Riding protection method based on AI and multi-source data analysis

Abstract

The invention belongs to the technical field of riding protection equipment, and particularly provides a riding protection method based on AI and multi-source data analysis, and the method comprises the steps: obtaining current environment data; acquiring attitude data and image data acquired by an attitude analysis module and an image acquisition module in real time; inputting the current environment data, the posture data and the image data into an AI analysis model to calculate a current danger level; if the current danger level reaches a preset threshold value, a warning signal is sent to an interaction module of a user, and the threshold value change of the current danger level is obtained in real time; if the threshold value of the current danger level is continuously increased, the warning signal is upgraded, and a protection pre-starting signal is sent to the protection module, so that the protection module enters a warning state; the attitude data acquired by the attitude analysis module is acquired in real time, and when it is detected that the attitude data exceeds a preset threshold value, the protection module is triggered to be started. And the protection module is triggered to perform active protection by analyzing the attitude data, so that the protection level of the rider is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of cycling protection equipment, and specifically relates to a cycling protection method based on AI and multi-source data analysis. Background Art

[0002] In recent years, cycling for fun (including but not limited to track racing, off-road / cross / track difficulty competitions, and long-distance motorcycle tours) has become a growing trend. Products and industries oriented towards "cycling for fun" are booming. Consequently, the balance between cycling safety, efficiency, and environmental friendliness has become increasingly prominent, becoming a key factor influencing and even restricting the further development of cycling as a leisure sport. Furthermore, recent technological advances in the IT industry and breakthroughs in the informatization of "people and the environment" have made it possible to introduce new technologies, transform, and optimize cycling's safety and environmental friendliness.

[0003] In existing technical solutions, the helmet serves as a protection center, information center, and interaction center, playing the role of more information assistance and information transmission. However, as a protection, it still mainly relies on very traditional head protection and passive protection.

[0004] Similarly, regarding the safety protection of other parts of the rider, new product ideas in recent years have also made great progress and breakthroughs with reference to the passive safety protection products of vehicles. Key vulnerable parts have been strengthened, and very mature passive safety protection equipment such as airbags have been developed. However, there is no effective interaction and connection with the environmental perception of modern information technology (mostly concentrated in helmets), and active safety protection cannot be achieved. As a result, the protection level of the entire rider is still stuck in the traditional passive protection era, with very low protection efficiency and the protection effect cannot meet the protection requirements of riding.

[0005] Based on this, the present invention provides a cycling protection method based on AI and multi-source data analysis to solve the above problems. Summary of the Invention

[0006] In order to overcome the shortcomings of the existing technology, the present invention provides a cycling protection method based on AI and multi-source data analysis to solve the problems in the existing technology.

[0007] One embodiment of the present invention provides a cycling protection method based on AI and multi-source data analysis, comprising the following steps:

[0008] Get current environment data;

[0009] Acquire the posture data and image data collected in real time by the posture analysis module and the image acquisition module;

[0010] Inputting the current environment data, posture data, and image data into an AI analysis model to calculate the current danger level;

[0011] Based on the calculation results of the AI ​​analysis model, if the current danger level reaches the preset threshold, a warning signal is sent to the user's interactive module and the threshold changes of the current danger level are obtained in real time;

[0012] If the threshold of the current danger level continues to increase within a preset time, the warning signal is upgraded and a protection pre-start signal is sent to the protection module, causing the protection module to enter an alert state;

[0013] The posture data collected by the posture analysis module is acquired in real time, and when it is detected that the posture data exceeds a preset threshold, the protection module is triggered to start.

[0014] In one embodiment, the step of acquiring the posture data collected by the posture analysis module in real time and triggering the activation of the protection module when the posture data exceeds a preset threshold value further includes the following steps:

[0015] Continuously obtain posture data collected by the posture analysis module;

[0016] If the posture data fluctuates continuously and does not return to a preset threshold range within a preset time, a start signal is sent to the sound and light warning module, and the sound and light warning module receives the start signal and sends a sound and light warning signal to the outside.

