Intelligent safety helmet system suitable for electric motorcycle

Abstract

The invention provides an intelligent safety helmet system suitable for an electric motorcycle, which relates to the technical field of intelligent wearable equipment and mainly comprises a helmet shell, a sensor module, a communication module, a display and audio module, a central control module, a power supply module and a charging navigation module. The sensor module is responsible for collecting the motion state, the position, the environmental condition and the physiological state of a rider and transmitting data to the central control module. The module performs collision detection and life judgment by analyzing the data, and gives an alarm in time to remind a rider and surrounding people, so that the risk of accidents is reduced. And the charging navigation module performs optimal charging path planning based on the data, thereby helping the user to reduce the charging waiting time and improve the travel efficiency. And the display and audio module provides visual and real-time voice navigation to ensure that the rider can easily obtain navigation information in the driving process.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent wearable devices, and in particular to an intelligent safety helmet system suitable for electric motorcycles. Background Art

[0002] With the rapid development of urban transportation and the enhancement of environmental awareness, electric motorcycles have gradually become an important means of transportation for people's daily travel due to their low-carbon and convenient features. However, the popularity of electric motorcycles also brings safety hazards, especially in the complex traffic environment of the city, where riders face many risks.

[0003] In recent years, the rapid development of smart wearable devices has made it possible for helmets to be intelligent. By integrating sensors, communication modules and display technologies, smart helmets can achieve real-time monitoring and information feedback of riders. However, the existing smart helmet products on the market still have some shortcomings, such as single functions, poor user experience, and insufficient compatibility with electric motorcycles. And with the popularization of electric motorcycles, the layout of charging infrastructure and the charging needs of users have become important factors affecting their user experience. Existing path planning methods usually fail to fully consider the special energy consumption characteristics of electric motorcycles and the personalized needs of users, resulting in insufficient accuracy and practicality of charging path recommendations. Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide an intelligent safety helmet system suitable for electric motorcycles, which can perform collision detection and life judgment based on the collected data, issue alarms in time to remind riders and surrounding personnel, reduce the risk of accidents, and provide users with optimal charging path planning based on real-time driving data and charging station distribution data, thereby reducing charging waiting time and improving travel efficiency.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] An intelligent safety helmet system suitable for an electric motorcycle comprises: a helmet shell, a sensor module arranged in the helmet shell, a communication module, a display and audio module, a central control module, a power module and a charging navigation module;

[0007] The sensor module, the display and audio module, the central control module, the power module and the charging navigation module are connected to the communication module respectively; the sensor module is used to collect the motion state, position, environmental conditions and physiological state of the user of the helmet shell; the power module is used to supply power to the sensor module, the communication module, the display and audio module, the central control module and the charging navigation module; the central control module is used to receive the motion state, position, environmental conditions and physiological state of the helmet shell transmitted by the communication module, and perform collision detection and life judgment according to the motion state, position, environmental conditions and physiological state, obtain the detection and judgment results, and give an alarm reminder according to the detection and judgment results; the communication module is also connected to the vehicle system of the electric motorcycle corresponding to the helmet shell, and is used to obtain the real-time driving data, real-time traffic data and charging station distribution data of the electric motorcycle; the charging navigation module is used to plan the optimal charging path according to the real-time driving data, the real-time traffic data and the charging station distribution data, and obtain the optimal charging path; the display and audio module is used to perform visualization and real-time voice navigation according to the optimal charging path.

[0008] Preferably, the charging navigation module includes:

[0009] A traffic model building submodule is used to build a dynamic traffic model with dynamic changes in road network vehicle speed based on the real-time traffic data and a preset static road network;

[0010] A user behavior model establishment submodule, used to establish a user behavior analysis model based on preset historical riding data and user power preference data in the vehicle system;

[0011] The energy consumption prediction and path planning submodule is used to predict the energy consumption on different paths using a neural network based on the dynamic traffic model and the user behavior analysis model, score the paths according to user preferences and real-time traffic conditions, and comprehensively consider travel time, energy consumption, and convenience of charging stations to obtain path scores and predicted energy consumption;

[0012] The optimal route determination submodule is used to screen the paths according to the path score and the predicted energy consumption to obtain the optimal charging path.

[0013] Preferably, the road speed of the dynamic traffic model changes at intervals of 6 minutes, and there are 240 speed points in 24 hours a day.

