Simulation practical training method, system and equipment based on digital twinning

Abstract

The invention relates to the field of simulation education, in particular to a simulation practical training method, system and equipment based on digital twinning, and aims to monitor a target user, collect and analyze driving behavior data of the target user in real time and construct and apply a digital twinning model through target equipment, so that the operation state of the target user can be effectively monitored; and an alarm prompt is sent when an abnormal operation state is detected, a simulation result report is generated through the driving environment and subsequent driving behaviors of the target user of the digital twin model, the target user is helped to predict subsequent possible dangerous conditions, the target user can reduce dangerous driving behaviors in the subsequent actual driving process, and the driving safety of the target user is improved. Safety self-rescue knowledge is added in the simulation practical training method, and the self-rescue ability of the target user in an emergency is enhanced.

Description

Technical Field

[0001] The present application relates to the technical field of simulation education, and in particular to a simulation training method, system and equipment based on digital twins. Background Art

[0002] With the increasing demand for driving training, traditional driving training methods mainly rely on real car operation and simulator training. However, real car operation has high safety risks and cost issues, while traditional simulator training has certain limitations in terms of realism and scene coverage, and it is difficult to meet the needs of complex and changing driving environments.

[0003] In recent years, digital twin technology has been gradually applied to various fields. By creating virtual models to map objects and environments in the real world in real time, it provides new possibilities for simulation training. However, the driving simulation training system based on digital twin technology on the market is still imperfect, especially in terms of scene diversity and real-time feedback. Therefore, the development of a driving simulation training system that can cover a variety of complex scenes and provide real-time feedback has become an urgent problem to be solved. Summary of the invention

[0004] In order to meet the needs of driving simulation learning that can cover a variety of complex scenarios and provide real-time feedback, the present application provides a simulation training method and related equipment based on digital twins.

[0005] In the first aspect, the present application provides a simulation training method based on digital twins, which adopts the following technical solutions:

[0006] A simulation training method based on digital twins is applied to a target device, where the target device is used to monitor a target user. The method includes:

[0007] Collect the target user's driving behavior data in real time, and analyze the target user's operating status in real time through the driving behavior data;

[0008] Determine whether the operation status is at an abnormal threshold;

[0009] If the operating status is outside the normal threshold, the target device sends an alarm prompt message.

[0010] Furthermore, a simulation training method based on digital twins analyzes the operating status of the target user in real time through driving behavior data, including:

[0011] Build a digital twin model;

[0012] Simulate the target user’s driving environment through a digital twin model;

[0013] Input driving behavior data into the digital twin model to update the target user’s operating status in real time;

[0014] Simulate the target user's subsequent driving behavior, analyze the simulation results, and generate a simulation result report.

[0015] Furthermore, a simulation training method based on digital twins is used to construct a digital twin model, including:

[0016] Obtain vehicle performance data and historical parameters of surrounding environmental elements;

[0017] Get current real-time environmental data through network-connected devices;

[0018] Combining historical parameters and real-time environmental data, digital fusion technology and artificial intelligence algorithms are used to build a digital twin model;

[0019] Update digital twin models in real time.

[0020] Furthermore, a simulation training method based on digital twins, an artificial intelligence algorithm constructs a digital twin model including a neural network model, including:

[0021] The neural network model includes at least one single neuron. The calculation formula of a single neuron is:

[0022]

[0023] Where: y is the output of the neuron, f is the activation function, w i is the i-th input x i The weight of x i is the ith input, b is the bias term, and n is the number of inputs.

[0024] Furthermore, a simulation training method based on digital twins is used to determine whether the operation state is within an abnormal threshold, including:

[0025] Obtain historical driving behavior data and operation status analysis results;

[0026] Determine standard values ​​for operating states;

[0027] Adjust the abnormal threshold based on the personalized differences of target users;

[0028] Update the abnormal threshold regularly.

[0029] Furthermore, a simulation training method based on digital twins also includes:

[0030] Identify special scenarios, and set up a safety self-rescue knowledge base and emergency response process for special scenarios;

[0031] If it is detected that the target user is currently in a special scenario, the emergency response process will be initiated immediately;

[0032] Monitor in real time whether the target user follows the emergency response process.

[0033] Furthermore, a simulation training method based on digital twins also includes:

[0034] If the target user fails to follow the emergency response process, a distress signal is automatically sent to the emergency service center through the target device;

[0035] Record the emergency response process steps that are not initiated by the target user in real time, upload the data and mark the emergency response process steps.