[0017] In one embodiment, the step of acquiring the posture data collected by the posture analysis module in real time and triggering the activation of the protection module when the posture data exceeds a preset threshold value further includes the following steps:

[0018] Continuously obtain posture data collected by the posture analysis module;

[0019] If the posture data fluctuates continuously and does not return to the preset threshold range within the preset time, a start signal is sent to the communication module. The communication module receives the start signal and sends an alarm signal containing location information and vital signs information to the emergency center.

[0020] In one embodiment, the step of obtaining the posture data and image data collected in real time by the posture analysis module and the image acquisition module further includes:

[0021] If the posture data exceeds a preset threshold, a warning signal is sent to the user interaction module and a protection pre-start signal is sent to the protection module, so that the protection module enters an alert state.

[0022] In one embodiment, in the step of acquiring the posture data collected by the posture analysis module in real time and triggering the protection module to start when detecting that the posture data exceeds a preset threshold:

[0023] The protection module includes a helmet protection component and a protective clothing component;

[0024] The helmet protection component is connected to the protective clothing component by wire or wirelessly, and the protective clothing component is provided with an airbag;

[0025] When it is detected that the posture data exceeds a preset threshold, the airbag inside the protective clothing component is triggered to start.

[0026] In one embodiment, in the step of sending a warning signal to the user's interaction module and obtaining the threshold change of the current danger level in real time based on the calculation result of the AI ​​analysis model if the current danger level reaches a preset threshold:

[0027] The interactive module includes an eyepiece component and an interactive component;

[0028] The eyepiece component and the interactive component are both arranged on the helmet protective component and are used for real-time display of warning information and voice interaction.

[0029] In one embodiment, in the step of acquiring the posture data and image data collected in real time by the posture analysis module and the image acquisition module:

[0030] The image acquisition module includes a 360° camera component provided on the helmet protective component;

[0031] The posture analysis module includes a gyroscope component arranged on a helmet protection component, a protective clothing component and a vehicle body.

[0032] In one embodiment, if the posture data fluctuates continuously and does not return to a preset threshold range within a preset time, a start signal is sent to the sound and light warning module, and the sound and light warning module receives the start signal and sends an sound and light warning signal to the outside:

[0033] The sound and light warning module includes an acoustic component and an optical component;

[0034] The acoustic component is provided in the protective helmet component;

[0035] The optical components are arranged on both the protective helmet component and the protective clothing component.

[0036] In one embodiment, a power module is provided inside the protective clothing component.

[0037] The cycling protection method based on AI and multi-source data analysis provided in the above embodiment has the following advantages:

[0038] Beneficial effects:

[0039] 1. By obtaining current environmental data, real-time posture data and image data and inputting them into the AI ​​analysis model, the current danger level is calculated. Based on the danger level, it can automatically determine whether the rider is currently in danger.

[0040] 2. When the danger level is calculated and reaches the preset threshold, a warning signal can be sent to the rider to remind the rider of potential risks and prompt them to take evasive actions to achieve the effect of early warning. At the same time, attention is paid to whether the danger level changes after the warning signal is issued; if the danger level value continues to increase, an upgraded warning signal is sent to the rider, and a pre-start signal is sent to the rider's protection module, so that the protection module enters the alert state, so that the protection module can be quickly started before the danger occurs. At the same time, after the protection module is in the alert state, it continues to pay attention to the rider's posture data. Once a change in the rider's posture data is detected, the protection module is triggered to fully start, achieving the effect of active protection, thereby increasing the protection energy efficiency and meeting the rider's riding protection requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 the structures shown in these drawings without paying any creative work.

[0042] Figure 1 A flowchart of a cycling protection method based on AI and multi-source data analysis provided by an embodiment of the present invention;

[0043] Figure 2 Schematic diagram of the protection module of the cycling protection method based on AI and multi-source data analysis provided in an embodiment of the present invention.