[0014] Preferably, the central control module includes:

[0015] A data preprocessing submodule, for performing denoising processing on the sensor signals of the motion state, position, environmental conditions of the helmet shell and the physiological state of the user of the helmet shell to obtain a denoised signal;

[0016] A signal feature extraction submodule performs feature extraction on each of the denoised signals to obtain extracted risk features;

[0017] A feature fusion submodule is used to fuse the risk features to obtain a fusion feature;

[0018] A risk judgment submodule is used to input the fusion features into a trained electric vehicle driving risk assessment model to perform collision detection and life judgment to obtain a detection and judgment result;

[0019] The alarm module is used to issue an alarm reminder according to the detection and judgment results.

[0020] Preferably, the data preprocessing submodule includes:

[0021] A signal translation unit, used for performing translation on the denoised signal to obtain a translation signal;

[0022] A wavelet decomposition unit, used for performing wavelet decomposition on the translation signal to obtain a plurality of wavelet coefficients;

[0023] A threshold determination unit, used to determine a filtering threshold according to a decomposition scale and a length of a signal;

[0024] A function determination unit, used to construct a denoising function according to the filtering threshold;

[0025] The denoising unit is used to remove the noise of the translation signal by using the denoising function to obtain a denoised signal.

[0026] Preferably, the risk characteristics include: acceleration change rate, angular velocity, movement mode, GPS positioning data, geographical environment data, degree of deviation from the driving route, temperature, humidity, light, heart rate and body temperature.

[0027] Preferably, the communication module is also connected to the server wirelessly; the communication module is used to send the detection and judgment result to the server.

[0028] Preferably, the electric vehicle driving risk assessment model is obtained by training a CNN-LSTM network.

[0029] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0030] The present invention provides an intelligent safety helmet system suitable for electric motorcycles, comprising: a helmet shell, a sensor module, a communication module, a display and audio module, a central control module, a power module and a charging navigation module arranged in the helmet shell; the sensor module, the display and audio module, the central control module, the power module and the charging navigation module are respectively connected to the communication module; the sensor module is used to collect the motion state, position, environmental conditions of the helmet shell and the physiological state of the user of the helmet shell; the power module is used to supply power to the sensor module, the communication module, the display and audio module, the central control module and the charging navigation module; the central control module is used to receive the information transmitted by the communication module The motion state, position, environmental conditions and physiological state of the helmet shell user are input, and collision detection and life judgment are performed according to the motion state, position, environmental conditions and physiological state to obtain the detection and judgment results, and an alarm is given according to the detection and judgment results; the communication module is also connected to the vehicle system of the electric motorcycle corresponding to the helmet shell to obtain the real-time driving data, real-time traffic data and charging station distribution data of the electric motorcycle; the charging navigation module is used to plan the optimal charging path according to the real-time driving data, the real-time traffic data and the charging station distribution data to obtain the optimal charging path; the display and audio module is used to visualize and perform real-time voice navigation according to the optimal charging path. The present invention can perform collision detection and life judgment according to the collected data, issue an alarm in time, remind the rider and the surrounding personnel, reduce the risk of accidents, and can also provide users with optimal charging path planning according to real-time driving data and charging station distribution data, reduce charging waiting time, and improve travel efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0032] Figure 1 A schematic diagram of the system structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] 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.

[0034] The purpose of the present invention is to provide an intelligent safety helmet system suitable for electric motorcycles, which can perform collision detection and life judgment based on the collected data, issue alarms in time, remind riders and surrounding personnel, and reduce the risk of accidents. It can also provide users with optimal charging path planning based on real-time driving data and charging station distribution data, reduce charging waiting time, and improve travel efficiency.