[0036] In a second aspect, the present application provides a simulation training system based on digital twins, comprising:

[0037] A data collection module, used to collect the driving behavior data of the target user in real time, and analyze the operating status of the target user in real time through the driving behavior data;

[0038] An operation determination module, used to determine whether the operation state is within an abnormal threshold;

[0039] The prompt information module is used for the target device to send an alarm prompt information if the operation state is at an abnormal threshold.

[0040] In a third aspect, the present disclosure provides a computer device including a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of a simulation training method based on digital twins in any of the above-mentioned embodiments when executing the computer program.

[0041] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a simulation training method based on digital twins in any of the above embodiments are implemented.

[0042] The above-mentioned simulation training method based on digital twins monitors the target user through the target device, collects and analyzes the target user's driving behavior data in real time, builds and applies the digital twin model, can effectively monitor the target user's operating status, and send an alarm prompt when an abnormal operating status is detected. Through the digital twin model, the target user's driving environment and subsequent driving behavior are generated, and a simulation result report is generated to help the target user predict the dangerous situations that may occur in the future, so that the target user can reduce dangerous driving behaviors in the actual driving process in the future. Safety self-rescue knowledge is added to the simulation training method to enhance the target user's self-rescue ability in emergency situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1The main flow chart of a simulation training method based on digital twin in an embodiment.

[0044] Figure 2 The first flowchart of a simulation training method based on digital twins in an embodiment.

[0045] Figure 3 It is a structural schematic diagram of a simulation training system based on digital twin in one embodiment.

[0046] Figure 4 Schematic diagram of the internal structure of a computer device in one embodiment.

[0047] In the drawings, the same reference numerals are used for the same components, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0050] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] Embodiment 1

[0052] Please refer to Figure 1 In one embodiment of the present application, a simulation training method based on digital twins is applied to a target device, and the target device is used to monitor a target user, including steps S101 to S103:

[0053] Step S101: collecting driving behavior data of a target user in real time, and analyzing the operating status of the target user in real time through the driving behavior data.

[0054] Among them, the driving behavior data includes data related to driving behavior, such as the steering wheel swing angle, the distance between the vehicle and the left and right guide lane lines, the vehicle start time, the vehicle speed and the vehicle braking distance.

[0055] Specifically, the vehicle sensors are used to collect the target user's driving behavior data in real time, and the collected driving behavior data is uploaded to the data processing center. The data processing center analyzes the driving behavior data. Through real-time analysis of the driving behavior data, we can understand the target user's operating habits, skill level, and whether there is any bad driving behavior such as fatigue driving and distracted driving.

[0056] The purpose of step S101 is to monitor the behavior of the target user in real time to ensure safety during driving.

[0057] Step S102: Determine whether the operation status is within an abnormal threshold.

[0058] The abnormal threshold refers to exceeding or falling below a preset safety range.

[0059] Specifically, the target user's current driving behavior data is monitored in real time and compared with the safety range pre-set by the data processing center to determine whether the current target user's operating status exceeds or falls below the pre-set safety value.

[0060] For example, the abnormal threshold is set to continuous driving time exceeding 3 hours, the target user's blinking frequency is lower than the normal level, and the current data is collected in real time using sensors and monitors. It is monitored that the target user has been driving for 5 hours in a row and the blinking frequency is abnormally low. The system determines that the target user may be in a fatigued state and the operating status has exceeded the normal threshold. Measures need to be taken to prevent accidents caused by fatigue driving.

[0061] The abnormal threshold is set to that if the distance between the two sides of the vehicle and the guide lane lines on either side is lower than the normal range within a continuous period of time, it is judged that the current vehicle is close to another lane and the current operating state has the risk of an accident, and the target user needs to be prompted to adjust the driving trajectory.

[0062] The function of step S102 is to identify and evaluate whether the operation status of the target user exceeds a preset safety range.

[0063] Step S103: If the operation status is at an abnormal threshold, the target device sends an alarm prompt message.

[0064] Among them, the target devices include vehicle-mounted display screens, virtual reality devices, smart phones and other devices that have the function of interacting with the target users.

[0065] Specifically, when the system determines that the target user's operating status is at an abnormal threshold, the target device will immediately send an alarm prompt message, which will be displayed through voice prompts and visual screens to ensure that the target user can be informed of potential dangers in a timely manner, allowing the target user to take quick measures to reduce the occurrence of accidents.

[0066] The purpose of step S103 is to help improve the safety awareness of target users and encourage them to correct bad driving habits by sending alarm prompt information to the target device.

