index I is compared with the safety threshold, and the corresponding second prompt instruction is executed according to the comparison result; If the marked point is a highway toll station scene, the pre-station data is obtained, and the pre-station data includes the number of vehicles piled up in front of the station and the toll speed of each toll gate. When the number of vehicles piled up in front of the station reaches the preset saturation value, the toll speed of each toll gate is compared to extract the top three toll gates in terms of toll speed as the calibration toll gates, and trigger the guidance prompt instruction; The feedback statistics module obtains and calculates the feedback index P for each prompt scenario based on the feedback data of the corresponding driver in each prompt scenario among the preset M drivers. q , and each feedback index P q Compare with the preset feedback threshold and execute corresponding strategies according to the comparison results; Feedback Index P q The calculation method is as follows: Where P q The q in represents the number of the corresponding prompt scene, and q = 1, 2, 3, P1 represents the feedback index in the highway intersection scene, P2 represents the feedback index in the highway tunnel scene, P3 represents the feedback index in the highway toll station scene, T i，q represents the feedback data of the i-th driver in the corresponding prompt scenario, where i = 1, 2, ..., M, T avg，q It represents the mean of the corresponding feedback data of M drivers in the corresponding prompt scenario.

2. The highway multi-scenario comprehensive application platform based on digital twin according to claim 1 is characterized by: Mark the corresponding scene S meters ahead on the navigation route, and the corresponding scene is the marked point, and the value of S in S meters ahead is at least 100.

3. The highway multi-scenario comprehensive application platform based on digital twin according to claim 2 is characterized by: Traffic density refers to the number of vehicles per unit length of highway, and the calculation formula of traffic density is as follows: Vk=sc / lr; Where Vk represents the traffic density, sc represents the number of vehicles passing through per unit time, and lr represents the length of the highway intersection section.

4. The highway multi-scenario comprehensive application platform based on digital twin according to claim 3 is characterized by: The process of executing the corresponding first prompt instruction according to the comparison result is as follows: When the traffic density exceeds the standard density value, the triggered lane change prompt instruction is: the corresponding driver is prompted by voice to change lanes to the side away from the intersection; when the traffic density does not exceed the standard density value, the triggered deceleration prompt instruction is: the corresponding driver is prompted by voice that there is an intersection ahead and needs to slow down.

5. The highway multi-scenario comprehensive application platform based on digital twin according to claim 4 is characterized by: The safety data set includes traffic density values, interior lighting values, and interior ventilation values, and the traffic density values ​​are the same as those in the highway intersection scenario.

6. The highway multi-scenario comprehensive application platform based on digital twin according to claim 5 is characterized by: The internal lighting value represents the lighting value in the highway tunnel, and the process of obtaining the lighting value is: install brightness sensors at equal intervals in the highway tunnel, extract the minimum value of each brightness data, and calculate the lighting value in combination with the standard brightness. The formula is as follows: Zm=∣dz min -Bd∣; Where Zm represents the lighting value, dz min It indicates the minimum brightness in the highway tunnel, and Bd indicates the preset standard brightness; The internal ventilation value represents the ventilation value in the highway tunnel, and the process of obtaining the ventilation value is: wind speed sensors are installed at equal intervals in the highway tunnel, the minimum value of each wind speed data is extracted, and the wind speed value is calculated in combination with the standard wind speed. The formula is as follows: Fs=∣df min -Bf∣; Where Fs represents the wind speed value, df min It indicates the minimum wind speed in the highway tunnel, and Bf indicates the preset standard wind speed.

7. The highway multi-scenario comprehensive application platform based on digital twin according to claim 6 is characterized by: The formula for calculating the safety index I is as follows: I = 1 / (αVt+βZm+γFs); Where Vt represents the traffic density value, α, β, γ are all weight coefficients, and 0<α≤1, 0<β≤1, 0<γ≤1; The process of executing the corresponding second prompt instruction according to the comparison result is as follows: When the safety index I exceeds the preset safety threshold, no response action is taken; when the safety index I does not exceed the preset safety threshold, a safety prompt instruction is triggered, and the corresponding driver is prompted by voice that there is an abnormal situation in the tunnel ahead and needs to reduce the speed and pay attention to the road conditions.

8. The highway multi-scenario comprehensive application platform based on digital twin according to claim 7 is characterized by: The method for obtaining the toll speed of each toll gate is: obtain the number of vehicles passing through the corresponding toll gate every half hour, and divide the number of vehicles by thirty minutes, then you can get the number of vehicles passing through the corresponding toll gate per minute, which is the toll speed of the corresponding toll gate; the triggered guidance prompt instruction is: prompt the corresponding driver to go to the calibrated toll gate through voice.

9. The highway multi-scenario comprehensive application platform based on digital twin according to claim 8 is characterized by: The process of obtaining driver feedback data is as follows: After the corresponding driver passes the marked point of the corresponding prompt scene, a voice message is sent to the corresponding driver to ask whether he is satisfied with the corresponding instruction before entering the marked point. If there is no response or recognition, it will not be counted in the feedback data. If the feedback is dissatisfied with the voice message of the corresponding instruction, it will be recorded in the feedback data of the corresponding scene.

10. The highway multi-scenario comprehensive application platform based on digital twin according to claim 9 is characterized by: The process of executing the corresponding strategy according to the comparison results is as follows: Each feedback index P q Compared with the preset feedback threshold, when the feedback index P q If the feedback index P is lower than the feedback threshold, no response action will be taken; q If it is not lower than the feedback threshold, a warning signal is triggered and an optimization adjustment strategy is executed; The process of executing the optimization adjustment strategy is as follows: The digital twin technology is used to analyze and process the traffic flow data obtained in the corresponding prompt scene in real time, and the machine learning algorithm is used to optimize the traffic flow data. q and traffic flow data to generate the optimized frequency under the corresponding prompt scenario q , and follow the optimized frequency Of q Carry out optimization processing; Among them, the traffic flow data in the highway intersection scenario is: traffic density Vk; The traffic flow data in the highway tunnel scenario are: safety index I; The traffic flow data in the highway toll station scenario are: the maximum value of the toll speed; Calculate the optimization frequencyOf q The formula is as follows: Of q =G1(w1P q +w2Sj q ); In the formula, G1 is the constant correction coefficient, Sj q It represents the traffic flow data under the corresponding prompt scenario, w1 and w2 are the preset proportional coefficients of the feedback index and the traffic flow data respectively, and w1>w2>0.

Images