[0035] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0036] Figure 1 A schematic diagram of the system structure provided by an embodiment of the present invention, such as Figure 1 As shown, the present invention provides an intelligent safety helmet system suitable for electric motorcycles, comprising: a helmet shell, a sensor module arranged in the helmet shell, a communication module, a display and audio module, a central control module, a power module and a charging navigation module;

[0037] The sensor module, the display and audio module, the central control module, the power module and the charging navigation module are connected to the communication module respectively; the sensor module is used to collect the motion state, position, environmental conditions and physiological state of the user of the helmet shell; the power module is used to supply power to the sensor module, the communication module, the display and audio module, the central control module and the charging navigation module; the central control module is used to receive the motion state, position, environmental conditions and physiological state of the helmet shell transmitted by the communication module, and perform collision detection and life judgment according to the motion state, position, environmental conditions and physiological state, obtain the detection and judgment results, and give an alarm reminder according to the detection and judgment results; the communication module is also connected to the vehicle system of the electric motorcycle corresponding to the helmet shell, and is used to obtain the real-time driving data, real-time traffic data and charging station distribution data of the electric motorcycle; the charging navigation module is used to plan the optimal charging path according to the real-time driving data, the real-time traffic data and the charging station distribution data, and obtain the optimal charging path; the display and audio module is used to perform visualization and real-time voice navigation according to the optimal charging path.

[0038] The working principle of the smart safety helmet system of this embodiment is to monitor the rider's status and environment in real time by integrating multiple sensors and modules, and perform data analysis and processing, thereby improving riding safety and user experience. The following is a detailed breakdown of the working principle of the system:

[0039] 1. Data collection and transmission. The core of the system lies in its sensor module, which has multiple sensors built in, including accelerometers, gyroscopes, GPS, environmental sensors, and physiological status monitors. The sensor module is responsible for real-time collection of the following data:

[0040] Movement status: The accelerometer and gyroscope monitor the acceleration, angular velocity and movement direction of the helmet to determine the rider's movement status.

[0041] Location: Use the GPS module to obtain the rider's real-time location to help analyze the riding route and environment.

[0042] Environmental conditions: Environmental sensors monitor environmental factors such as temperature, humidity, and light to assess the safety of the riding environment.

[0043] Physiological status: Physiological sensors (such as heart rate monitors) monitor the cyclist's physiological status in real time to ensure that his or her health is normal.

[0044] These data are transmitted to the central control module through the communication module to achieve real-time updating and processing of the data.

[0045] 2. Data processing and analysis: In the central control module, the received sensor data is denoised by the data preprocessing submodule to eliminate interference and noise in the sensor signal and obtain a more accurate denoised signal. Next, the system analyzes the denoised signal through the signal feature extraction submodule to extract key risk features. These features include:

[0046] Motion state characteristics: such as changes in acceleration and angular velocity, to determine whether there is abnormal movement (such as falling or collision).

[0047] Location characteristics: such as whether the cyclist is in a high-risk area (such as a busy traffic section).

[0048] Environmental characteristics: such as whether weather conditions are suitable for cycling.

[0049] Physiological characteristics: such as whether the heart rate is within the normal range.

[0050] The extracted risk features are then sent to the feature fusion submodule for feature fusion, which comprehensively considers the impact of each feature to form a comprehensive risk assessment model.

[0051] 3. Collision detection and life judgment, the fused features are input into the trained electric vehicle driving risk assessment module for collision detection and life judgment. The system analyzes the current motion state, position, environmental conditions and physiological state through the set thresholds and algorithms to determine whether a collision has occurred or whether the rider is in a dangerous state. If an abnormal acceleration change or an abnormal motion pattern is detected, the system will judge it as a possible collision event; if the physiological state (such as heart rate) is abnormal, the system will judge that the rider may have health problems. In this embodiment, based on the detection and judgment results, the system will trigger the alarm module and send an alarm to the rider through the display and audio modules to remind him to pay attention to safety or seek help.

[0052] 4. Charging navigation and route planning. In addition to safety monitoring, the system also has a charging navigation function. The communication module is connected to the electric motorcycle's onboard system to obtain real-time driving data, traffic data, and charging station distribution information. The charging navigation module plans the optimal charging route based on this data, taking into account the following factors:

[0053] Real-time driving data: current driving speed and remaining battery power.

[0054] Real-time traffic data: road conditions, traffic flow and other information.

[0055] Charging station distribution data: Location and availability of nearby charging stations.

[0056] By comprehensively analyzing this information, the system can provide riders with the best charging path, ensuring that they can find a charging station in time during driving and avoiding trouble caused by insufficient power.

[0057] 5. Visualization and real-time navigation. The display and audio modules of this embodiment are responsible for visualizing the optimal charging path and providing real-time voice navigation. Riders can view navigation information through the display screen inside the helmet, and the system will guide the rider to the destination through audio prompts. This intuitive navigation method not only improves the user experience, but also ensures that riders can focus on the road during driving, reducing the risk of distraction.