[0067] Through the above technical solutions, a simulation training method based on digital twins can simulate the monitoring and feedback mechanism in the real driving environment and provide instant operation guidance for the target users. In a safe virtual environment, the target users can practice repeatedly and receive alarm prompts about abnormal operation status, so as to learn how to deal with various emergencies without causing actual danger. It can achieve the key link of real-time intervention and improve the training effect, ensuring that the target users can get effective safety warnings and operation guidance in the simulation environment.

[0068] In one embodiment, if Figure 2 As shown, in S101, that is, in real-time analysis of the operating state of the target user through driving behavior data, the following steps are included:

[0069] Step S201: Build a digital twin model.

[0070] Step S202: Simulate the target user's driving environment through the digital twin model.

[0071] Step S203: Input the driving behavior data into the digital twin model and update the operating status of the target user in real time.

[0072] Step S204: simulate the subsequent driving behavior of the target user, analyze the simulation results, and generate a simulation result report.

[0073] Specifically, an accurate virtual model corresponding to the real vehicle and its driving environment is created, and the same conditions as the actual driving environment of the target user are set in the virtual environment, such as night, rainy days, specific roads, etc. The actual driving data of the target user (such as steering wheel rotation angle, accelerator and brake usage) is input into the model to simulate the user's driving behavior in real time. The user's future behavior under the current operating state is predicted, and possible results are analyzed, such as whether the lane will be maintained and whether obstacles can be avoided in time.

[0074] The purpose of steps S201 to S204 is that the method simulates different driving environments and conditions, evaluates the safety risks of the target user in these situations, analyzes the operating behavior of the target user, identifies situations that may lead to danger, and provides improvement suggestions.

[0075] In one embodiment, in S201, i.e., in building the digital twin model, the following steps are also included:

[0076] Step S301: Acquire vehicle performance data and historical parameters of surrounding environment elements.

[0077] Step S302: Acquire current real-time environmental data through a network connection device:.

[0078] Step S303: Combine historical parameters and real-time environmental data, and apply digital fusion technology and artificial intelligence algorithms to build a digital twin model.

[0079] Step S304: Update the digital twin model in real time.

[0080] Among them, the digital twin model refers to the use of digital technology to build a dynamic digital model in a virtual space that is highly mirrored of the physical entity.

[0081] Specifically, historical performance data of the vehicle (such as engine efficiency, tire wear, etc.) and historical environmental parameters (such as road conditions, traffic flow, weather patterns, etc.) are collected to provide basic data support for building a digital twin model. Then, network-connected devices such as sensors, cameras, and GPS are used to collect real-time environmental data of the vehicle (such as current weather, road wetness, traffic conditions, etc.) to ensure that the digital twin model can reflect the latest environmental conditions. Through digital fusion technology, historical data is combined with real-time data, and artificial intelligence algorithms are used to process and analyze these data to build a digital twin model that can simulate the real behavior of the vehicle and its environment. As the vehicle and environmental data continue to change, the digital twin model is updated in real time to ensure the accuracy and timeliness of the model.

[0082] The purpose of steps S301 to S304 is that the method builds and updates in real time a highly accurate and dynamic digital twin model by integrating historical and real-time data and applying digital fusion technology and artificial intelligence algorithms.

[0083] In one embodiment, in S303, the artificial intelligence algorithm constructs a digital twin model including a neural network model, including the following steps:

[0084] Step S401: The neural network model includes at least one single neuron, and the calculation formula of the single neuron is:

[0085]

[0086] Where: y is the output of the neuron, f is the activation function, w i is the i-th input x i The weight of x i is the ith input, b is the bias term, and n is the number of inputs.

[0087] Specifically, neurons are the basic units for information processing in neural networks. They can receive multiple inputs, perform linear combinations through weights and biases, and perform nonlinear transformations through activation functions, thereby approximating complex functions. By combining multiple such neurons, a multi-layer neural network can be constructed to solve classification, regression, and clustering machine learning problems.

[0088] For example, suppose we are building a neural network model to predict the fuel consumption of a vehicle in the future. This prediction model needs to consider multiple inputs, such as vehicle speed, engine speed, road slope, etc.

[0089] Input: vehicle speed x1, engine speed x2, road slope x3.

[0090] Weights: w1, w2, and w3 correspond to the weights of the three inputs respectively.

[0091] Bias: b is a constant used to adjust the activation threshold of the neuron.

[0092] Activation function: f may be a Sigmoid function, which is used to limit the output of the neuron to between 0 and 1, indicating the predicted value of fuel consumption.

[0093] Calculate the weighted sum of each input (w1x1+w2x2+w3x3+b), which represents the linear relationship between the vehicle's fuel consumption and each factor. Apply the activation function f to introduce nonlinear factors, allowing the neural network to capture more complex fuel consumption patterns. Generate a predicted value y, which can be used to estimate the vehicle's fuel consumption under given input conditions.