[0044] Figure Number:

[0045] 100. Helmet protection components; 200. Protective clothing components; 300. Airbag; 400. Eyepiece components; 500. Interactive components; 600. Camera components; 700. Gyroscope components; 800. Acoustic components; 900. Optical components. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0047] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0048] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features limited to "first" and "second" may explicitly or implicitly include at least one of such features. In addition, if "and / or" or "and / or" appears in the full text, its meaning includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0049] Reference Figure 1 One embodiment of the present invention provides a cycling protection method based on AI and multi-source data analysis, comprising the following steps:

[0050] S10, obtaining current environment data;

[0051] S20, acquiring the posture data and image data collected in real time by the posture analysis module and the image acquisition module;

[0052] S30, inputting the current environment data, posture data, and image data into an AI analysis model to calculate the current danger level;

[0053] S40. Based on the calculation results of the AI ​​analysis model, if the current danger level reaches a preset threshold, a warning signal is sent to the user's interaction module and the threshold change of the current danger level is obtained in real time;

[0054] S50, if the threshold of the current danger level continues to increase within a preset time, upgrading the warning signal and sending a protection pre-start signal to the protection module, so that the protection module enters an alert state;

[0055] S60: Acquire the posture data collected by the posture analysis module in real time, and trigger the protection module to start when it is detected that the posture data exceeds a preset threshold.

[0056] In this embodiment, as in the above steps S10 to S60, refer to Figure 2 :

[0057] The protection module includes a helmet protection component 100 and a protective clothing component 200; the helmet protection component 100 and the protective clothing component 200 are connected by wire or wirelessly for data transmission. An airbag 300 is arranged in the protective clothing component 200. There are several airbags 300, such as those arranged in important positions such as the elbows and joints of the protective clothing component 200.

[0058] The interactive module includes an eyepiece component 400 and an interactive component 500; the eyepiece component 400 and the interactive component 500 are both arranged on the helmet protective component 100, and are used to display warning information and voice interaction in real time. The eyepiece component 400 is an optical waveguide AR eyepiece, and the prompt information sent at critical moments is displayed on the AR eyepiece. The interactive component 500 is acoustic interaction, including headphones and a microphone.

[0059] The image acquisition module includes a 360° camera component 600 arranged on the helmet protective component 100, which is composed of multiple cameras and is used for 360° all-round real-time image capture; the posture analysis module includes a gyroscope component 700 arranged on the helmet protective component 100, the protective clothing component 200 and the vehicle body, which is used to detect the angle change data between the rider, the vehicle body and the ground plane.

[0060] The sound and light warning module includes an acoustic component 800 and an optical component 900; the acoustic component 800 is set in the protective helmet component 100 and is a speaker; the optical component 900 is set in both the protective helmet component 100 and the protective clothing component 200, and includes an LED light group and reflective / fluorescent cloth.

[0061] The protective clothing component 200 is internally provided with a power supply module for providing electrical energy to the above components.

[0062] Furthermore, the protective helmet component 100 is also provided with a wireless transmission module and a communication module for data interaction with the cloud.

[0063] Furthermore, as needed, the protective clothing component 200 is provided with a vibration module for performing local vibration when prompting the rider to achieve a tactile feedback effect.

[0064] Furthermore, as needed, the protective clothing component 200 is provided with a temperature control module for cooling and heating the protective clothing component 200 .

[0065] As described in step S10 above, the current environmental data includes basic condition data such as the rider's current road traffic conditions, location, navigation, weather, humidity, etc., which are acquired by the first data acquisition module.

[0066] As described in the above step S20, the posture data includes the angle change data between the rider, the vehicle body and the ground plane collected by the posture analysis module, and the image data includes the full-angle image data around the rider collected by the image acquisition module and the vehicle speed data displayed on the vehicle instrument panel, which are acquired by the second data acquisition module.