[0058] In summary, the intelligent safety helmet system of this embodiment provides comprehensive safety protection and convenient navigation services through real-time data collection, intelligent analysis and path planning. It not only improves the safety of riders, but also optimizes the user experience of electric motorcycles and promotes the development of intelligent transportation.

[0059] Preferably, the charging navigation module includes:

[0060] A traffic model building submodule is used to build a dynamic traffic model with dynamic changes in road network vehicle speed based on the real-time traffic data and a preset static road network;

[0061] A user behavior model establishment submodule, used to establish a user behavior analysis model based on preset historical riding data and user power preference data in the vehicle system;

[0062] The energy consumption prediction and path planning submodule is used to predict the energy consumption on different paths using a neural network based on the dynamic traffic model and the user behavior analysis model, score the paths according to user preferences and real-time traffic conditions, and comprehensively consider travel time, energy consumption, and convenience of charging stations to obtain path scores and predicted energy consumption;

[0063] The optimal route determination submodule is used to screen the paths according to the path score and the predicted energy consumption to obtain the optimal charging path.

[0064] Specifically, the charging navigation module of this embodiment works together through multiple sub-modules to recommend the optimal charging path for electric motorcycles. First, the traffic model establishment sub-module uses real-time traffic data and static road network information to build a dynamic traffic model to reflect changes in road network vehicle speeds. Next, the user behavior model establishment sub-module analyzes the user's travel habits and charging needs based on historical riding data and user power preferences in the vehicle system. Subsequently, the energy consumption prediction and path planning sub-module combines the dynamic traffic model and the user behavior analysis model, uses a neural network to predict the energy consumption of different paths, and scores feasible paths based on user preferences and real-time traffic conditions, taking into account travel time, energy consumption, and the convenience of charging stations. Finally, the optimal route determination sub-module selects the optimal charging path based on the path score and predicted energy consumption, ensuring that users can find charging stations efficiently and conveniently during travel, thereby improving the user experience and safety of electric motorcycles.

[0065] Furthermore, the process of establishing a user behavior analysis model in this embodiment first requires collecting and organizing the preset historical riding data and user power preference data in the vehicle system. The historical riding data includes information such as the user's riding frequency, driving route, driving time, speed change, charging habits, etc., which are obtained through the recording function of the vehicle system. The user's power preference data involves the user's preference for power usage, such as charging choices in different situations, preferences for charging stations (such as distance, charging speed, etc.), and sensitivity to driving time and energy consumption. Next, a machine learning algorithm (such as cluster analysis, decision tree, or the neural network used in this embodiment) is used to analyze these data to identify the user's riding pattern and charging behavior. Through feature extraction, the model can capture the user's decision-making logic in different situations, and then establish a dynamic user behavior analysis model that can be updated in real time and adapt to the user's changing needs, thereby providing personalized suggestions and optimization solutions for subsequent path planning and charging navigation.

[0066] Furthermore, this embodiment uses a neural network to predict energy consumption. The neural network predicts energy consumption on different paths by learning traffic patterns and user behaviors in historical data. This process requires a large amount of training data, including energy consumption records under different traffic conditions and user driving habits. The neural network can comprehensively consider multiple factors, such as traffic flow, road type, and user driving style, to provide accurate energy consumption predictions. Path screening is performed based on the predicted energy consumption and path score. The path score comprehensively considers travel time, energy consumption, and the convenience of charging stations. By scoring each possible path, the system selects the optimal path based on user preferences and real-time traffic conditions. This method ensures that users can not only complete their journey with the lowest energy consumption, but also charge at the most convenient charging station, improving overall travel efficiency and user experience. Exemplarily, in energy consumption prediction, this embodiment uses a long short-term memory network (LSTM) to process time series data. LSTM networks are particularly suitable for capturing long-term dependencies in time series, which is very important for analyzing traffic patterns and user behaviors. In this application, the LSTM network inputs a series of features, including historical traffic flow data, road types, user driving habits (such as acceleration and braking patterns), etc. Through training, the LSTM network can learn the complex relationship between these features and energy consumption, so that when given new input data, it can predict the energy consumption on different paths. This method can not only handle nonlinear relationships, but also adapt to dynamically changing traffic environments and provide more accurate energy consumption predictions.