[0094] The purpose of step S401 is that the method can learn and optimize weights and biases through a neural network model to minimize prediction errors, and ultimately provide a tool for accurately predicting vehicle fuel consumption and accurately simulating the real behavior of the vehicle and its environment.

[0095] In one embodiment, in S102, i.e., determining whether the operation state is within an abnormal threshold, the following steps are included:

[0096] Step S501: Acquire historical driving behavior data and operation status analysis results.

[0097] Step S502: Determine the standard value of the operating state.

[0098] Step S503: adjusting the abnormal threshold based on the personalized differences of the target user.

[0099] Step S504: regularly update the abnormal threshold.

[0100] Specifically, collect and analyze past driving behavior data and previous operating status analysis results to provide a basis for determining standard values ​​and abnormal thresholds. Based on historical data analysis, set one or more standard values ​​for operating states that represent the range of normal driving behavior. Consider the individual differences of different target users, such as driving skills, habits, and preferences, and make personalized adjustments to the abnormal thresholds to improve the accuracy and adaptability of the monitoring system. As time goes by and data accumulates, regularly update the abnormal thresholds to ensure that the monitoring system can reflect the latest driving behavior and operating status of the target users.

[0101] For example: suppose in the simulation system, a target user often shows signs of fatigue when driving at night, such as frequent blinking and head tilt. By obtaining historical driving behavior data, the system determines the standard state of normal night driving. According to the personalized differences of the target user (such as working hours, work and rest habits), the abnormal threshold is adjusted so that the system believes that the target user is more sensitive to fatigue driving. After that, the system will regularly update these thresholds based on the latest driving data to ensure the accuracy of monitoring.

[0102] The purpose of steps S501 to S504 is that the method analyzes historical data, sets and adjusts standard values ​​and abnormal thresholds of operating states, so as to achieve personalized monitoring and optimize the safety of driving behavior.

[0103] In one embodiment, the following steps are also included:

[0104] Step S601: Identify special scenarios, and set up a safety self-rescue knowledge base and emergency response process for special scenarios.

[0105] Step S602: If it is detected that the target user is currently in a special scenario, the emergency response process is immediately initiated.

[0106] Step S603: monitor in real time whether the target user operates according to the emergency response process.

[0107] Among them, special scenarios refer to scenarios that vehicles may encounter under special circumstances such as vehicle loss of control, tire blowout, water entry, landslide, fire, etc.

[0108] Specifically, safety measures and self-rescue methods for different special driving scenarios (such as vehicle loss of control, tire blowout, flood, landslide, etc.), as well as necessary emergency response steps are set and prepared in the virtual space. When the target user is detected in a preset special scenario, the system automatically activates the emergency response process, and the target user performs self-rescue by operating the vehicle to ensure that the target user follows the correct emergency steps. If the target user's operation does not comply with the emergency response process, the system can issue a warning or take other measures in a timely manner.

[0109] For example, in the simulation system, a vehicle is set to have a tire blowout while driving at high speed. The safety self-rescue knowledge base includes steps such as how to keep the steering wheel steady, slow down slowly, avoid sudden braking, and drive safely to the emergency lane. The emergency response process requires the target user to complete the entire operation process from the occurrence of a tire blowout to safe parking.

[0110] The system detects that the vehicle suddenly deviates from the driving track and determines that a tire may have blown out. The system immediately initiates the emergency response process and guides the target user through voice prompts, screen displays, etc. The target user immediately stabilizes the direction of the vehicle, slowly decelerates, and safely drives to the emergency lane. If the vehicle is driving too fast, find the nearest vehicle escape lane.

[0111] The purpose of steps S601 to S603 is that the method identifies special driving scenarios, presets corresponding safety self-rescue knowledge bases and emergency response processes, and ensures that target users can receive timely guidance and take correct response measures when facing emergencies.

[0112] In one embodiment, the following steps are also included:

[0113] Step S701: If the target user fails to follow the emergency response process, a distress signal is automatically sent to an emergency service center through the target device.

[0114] Step S702: Record in real time the emergency response process steps that are not initiated by the target user, upload the data and mark the emergency response process steps.

[0115] Specifically, the target user failed to perform the correct operation according to the system prompts when the vehicle lost control. When the system detects that the target user's operation does not comply with the emergency response process, it immediately sends a distress signal to the emergency service center through the vehicle communication system. The emergency response steps that the target user did not perform are recorded and uploaded, providing important information for accident analysis, system improvement and target user training, and focusing on training for the next simulation training.