[0067] As described in step S30 above, the AI ​​analysis model and the pre-trained machine learning model use data such as the relative position / relative acceleration / acceleration discrimination of the angle and arc motion of the vehicle body during cornering / bending, as well as data such as the head and body posture of the rider during cornering as training data for the model. The acquired current environment data, posture data, and image data are input into the trained AI analysis model, and the current danger level is calculated and analyzed by the AI ​​analysis model; the current environment data, posture data, and image data are used as the basis for calculation and analysis to increase the accuracy. For the danger level, multiple danger levels can be preset; if they are divided into three danger levels: low, medium, and high, at a low danger level, the rider is warned; at a medium danger level, the warning is upgraded and the protection module is pre-started; at a high danger level, the protection module is triggered to start, with the scenario of an obstacle in front of the rider as the following:

[0068] The preset thresholds for triggering low-risk conditions are:

[0069] Obstacle distance: 20 meters ≤ distance < 30 meters; relative speed: 20 km / h ≤ speed < 30 km / h; environmental conditions: dry road surface and good visibility.

[0070] The preset thresholds for triggering the medium hazard level are:

[0071] Obstacle distance: 10 meters ≤ distance < 20 meters; relative speed: 30km / h ≤ speed < 50km / h; environmental conditions: slippery road surface, average visibility.

[0072] The preset thresholds for triggering high-risk conditions are:

[0073] Obstacle distance: <10 meters; relative speed: ≥50 km / h; environmental conditions: icy road surface, extremely low visibility.

[0074] As described in step S40 above, based on the calculation results of the AI ​​analysis model, if the current value is "obstacle distance 20 meters ≤ distance < 30 meters and relative speed 20 km / h ≤ speed < 30 km / h", when the danger level reaches the preset threshold of the low danger level, a warning signal is sent to the rider's interaction module. The rider's interaction module receives the warning signal and plays a warning prompt, such as a voice prompt played in the earphones: "There is an obstacle / pedestrian / vehicle ahead, please pay attention to avoid it" or the dangerous direction is displayed through the optical waveguide AR eyepiece (such as a highlighted prompt of the obstacle in front of the left), which reminds the rider of potential risks and prompts him to take evasive action. After prompting the rider, the threshold change of the current danger level is continuously monitored to determine whether the rider takes corresponding braking measures to reduce the threshold of the current danger level after prompting the rider.

[0075] As described in step S50 above, after the rider is prompted, if the rider fails to take appropriate braking measures within a preset time, for example, 2 seconds, causing the danger level threshold to increase, the warning signal is upgraded. For example, the yellow warning originally sent to the rider's AR eyepiece is now upgraded to a red flashing warning, and the earphones emit a high-frequency alarm sound. If necessary, a start signal can also be sent to the vibration module in the cycling suit component, and the vibration module further provides tactile feedback to the rider. In addition, a protection pre-start signal is sent to the protection module to put the protection module into an alert state. For example, a protection pre-start signal is sent to the protective suit component to pre-inflate the airbag inside the protective suit, tightening the cycling suit and entering an alert state, providing preventive protection for the rider to prevent the airbag from deploying after the accident, at which time the rider may be in danger.

[0076] As described in the above step S60, after the protection module enters the alert state, the posture data collected by the posture analysis module is obtained in real time to analyze whether the posture data fluctuates. If fluctuations occur, for example, the angles between the rider, the vehicle body and the ground plane change and show a decreasing trend, the protection module is triggered to fully start, avoiding the airbag popping out after the rider falls.

[0077] As in the above steps S10 to S60, substitute the actual scenario for explanation:

[0078] Scenario description: A rider is riding on a mountain road in the rain at a speed of 30 km / h. The system detects fallen rocks on a bend 30 meters ahead and the slippery road surface causes the tire grip to decrease.

[0079] Process execution: The rider's AR eyepiece displays the location of fallen rocks on the curve (highlighted in yellow), and the headset voice prompts: "There are fallen rocks on the curve, the road is slippery, it is recommended to slow down to below 20 km / h."

[0080] When the distance to the obstacle ahead gradually decreases and the rider does not take corresponding braking measures or the vehicle is still moving at a high speed, an upgraded warning signal is triggered, the AR eyepiece switches to a red flashing alarm, and the headset voice prompts "slow down immediately", and the airbag of the cycling suit is pre-inflated.