[0067] Preferably, the road speed of the dynamic traffic model changes at intervals of 6 minutes, and there are 240 speed points in 24 hours a day.

[0068] Demonstratively, this embodiment can provide more detailed and accurate information on traffic flow changes, so that the model can reflect the dynamic changes of traffic conditions in real time and help identify peak and trough periods. Secondly, this fine-grained data helps to capture traffic events in a short period of time, such as accidents, construction or sudden congestion, thereby improving the efficiency of traffic management and emergency response. In addition, the rich data volume of 240 vehicle speed points provides a stronger statistical basis for subsequent analysis and prediction, so that the model can better take into account the traffic characteristics of different time periods when performing route planning and energy consumption prediction, thereby optimizing travel plans and improving users' travel experience and safety.

[0069] Preferably, the central control module includes:

[0070] A data preprocessing submodule, for performing denoising processing on the sensor signals of the motion state, position, environmental conditions of the helmet shell and the physiological state of the user of the helmet shell to obtain a denoised signal;

[0071] A signal feature extraction submodule performs feature extraction on each of the denoised signals to obtain extracted risk features;

[0072] A feature fusion submodule is used to fuse the risk features to obtain a fusion feature;

[0073] A risk judgment submodule is used to input the fusion features into a trained electric vehicle driving risk assessment model to perform collision detection and life judgment to obtain a detection and judgment result;

[0074] The alarm module is used to issue an alarm reminder according to the detection and judgment results.

[0075] Preferably, the data preprocessing submodule includes:

[0076] A signal translation unit, used for performing translation on the denoised signal to obtain a translation signal;

[0077] A wavelet decomposition unit, used for performing wavelet decomposition on the translation signal to obtain a plurality of wavelet coefficients;

[0078] A threshold determination unit, used to determine a filtering threshold according to a decomposition scale and a length of a signal;

[0079] A function determination unit, used for constructing a denoising function according to the filtering threshold;

[0080] The denoising unit is used to remove the noise of the translation signal by using the denoising function to obtain a denoised signal.

[0081] Specifically, the data preprocessing submodule of this embodiment receives sensor signals from the helmet shell, which include motion state, position, environmental conditions and the user's physiological state. By applying a filtering algorithm (such as Kalman filtering or wavelet transform), these signals are denoised to eliminate environmental interference and sensor noise to obtain a clear denoised signal. Next, the signal feature extraction submodule analyzes the denoised signal and extracts key risk features, such as acceleration changes, tilt angles and physiological parameters (such as heart rate). Then, the feature fusion submodule integrates these risk features to form a comprehensive feature set to more comprehensively reflect driving risks. The fused features are input into a trained electric vehicle driving risk assessment model, and the risk judgment submodule uses the model to perform collision detection and life state judgment, and finally generates a detection judgment result. Finally, the alarm module triggers the corresponding alarm reminder according to the judgment result to ensure timely notification of the user or surrounding personnel, thereby improving safety.

[0082] Preferably, the risk characteristics include: acceleration change rate, angular velocity, movement mode, GPS positioning data, geographical environment data, degree of deviation from the driving route, temperature, humidity, light, heart rate and body temperature.

[0083] Preferably, the communication module is also connected to the server wirelessly; the communication module is used to send the detection and judgment result to the server.

[0084] Specifically, the communication module of this embodiment integrates wireless communication technology, such as Wi-Fi, Bluetooth or cellular network (such as 4G / 5G), to establish a stable connection with the server. The wireless communication module built into the module will regularly check the network status and automatically connect to the preset server address when it detects that the network is available. In order to ensure the security of data transmission, the communication module uses encryption protocols (such as TLS / SSL) to encrypt the sent data to protect user privacy and data security.

[0085] Next, when the risk judgment submodule generates the detection judgment results, the communication module will package these results into data packets, which contain necessary information such as user ID, detection results, timestamp and location information. The format of the data packet adopts standard formats such as JSON or XML to facilitate server parsing and processing. Then, the communication module sends these data packets to the server through the wireless network, using protocols such as HTTP or MQTT for data transmission.

[0086] Once the server receives the data packet from the communication module, it will parse the data and perform corresponding processing according to the detection judgment result. If the judgment result shows that there is a potential danger or emergency, the server will immediately send an alarm notification to nearby rescuers or volunteers. This embodiment is implemented by push notifications, text messages or emails to ensure timely communication of information. In addition, the server also uses geographic information system (GIS) technology to analyze the user's location information, determine the nearest rescue resources, and feed back their information to the user or relevant personnel for rapid response and rescue.