[0116] The purpose of step S701 to step S702 is that the method identifies the behavior patterns and potential problems of the target user in an emergency by recording and analyzing the unexecuted emergency response steps, and uses the collected data to improve the emergency response process to make it more in line with the actual operation needs of the target user.

[0117] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0118] Embodiment 2

[0119] In this embodiment, a simulation training system based on digital twins is provided, and the simulation training system based on digital twins corresponds one-to-one to the simulation training method based on digital twins in the above embodiment. Figure 3 As shown, the simulation training system based on digital twins includes a data collection module 101, an operation judgment module 102 and a prompt information module 103. The detailed description of each functional module is as follows:

[0120] The data collection module 101 is used to collect the driving behavior data of the target user in real time, and analyze the operating status of the target user in real time through the driving behavior data;

[0121] An operation determination module 102 is used to determine whether the operation state is within an abnormal threshold;

[0122] The prompt information module 103 is used to send an alarm prompt information to the target device if the operation status is at an abnormal threshold.

[0123] For the specific definition of a simulation training system based on digital twins, please refer to the definition of a simulation training method based on digital twins above, which will not be repeated here. Each module in the above-mentioned simulation training system based on digital twins can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the device in hardware form, or can be stored in the memory in the device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0124] Embodiment 3

[0125] In this embodiment, a computer device is provided. Its internal structure diagram can be shown as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program, and the non-volatile storage medium is deployed with a database, which is used to store all data involved in a simulation training method based on digital twins. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with other computer devices that deploy application software. When the computer program is executed by the processor, a simulation training method based on digital twins is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0126] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a simulation training method based on digital twins described in any of the above embodiments are implemented.

[0128] Embodiment 4

[0129] In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a simulation training method based on digital twins described in any of the above embodiments are implemented.

[0130] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0131] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A simulation training method based on digital twins, characterized in that: Applied to a target device, the target device is used to monitor a target user, the method comprises: Collecting driving behavior data of the target user in real time, and analyzing the operating status of the target user in real time through the driving behavior data; Determining whether the operation state is within an abnormal threshold; If the operating status is within an abnormal threshold, the target device sends an alarm prompt message.

2. A simulation training method based on digital twins according to claim 1, characterized in that: Analyzing the target user's operating status in real time through the driving behavior data includes: Build a digital twin model; Simulating the driving environment of the target user by using the digital twin model; Inputting the driving behavior data into the digital twin model to update the operation status of the target user in real time; Simulate the subsequent driving behavior of the target user, analyze the simulation results, and generate a simulation result report.

3. A simulation training method based on digital twins according to claim 2, characterized in that: The construction of the digital twin model includes: Obtain vehicle performance data and historical parameters of surrounding environmental elements; Get current real-time environmental data through network-connected devices; Combining the historical parameters and the real-time environmental data, applying digital fusion technology and artificial intelligence algorithms to construct the digital twin model; The digital twin model is updated in real time.

4. A simulation training method based on digital twins according to claim 3, characterized in that: The artificial intelligence algorithm constructs a digital twin model including a neural network model, including: The neural network model includes at least one single neuron, and the calculation formula of the single neuron is: Where: y is the output of the neuron, f is the activation function, w i is the i-th input x i The weight of x i is the ith input, b is the bias term, and n is the number of inputs.

5. The simulation training method based on digital twin according to claim 1 is characterized in that: The determining whether the operation state is within an abnormal threshold value includes: Obtain historical driving behavior data and operation status analysis results; determining a standard value for the operating state; Adjusting the abnormal threshold based on the personalized differences of the target users; Update the abnormal threshold regularly.

6. The simulation training method based on digital twin according to claim 1 is characterized in that: The method further comprises: Identify special scenarios and set up a safety self-rescue knowledge base and emergency response process for the special scenarios; If it is detected that the target user is currently in a special scenario, the emergency response process is immediately initiated; Monitor in real time whether the target user operates according to the emergency response process.

7. A simulation training method based on digital twins according to claim 6, characterized in that: The method further comprises: If the target user fails to operate according to the emergency response process, a distress signal is automatically sent to an emergency service center through the target device; The emergency response process steps that are not initiated by the target user are recorded in real time, and data is uploaded and marked.

8. A simulation training system based on digital twins, characterized in that: include: A data collection module, used to collect the driving behavior data of the target user in real time, and analyze the operating status of the target user in real time through the driving behavior data; An operation determination module, used to determine whether the operation state is within an abnormal threshold; The prompt information module is used for the target device to send an alarm prompt information if the operation state is at an abnormal threshold.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images