[0081] When a fluctuation in posture data is detected, such as when a rider loses control due to slipping on the road, the gyroscope detects that the body of the vehicle has tilted significantly and has not recovered. At this time, the airbag in the cycling suit is triggered to fully deploy to protect the rider.

[0082] In one embodiment, step S60 further includes the following steps:

[0083] S70A, continuously acquiring posture data collected by the posture analysis module;

[0084] S71A: If the posture data continuously fluctuates and does not return to the preset threshold range within the preset time, a start signal is sent to the sound and light warning module, and the sound and light warning module receives the start signal and sends a sound and light warning signal to the outside.

[0085] In this embodiment, after the protection module is triggered to be fully started, the rider's posture data is continuously obtained to analyze whether the rider has slipped. If there is a continuous fluctuation in the posture data and it does not return to the preset threshold range within a preset time, such as 60s, it means that the rider may have slipped and has not recovered. To avoid further danger, a start signal is sent to the sound and light warning module. The sound and light warning module receives the start signal and sends a sound and light warning signal to the outside. For example, the speaker in the protective helmet component sends a high-decibel alarm to the outside world, and the LED light group in the protective component of the cycling suit emits a strong flashing light to attract the attention of the surrounding.

[0086] In one embodiment, step S60 further includes the following steps:

[0087] S70B, continuously acquiring posture data collected by the posture analysis module;

[0088] S71B: If the posture data fluctuates continuously and does not return to the preset threshold range within the preset time, a start signal is sent to the communication module. The communication module receives the start signal and sends an alarm signal containing location information and vital signs information to the emergency center.

[0089] In this embodiment, after the protection module is triggered and fully started, the rider's posture data is continuously obtained to analyze whether the rider has slipped. If there is a continuous fluctuation in the posture data and it does not return to the preset threshold range within a preset time, such as 60s, it means that the rider may have slipped and has not recovered. To avoid further danger, a start signal is sent to the communication module. The communication module receives the start signal and sends an alarm signal containing location information and vital signs information to the emergency center. The vital signs information can be detected by the rider's wearable bracelet, including heart rate, blood pressure, blood oxygen, etc.; thereby providing further safety protection for the rider.

[0090] In one embodiment, step S20 further includes:

[0091] S21. If the posture data exceeds a preset threshold, a warning signal is sent to the user interaction module and a protection pre-start signal is sent to the protection module, so that the protection module enters an alert state.

[0092] In this embodiment, when collecting the rider's posture data, if the posture data exceeds a preset threshold, it means that the rider may be in danger, and a red flashing warning is directly sent to the rider's AR eyepiece. At the same time, the earphones emit a high-frequency alarm sound, and a protective pre-start signal is sent to the protective clothing components. The airbag inside the protective clothing is pre-inflated, causing the cycling suit to tighten and enter an alert state to provide preventive protection for the rider.

[0093] Furthermore, it also involves a cycling protection system based on AI and multi-source data analysis, including:

[0094] A first data acquisition module is used to acquire current environment data;

[0095] A second data acquisition module is used to acquire the posture data and image data collected in real time by the posture analysis module and the image acquisition module;

[0096] An analysis module, configured to input the current environment data, posture data, and image data into an AI analysis model to calculate the current danger level;

[0097] The first generation module is used to send a warning signal to the user interaction module and obtain the threshold change of the current danger level in real time if the current danger level reaches the preset threshold based on the calculation results of the AI ​​analysis model;

[0098] The second generating module is configured to upgrade the warning signal and send a protection pre-start signal to the protection module if the current danger level threshold continues to increase within a preset time, so that the protection module enters an alert state;

[0099] The trigger module is used to obtain the posture data collected by the posture analysis module in real time, and when it is detected that the posture data exceeds a preset threshold, the protection module is triggered to start.