[0087] Finally, in order to improve the reliability and response speed of the system, the communication module of this embodiment is designed to have a retransmission mechanism. When a data packet fails to successfully reach the server during the transmission process, the module will automatically retransmit to ensure that important detection and judgment results will not be lost. At the same time, the communication module also regularly sends a heartbeat signal to the server to maintain the stability of the connection and monitor the network status to ensure that data can be quickly transmitted in an emergency. Through these steps, the communication module can effectively send the detection and judgment results to the server, and provide timely rescue reminders through the server.

[0088] Preferably, the electric vehicle driving risk assessment model is obtained by training a CNN-LSTM network.

[0089] Specifically, the electric vehicle driving risk assessment model of this embodiment adopts the CNN-LSTM network architecture, combining the advantages of convolutional neural network (CNN) and long short-term memory network (LSTM) to achieve efficient assessment of driving risks. The operation and data processing process of the model are as follows:

[0090] First of all, data collection and preprocessing are the basis of model training. The system collects a variety of sensor data, including acceleration, speed, direction, environmental conditions (such as temperature, humidity), and the user's physiological state (such as heart rate, breathing rate). These data are usually time series data, so they need to be standardized to eliminate the influence between different dimensions. Next, the data will be divided into training sets, validation sets, and test sets for subsequent model training and evaluation.

[0091] In the specific operation of the model, CNN is first used to extract features from the input multi-dimensional sensor data. CNN can effectively capture spatial features in the data, such as acceleration changes and environmental impacts during driving. Through multiple convolutional layers and pooling layers, CNN extracts high-level feature representations that can reflect key changes in driving status.

[0092] The extracted features are then fed into the LSTM network. LSTM is a recurrent neural network suitable for processing time series data and can capture the time dependencies in the data. At this stage, LSTM analyzes the time series features of the driving process through memory cells and gating mechanisms to identify potential risk patterns. For example, LSTM learns the risk of collision that may occur under certain driving conditions (such as sudden acceleration or sudden braking).

[0093] Finally, after being processed by CNN and LSTM, the model outputs a risk assessment result, that is, a probability value, which indicates the risk level of an accident under the current driving state. This result is used for real-time monitoring and alarming, helping drivers to adjust their driving behavior in a timely manner and reduce the possibility of accidents. Through continuous training and optimization, the CNN-LSTM network can adapt to different driving scenarios and improve the accuracy and reliability of risk assessment.

[0094] The beneficial effects of the present invention are as follows:

[0095] (1) The present invention monitors the rider's motion state, environmental conditions and physiological state in real time through the sensor module, and can promptly detect potential dangerous situations such as collisions, falls or health problems.

[0096] (2) The present invention can perform collision detection and life judgment based on the collected data, and issue an alarm in time to remind the rider and surrounding people, thereby reducing the risk of accidents.

[0097] (3) The present invention provides users with optimal charging route planning based on real-time driving data and charging station distribution data, thereby reducing charging waiting time and improving travel efficiency.

[0098] (4) The present invention provides intuitive visual information and real-time voice navigation to help riders better understand the driving route and charging station locations, thereby improving the riding experience.

[0099] (5) By monitoring the physiological status of the rider (such as heart rate, body temperature, etc.), the system can detect health abnormalities in a timely manner, help the rider to manage themselves, and prevent health problems. The system can assess the rider's fatigue level and remind the user to rest in time to reduce the risk of accidents caused by fatigue.

[0100] (6) Through comprehensive analysis of motion status, environmental conditions and physiological status, the system can realize intelligent risk assessment and improve safety and reliability. The communication module is connected to the vehicle system of the electric motorcycle to obtain real-time driving data and traffic information, realizing more intelligent path planning and safety monitoring.

[0101] (7) The system of the present invention can adjust the monitoring and alarm strategies according to different environmental conditions (such as weather, road conditions, etc.) to ensure safety in various riding environments. The system can be expanded according to user needs, such as adding more sensors or integrating other smart devices to meet the needs of different users.

[0102] (8) The present invention enhances users' confidence in electric motorcycles by providing safety assurance and intelligent navigation, and promotes their popularization and application in urban transportation. It encourages users to use electric motorcycles and reduce the use of traditional fuel motorcycles, thus supporting environmental protection and sustainable development.

[0103] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0104] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An intelligent safety helmet system suitable for electric motorcycles, characterized in that: include: A helmet shell, a sensor module, a communication module, a display and audio module, a central control module, a power module and a charging navigation module arranged in the helmet shell; The sensor module, the display and audio module, the central control module, the power module and the charging navigation module are respectively connected to the communication module; the sensor module is used to collect the motion state, position, environmental conditions of the helmet shell and the physiological state of the user of the helmet shell; the power module is used to supply power to the sensor module, the communication module, the display and audio module, the central control module and the charging navigation module; The central control module is used to receive the motion state, position, environmental conditions of the helmet shell and the physiological state of the user of the helmet shell transmitted by the communication module, and perform collision detection and life judgment according to the motion state, position, environmental conditions and the physiological state, obtain the detection and judgment results, and issue an alarm reminder according to the detection and judgment results; The communication module is also connected to the vehicle system of the electric motorcycle corresponding to the helmet shell, and is used to obtain the real-time driving data, real-time traffic data and charging station distribution data of the electric motorcycle; the charging navigation module is used to plan the optimal charging path according to the real-time driving data, the real-time traffic data and the charging station distribution data, and obtain the optimal charging path; The display and audio module is used to perform visualization and real-time voice navigation based on the optimal charging path.

2. The intelligent safety helmet system for electric motorcycles according to claim 1, characterized in that: The charging navigation module includes: A traffic model building submodule is used to build a dynamic traffic model with dynamic changes in road network vehicle speed based on the real-time traffic data and a preset static road network; A user behavior model establishment submodule, used to establish a user behavior analysis model based on preset historical riding data and user power preference data in the vehicle system; The energy consumption prediction and path planning submodule is used to predict the energy consumption on different paths using a neural network based on the dynamic traffic model and the user behavior analysis model, score the paths according to user preferences and real-time traffic conditions, and comprehensively consider travel time, energy consumption, and convenience of charging stations to obtain path scores and predicted energy consumption; The optimal route determination submodule is used to screen the paths according to the path score and the predicted energy consumption to obtain the optimal charging path.

3. The intelligent safety helmet system for electric motorcycles according to claim 1, characterized in that: The road speed of the dynamic traffic model changes at intervals of 6 minutes, and there are 240 speed points in 24 hours a day.

4. The intelligent safety helmet system for electric motorcycles according to claim 1, characterized in that: The central control module comprises: A data preprocessing submodule, for performing denoising processing on the sensor signals of the motion state, position, environmental conditions of the helmet shell and the physiological state of the user of the helmet shell to obtain a denoised signal; A signal feature extraction submodule performs feature extraction on each of the denoised signals to obtain extracted risk features; A feature fusion submodule is used to fuse the risk features to obtain a fusion feature; A risk judgment submodule is used to input the fusion features into a trained electric vehicle driving risk assessment model to perform collision detection and life judgment to obtain a detection and judgment result; The alarm module is used to issue an alarm reminder according to the detection and judgment results.

5. The intelligent safety helmet system for electric motorcycles according to claim 4, characterized in that: The data preprocessing submodule includes: A signal translation unit, used for performing translation on the denoised signal to obtain a translation signal; A wavelet decomposition unit, used for performing wavelet decomposition on the translation signal to obtain a plurality of wavelet coefficients; A threshold determination unit, used to determine a filtering threshold according to a decomposition scale and a length of a signal; A function determination unit, used for constructing a denoising function according to the filtering threshold; The denoising unit is used to remove the noise of the translation signal by using the denoising function to obtain a denoised signal.

6. The intelligent safety helmet system for electric motorcycles according to claim 4, characterized in that: The risk characteristics include: acceleration change rate, angular velocity, movement pattern, GPS positioning data, geographic environment data, degree of deviation from the driving route, temperature, humidity, light, heart rate and body temperature.

7. The intelligent safety helmet system for electric motorcycles according to claim 4, characterized in that: The communication module is also connected to the server wirelessly; the communication module is used to send the detection and judgment results to the server.

8. The intelligent safety helmet system for electric motorcycles according to claim 4, characterized in that: The electric vehicle driving risk assessment model is obtained by training the CNN-LSTM network.

Images