[0100] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A cycling protection method based on AI and multi-source data analysis, characterized in that: The steps include: Get current environment data; Acquire the posture data and image data collected in real time by the posture analysis module and the image acquisition module; Inputting the current environment data, posture data, and image data into an AI analysis model to calculate the current danger level; Based on the calculation results of the AI ​​analysis model, if the current danger level reaches the preset threshold, a warning signal is sent to the user's interactive module and the threshold changes of the current danger level are obtained in real time; If the threshold of the current danger level continues to increase within a preset time, the warning signal is upgraded and a protection pre-start signal is sent to the protection module, causing the protection module to enter an alert state; The posture data collected by the posture analysis module is acquired in real time, and when it is detected that the posture data exceeds a preset threshold, the protection module is triggered to start.

2. The cycling protection method based on AI and multi-source data analysis according to claim 1 is characterized in that: The step of acquiring the posture data collected by the posture analysis module in real time and triggering the protection module to start when the posture data exceeds a preset threshold value also includes the following steps: Continuously obtain posture data collected by the posture analysis module; If the posture data fluctuates continuously and does not return to a preset threshold range within a preset time, a start signal is sent to the sound and light warning module, and the sound and light warning module receives the start signal and sends a sound and light warning signal to the outside.

3. The cycling protection method based on AI and multi-source data analysis according to claim 1 is characterized in that: The step of acquiring the posture data collected by the posture analysis module in real time and triggering the protection module to start when the posture data exceeds a preset threshold value also includes the following steps: Continuously obtain posture data collected by the posture analysis module; If the posture data fluctuates continuously and does not return to the preset threshold range within the preset time, a start signal is sent to the communication module. The communication module receives the start signal and sends an alarm signal containing location information and vital signs information to the emergency center.

4. The cycling protection method based on AI and multi-source data analysis according to claim 1 is characterized in that: The step of obtaining the posture data and image data collected in real time by the posture analysis module and the image acquisition module further includes: If the posture data exceeds a preset threshold, a warning signal is sent to the user interaction module and a protection pre-start signal is sent to the protection module, so that the protection module enters an alert state.

5. The cycling protection method based on AI and multi-source data analysis according to claim 2, characterized in that: In the step of acquiring the posture data collected by the posture analysis module in real time and triggering the protection module to start when it is detected that the posture data exceeds a preset threshold: The protection module includes a helmet protection component and a protective clothing component; The helmet protection component is connected to the protective clothing component by wire or wirelessly, and the protective clothing component is provided with an airbag; When it is detected that the posture data exceeds a preset threshold, the airbag inside the protective clothing component is triggered to start.

6. The cycling protection method based on AI and multi-source data analysis according to claim 5 is characterized in that: In the step of sending a warning signal to the user's interaction module and obtaining the threshold change of the current danger level in real time based on the calculation result of the AI ​​analysis model if the current danger level reaches the preset threshold: The interactive module includes an eyepiece component and an interactive component; The eyepiece component and the interactive component are both arranged on the helmet protective component and are used for real-time display of warning information and voice interaction.

7. The cycling protection method based on AI and multi-source data analysis according to claim 5, characterized in that: In the step of obtaining the posture data and image data collected in real time by the posture analysis module and the image acquisition module: The image acquisition module includes a 360° camera component provided on the helmet protective component; The posture analysis module includes a gyroscope component arranged on a helmet protection component, a protective clothing component and a vehicle body.

8. The cycling protection method based on AI and multi-source data analysis according to claim 5 is characterized in that: If the posture data fluctuates continuously and does not return to a preset threshold value within a preset time, a start signal is sent to the sound and light warning module, and the sound and light warning module receives the start signal and sends an sound and light warning signal to the outside: The sound and light warning module includes an acoustic component and an optical component; The acoustic component is provided in the protective helmet component; The optical components are arranged on both the protective helmet component and the protective clothing component.

9. The cycling protection method based on AI and multi-source data analysis according to any one of claims 5 to 8, characterized in that: A power supply module is provided inside the protective clothing component.

Images